Skip to content

Proof Holdings MCP server

holdings.proof/mcp-serverproof.holdingsstreamable-httpv1.13.0Scanned

One API, all things verified — control, delegation, human approval, anti-impersonation.

219 tools: 60 can delete or cancel things, 10 do something that can't be undone, 52 change things and 97 only read.

Tools: 60 delete, 10 irreversible, 52 write, 97 read.
  • Reads private data · 11
  • Reads text others write · 11
  • Can send data out · 31
  • 27 findings, 1 high

Tools listed without sign-in. Remote posture

With Anlyon

60 tools here can delete or cancel things and 10 do something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Proof Holdings MCP server can do

The Proof Holdings MCP server is published by proof.holdings, a domain the MCP Registry verified. It has 219 tools. It can delete or cancel things (60 tools: delete_domain_verification, cancel_verification_request, revoke_proof, pause_proof and 56 more), do things that cannot be undone, such as sending, paying or publishing (resend_verification, resend_email_otp, verify_domain_with_credentials, resend_domain_email and 6 more) and create or change data (52 tools: create_verification, trigger_verification, submit_verification_code, test_verify and 48 more). 97 tools only read.

11 tools read private data (get_company, list_templates, get_default_templates and 8 more); 11 tools bring in text other people can write (get_company, list_templates, get_default_templates and 8 more); 31 tools can send data out of your system (create_verification, resend_verification, create_multi_channel_verification and 28 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 27 findings, 1 of them high severity (credentials-mention, long-description, annotation-conflict and model-directed-text). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 8 times since Anlyon Radar first saw them.

Last scanned Nov 16, 2026, version 1.13.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

219 tools

Deletes or cancels 60Claude Code: deny
  • add_verification_providerAdd an additional DNS provider for verification to an already-verified domain.3 findings

    Why it is in this group

    • The name "add_verification_provider" says "add": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...on to an already-verified domain. Note: credentials will be visible in the AI conversation..."

      What this check looks for
    • Info

      The input schema at properties.credentials.description mentions "credential".

      Matched text

      inputSchema.properties.credentials.description: "Provider-specific credential key-value pairs"

      What this check looks for
    • Info

      The input schema at required[2] mentions "credentials".

      Matched text

      inputSchema.required[2]: "credentials"

      What this check looks for
    Description, as the server wrote it
    Add an additional DNS provider for verification to an already-verified domain. Note: credentials will be visible in the AI conversation context. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • archive_approval_channelDelete (archive) an approval channel.No findings

    Why it is in this group

    • The name "archive_approval_channel" says "archive": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Delete (archive) an approval channel. Sets status to archived. Cannot be used for new confirmations after deletion. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • cancel_lookalike_watchTurn Lookalike Watch off.No findings

    Why it is in this group

    • The name "cancel_lookalike_watch" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Turn Lookalike Watch off. The subscription is kept as canceled and returned in the same shape get_lookalike_watch reads; past alerts and reports stay readable. 404 when not subscribed. Needs lookalike-watch:write on an account-wide key. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • cancel_user_requestCancel a pending verification request.No findings

    Why it is in this group

    • The name "cancel_user_request" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Cancel a pending verification request. Only the creator can cancel. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • cancel_verification_requestCancel a pending verification request.No findings

    Why it is in this group

    • The name "cancel_verification_request" says "cancel": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Cancel a pending verification request. Only pending requests can be cancelled. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • connect_cloudflareConnect a Cloudflare API token to a domain: the server publishes the verification record through it.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Connect a Cloudflare API token to a domain: the server publishes the verification record through it. The domain is verified once that record is live in public DNS — often at once, else status "verifying" while the server keeps checking (call get_domain). Note: the API token will be visible in the AI conversation context. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • connect_dns_providerConnect a generic DNS provider to a domain using provider-specific credentials.3 findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...der to a domain using provider-specific credentials. The server publishes the verification..."

      What this check looks for
    • Info

      The input schema at properties.credentials.description mentions "credential".

      Matched text

      inputSchema.properties.credentials.description: "Provider-specific credential key-value pairs"

      What this check looks for
    • Info

      The input schema at required[2] mentions "credentials".

      Matched text

      inputSchema.required[2]: "credentials"

      What this check looks for
    Description, as the server wrote it
    Connect a generic DNS provider to a domain using provider-specific credentials. The server publishes the verification record through it; the domain is verified once that record is live in public DNS — often at once, else status "verifying" while the server keeps checking (call get_domain). Note: credentials will be visible in the AI conversation context. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • connect_godaddyConnect GoDaddy credentials to a domain: a Personal Access Token (api_token, permissions domains.domain:read and domains.dns:update), or a Production API key with its secret.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "Connect GoDaddy credentials to a domain: a Personal Access Token (a..."

      What this check looks for
    Description, as the server wrote it
    Connect GoDaddy credentials to a domain: a Personal Access Token (api_token, permissions domains.domain:read and domains.dns:update), or a Production API key with its secret. The server publishes the verification record through it; the domain is verified once that record is live in public DNS — often at once, else status "verifying" while the server keeps checking (call get_domain). Note: the credentials will be visible in the AI conversation context. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • create_dns_credentialStore DNS provider credentials for automated domain verification.3 findings

    Why it is in this group

    • The name "create_dns_credential" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "Store DNS provider credentials for automated domain verification. Note..."

      What this check looks for
    • Info

      The input schema at properties.credentials.description mentions "credential".

      Matched text

      inputSchema.properties.credentials.description: "Provider-specific credential key-value pairs"

      What this check looks for
    • Info

      The input schema at required[1] mentions "credentials".

      Matched text

      inputSchema.required[1]: "credentials"

      What this check looks for
    Description, as the server wrote it
    Store DNS provider credentials for automated domain verification. Note: credentials will be visible in the AI conversation context. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • create_profileDeprecated: use create_sub_accountNo findings

    Why it is in this group

    • The name "create_profile" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use create_sub_account

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • create_sub_accountCreate a new sub-account with optional display name, bio, avatar, business info, email branding (theme, support email), and theme settings.No findings

    Why it is in this group

    • The name "create_sub_account" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Create a new sub-account with optional display name, bio, avatar, business info, email branding (theme, support email), and theme settings. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_approval_channel_keysDelete the encryption keypair from an approval channel.No findings

    Why it is in this group

    • The name "delete_approval_channel_keys" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Delete the encryption keypair from an approval channel. WARNING: Existing ciphertexts will become permanently unreadable. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_circleArchive a Circle (soft delete — sets status to archived).No findings

    Why it is in this group

    • The name "delete_circle" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Archive a Circle (soft delete — sets status to archived). It stops appearing in the default list but is recoverable via list_circles with status="archived". ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_dns_credentialDelete a stored DNS provider credential.2 findings

    Why it is in this group

    • The name "delete_dns_credential" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "Delete a stored DNS provider credential. Domains using this credential will nee..."

      What this check looks for
    • Info

      The input schema at properties.id.description mentions "credential".

      Matched text

      inputSchema.properties.id.description: "DNS credential ID to delete"

      What this check looks for
    Description, as the server wrote it
    Delete a stored DNS provider credential. Domains using this credential will need new credentials for automated verification. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_domainRemove a domain from the account.No findings

    Why it is in this group

    • The name "delete_domain" says "delete": a word for removing or ending something.
    • The description says "Cannot be undone".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove a domain from the account. Revokes every proof of the domain and every delegation issued from it (for good — re-adding the domain does not bring them back), deletes the domain and its records, and removes our _proof TXT record and the Resend sending domain where we can; the response lists what is left for you to remove by hand. Owner only, in a start_login session, with one code: start_2fa_for_action with action_type domain_remove and targets [this domain id]. Need only a fresh proof? Revoke the proofs instead (revoke_my_proof), which keeps the domain. Cannot be undone. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_domain_verificationDelete a domain verification attempt that is not verified (pending, verifying or failed) — nothing is revoked.No findings

    Why it is in this group

    • The name "delete_domain_verification" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Delete a domain verification attempt that is not verified (pending, verifying or failed) — nothing is revoked. A verified domain, or one that needs re-verification, is refused with domain_verified: removing it revokes its proofs and every delegation issued from it, which is delete_domain in a start_login session (or the dashboard). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_hitlDeprecated: use archive_approval_channelNo findings

    Why it is in this group

    • The name "delete_hitl" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use archive_approval_channel

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_hitl_keysDeprecated: use delete_approval_channel_keysNo findings

    Why it is in this group

    • The name "delete_hitl_keys" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use delete_approval_channel_keys

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_profileDeprecated: use delete_sub_accountNo findings

    Why it is in this group

    • The name "delete_profile" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use delete_sub_account

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_sub_accountDelete a sub-account.No findings

    Why it is in this group

    • The name "delete_sub_account" says "delete": a word for removing or ending something.
    • The description says "irreversible".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Delete a sub-account. Revokes its API keys, archives the approval channels and declines the pending requests created with its own keys, keeps its history but unlinks it, deletes its message templates, and retires its username for good. The last sub-account cannot be deleted; deleting the primary sub-account makes the oldest remaining one primary (the response names it). In a start_login session: one code first — start_2fa_for_action with action_type profile_delete and targets [this sub-account id]. With an API key alone only an EMPTY sub-account (no API keys, approval channels or pending requests) can be deleted; anything else answers owner_session_required. archive_default_linked is deliberately not offered here: archiving or cancelling everything linked only by default is an irreversible fan-out, so archive each item explicitly instead. Cannot be undone. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), or sign in with start_login — either opens this tool — then call this tool again.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_templateDelete a sub-account's custom template, reverting that sub-account to the default template for the channel and message type.No findings

    Why it is in this group

    • The name "delete_template" says "delete": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Delete a sub-account's custom template, reverting that sub-account to the default template for the channel and message type. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • delete_webhook_endpointDelete a webhook endpoint.No findings

    Why it is in this group

    • The name "delete_webhook_endpoint" says "delete": a word for removing or ending something.
    • The description says "Cannot be undone".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Delete a webhook endpoint. It receives no new events; deliveries already queued to it are still attempted, signed with the secret they were queued with. Cannot be undone. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • pause_proofPause a proof by its public handle (ph_ctl_* / ph_dlg_*) or a verification ID — a reversible stop, undone with resume_proof.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Pause a proof by its public handle (ph_ctl_* / ph_dlg_*) or a verification ID — a reversible stop, undone with resume_proof. While paused the proof is invalid: the status endpoint, the public validator and the Token Status List report it suspended; it is deliberately NOT put on the revocation list. Only an active proof can be paused (already_suspended, proof_expired or proof_revoked otherwise). Pausing a delegation (ph_dlg_*) stops a live publisher's tools: an MCP server running the Proof delegation gate refuses its tool calls once its next status check sees the pause (self-refusal). Pausing a domain CONTROL proof hides every delegation issued from it until it is resumed; nothing is revoked. The API key needs proofs:write, plus delegations:write for a ph_dlg_* or while delegations under a control proof are live. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • regenerate_api_keyRegenerate an API key: issues a new key (a new id and secret) with the same name, environment, scopes and sub-account.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Regenerate an API key: issues a new key (a new id and secret) with the same name, environment, scopes and sub-account. The new key expires when the old one would have (expires_at in this response). A key whose expires_at has passed (see list_api_keys) is refused (api_key_expired), so check it before starting 2FA: for a key an MCP sign-in minted the message reads "This key expired on <day>. Connect your AI client again to get a new one."; for any other key, "This key expired on <day>. Create a new key." The old key stops working immediately; use the id in this response from now on. The new key lists the old one in replaced_key_ids, so its requests and usage stay with it. The new secret is returned ONLY in this response. Note: the secret will be visible in the AI conversation context. Agent usage: This operation requires 2FA. Before calling, complete the 2FA flow: (1) call start_2fa with action_type "api_key_regenerate", (2) wait for user to verify the code, (3) poll get_2fa_status until "verified", (4) then call regenerate_api_key. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • remove_circle_memberRemove a member from a Circle.No findings

    Why it is in this group

    • The name "remove_circle_member" says "remove": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove a member from a Circle. Deletes the member's channels and revokes any live authorizations that routed through them. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • remove_circle_member_channelRemove a channel from a Circle member.No findings

    Why it is in this group

    • The name "remove_circle_member_channel" says "remove": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove a channel from a Circle member. Removing the last channel is allowed (the member simply becomes unreachable). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • remove_emailRemove an email address from the account.No findings

    Why it is in this group

    • The name "remove_email" says "remove": a word for removing or ending something.
    • The description says "Cannot be undone".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove an email address from the account. Always requires one code: start_2fa_for_action with action_type email_remove and targets [this email id]. Revokes every proof of the address and your own consents naming it, declines pending confirmations waiting on it, moves Lookalike Watch alerts to your remaining primary email (or stops the watch when none is left), deletes the record, signs out your other devices, and names the new primary email. Refused for the address you signed in with and for your only way to sign in. Cannot be undone. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • remove_phoneRemove a phone number from the account.No findings

    Why it is in this group

    • The name "remove_phone" says "remove": a word for removing or ending something.
    • The description says "Cannot be undone".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Remove a phone number from the account. Always requires one code: start_2fa_for_action with action_type phone_remove and targets [this phone id]. Revokes every proof of the number and your own consents naming it, declines pending confirmations waiting on it, flags approval setups left with no approver, deletes the record and its messenger links, signs out your other devices, and names the new primary phone — your Proof of Me circles then reach you there. Refused for the number you signed in with, for your only way to sign in, and for your last phone while circles are active (circles_need_phone: add another phone first, or archive the circles). Cannot be undone. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • resume_proofResume a proof paused with pause_proof, by the same handle (ph_ctl_* / ph_dlg_*) or verification ID: it validates again everywhere, and a resumed delegation is honoured again by ga…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Resume a proof paused with pause_proof, by the same handle (ph_ctl_* / ph_dlg_*) or verification ID: it validates again everywhere, and a resumed delegation is honoured again by gated publishers on their next status check. Only the paused row flips back — a proof revoked while paused stays revoked, and a handle whose own row is not the paused one answers not_suspended. The API key needs proofs:write, plus delegations:write for a ph_dlg_*. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • revoke_api_keyRevoke an API key by ID.No findings

    Why it is in this group

    • The name "revoke_api_key" says "revoke": a word for removing or ending something.
    • The description says "cannot be undone".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Revoke an API key by ID. The key will immediately stop working. This action cannot be undone. Agent usage: This operation requires 2FA. Before calling, complete the 2FA flow: (1) call start_2fa with action_type "api_key_revoke", (2) wait for user to verify the code, (3) poll get_2fa_status until "verified", (4) then call revoke_api_key. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • revoke_assetDeprecated: use revoke_my_proofNo findings

    Why it is in this group

    • The name "revoke_asset" says "revoke": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use revoke_my_proof

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • revoke_auth_sessionSign out one device (session) by ID.No findings

    Why it is in this group

    • The name "revoke_auth_session" says "revoke": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Sign out one device (session) by ID. Over a signed-in session it cannot end the current one (that is logout). Over an API key it can end any of the account's sessions. NOT AVAILABLE HERE: This tool is not available on the hosted Proof MCP server: it needs the auth:read or auth:write scope, which the hosted server never grants (an agent holding it could list and sign out the owner's devices). The account owner manages signed-in devices in the dashboard: Settings → Signed-in devices (https://proof.holdings/dev). A local (stdio) Proof MCP server run with an API key that holds the scope can call it.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • revoke_authorizationRevoke an active or pending authorization.No findings

    Why it is in this group

    • The name "revoke_authorization" says "revoke": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Revoke an active or pending authorization. Only authorizations with status "active" or "pending" can be revoked. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • revoke_delegationRevoke ONE delegation.No findings

    Why it is in this group

    • The name "revoke_delegation" says "revoke": a word for removing or ending something.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Revoke ONE delegation. The domain control proof and sibling delegations stay valid; the revocation is mirrored into the proof registry so the CRL, status list and public status lookup all see it. Idempotent: a repeat revoke answers success with the same body, both here and through revoke_proof with the ph_dlg_ handle — unlike a PROOF, where a repeat answers already_revoked. The result carries the DERIVED effective_status/is_valid beside the stored status. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • revoke_my_proofRevoke EVERY proof of one of your assets (a phone, email or domain), by its asset id from list_my_proofs — the asset stays on the account.No findings

    Why it is in this group

    • The name "revoke_my_proof" says "revoke": a word for removing or ending something.
    • The description says "Cannot be undone".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Revoke EVERY proof of one of your assets (a phone, email or domain), by its asset id from list_my_proofs — the asset stays on the account. A ph_ctl_* / ph_dlg_* handle is one proof, not an asset: revoke that with revoke_proof. Owner only: sign in with start_login (a connection with only an API key is refused user_session_required — a key revokes a proof with revoke_proof instead), then one code: start_2fa_for_action with action_type revocation_bulk and targets [this asset id], wait_for_2fa, and call again. A phone or email: every proof of that number or address is revoked; signing in with it again issues a fresh proof. A domain you own: every proof of the domain and every delegation issued from it are revoked for good, and the domain needs re-verification — re-verifying does NOT bring the delegations back. Need a temporary stop for a domain proof? Use pause_proof instead. Status-checking verifiers see the revocation within about a minute; signature-only verifiers accept a token until it expires. Cannot be undone. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • revoke_proofRevoke a proof by its public handle (ph_ctl_* / ph_dlg_*) or a verification ID — the same addresses get_proof_status takes.No findings

    Why it is in this group

    • The name "revoke_proof" says "revoke": a word for removing or ending something.
    • The description says "Cannot be undone".
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Revoke a proof by its public handle (ph_ctl_* / ph_dlg_*) or a verification ID — the same addresses get_proof_status takes. The proof token will no longer validate anywhere: the status endpoint, the public validator, the revocation list and the Token Status List all report it revoked. A domain CONTROL proof (a ph_ctl_* of a domain) also revokes, for good, every delegation issued from it; for a domain you own, every proof of the domain is revoked and the domain needs re-verification. The API key needs proofs:write, plus delegations:write while the revocation reaches live delegations — for a domain you own, any live delegation of the domain, whichever of its handles you name (the refusal names the scope and the count). A handle revoked before the domain was verified again does not reach the new proof: revoke that one by its own handle. Otherwise it revokes the PROOF only — the asset or consent it is about stays. Need a temporary stop? Use pause_proof instead. Cannot be undone. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • rotate_callback_secretRotate a sub-account's callback signing secret — the secret that signs every callback_url delivery of its verification requests — and return the new one.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Rotate a sub-account's callback signing secret — the secret that signs every callback_url delivery of its verification requests — and return the new one. This is the only time it is returned, so store it now. Callback deliveries already queued keep the secret they were signed with. An account still delivering through its settings webhook URL is switched over to webhook endpoints first. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • rotate_webhook_endpoint_secretReplace a webhook endpoint's signing secret and return the new one — this and create_webhook_endpoint are the only times a secret is returned, so store it now.No findings

    Why it is in this group

    • The description's first verb is "replace": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Replace a webhook endpoint's signing secret and return the new one — this and create_webhook_endpoint are the only times a secret is returned, so store it now. New deliveries are signed with the new secret; deliveries already queued keep the secret they were queued with. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • set_email_account_accessTurn Account access on or off for one of the account's email addresses: whether it signs in to the account and confirms its sensitive actions (2FA step-ups).Can send data outNo findings

    Why it is in this group

    • The name "set_email_account_access" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • outboundThe name "set_email_account_access" says "set" and "email": it writes something other people read.
    Description, as the server wrote it
    Turn Account access on or off for one of the account's email addresses: whether it signs in to the account and confirms its sensitive actions (2FA step-ups). Every new email address starts on. Either direction requires one code: start_2fa_for_action with action_type account_access and targets ["act:access_on", "<id>"] to turn it on or ["act:access_off", "<id>"] to turn it off; without it the call answers 403 2fa_required. Turning off the last way into the account answers 409 last_account_access. Turning it off ends the sign-in sessions this address opened within 15 minutes (at their next renewal) and signs out no other device; MCP sign-ins and API keys are not sessions and are not affected. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • set_phone_account_accessTurn Account access on or off for one of the account's phone numbers: whether it signs in to the account and confirms its sensitive actions (2FA step-ups).No findings

    Why it is in this group

    • The name "set_phone_account_access" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Turn Account access on or off for one of the account's phone numbers: whether it signs in to the account and confirms its sensitive actions (2FA step-ups). Every new phone number starts on. Either direction requires one code: start_2fa_for_action with action_type account_access and targets ["act:access_on", "<id>"] to turn it on or ["act:access_off", "<id>"] to turn it off; without it the call answers 403 2fa_required. Turning off the last way into the account answers 409 last_account_access. Turning it off ends the sign-in sessions this number opened within 15 minutes (at their next renewal) and signs out no other device; MCP sign-ins and API keys are not sessions and are not affected. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • set_primary_emailSet an email address as the primary email for the account.Can send data outNo findings

    Why it is in this group

    • The name "set_primary_email" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • outboundThe name "set_primary_email" says "set" and "email": it writes something other people read.
    Description, as the server wrote it
    Set an email address as the primary email for the account. Always requires one code: start_2fa_for_action with action_type email_primary (no targets); without it the call answers 403 2fa_required. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • set_primary_phoneSet a phone number as the primary phone for the account.No findings

    Why it is in this group

    • The name "set_primary_phone" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Set a phone number as the primary phone for the account. Always requires one code: start_2fa_for_action with action_type phone_primary (no targets); without it the call answers 403 2fa_required. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • set_primary_profileDeprecated: use set_primary_sub_accountNo findings

    Why it is in this group

    • The name "set_primary_profile" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use set_primary_sub_account

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • set_primary_sub_accountMake a sub-account the primary one.No findings

    Why it is in this group

    • The name "set_primary_sub_account" says "set": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Make a sub-account the primary one. The previous primary sub-account becomes secondary. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_approval_channelUpdate an approval channel.No findings

    Why it is in this group

    • The name "update_approval_channel" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Update an approval channel. Can change name, channels, or timeout. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_circleUpdate a Circle's name and/or owner name.No findings

    Why it is in this group

    • The name "update_circle" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Update a Circle's name and/or owner name. Omitted fields are left unchanged; the sub-account and identity binding is set at creation only. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_hitlDeprecated: use update_approval_channelNo findings

    Why it is in this group

    • The name "update_hitl" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use update_approval_channel

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_my_profileDeprecated: use update_public_pageNo findings

    Why it is in this group

    • The name "update_my_profile" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use update_public_page

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_profileDeprecated: use update_sub_accountNo findings

    Why it is in this group

    • The name "update_profile" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use update_sub_account

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_profile_proofsDeprecated: use update_sub_account_page_proofsNo findings

    Why it is in this group

    • The name "update_profile_proofs" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use update_sub_account_page_proofs

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_public_pageUpdate the record get_current_sub_account reads: a sub-account key's own sub-account, otherwise the primary sub-account (never creates one).No findings

    Why it is in this group

    • The name "update_public_page" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Update the record get_current_sub_account reads: a sub-account key's own sub-account, otherwise the primary sub-account (never creates one). Takes presentation fields only — display name, bio, avatar, theme, custom links, and verification display settings; business details, the primary flag and email branding go through update_sub_account. In the dashboard, the Profile page (https://proof.holdings/profile) edits whichever sub-account is selected there. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_public_page_proofsUpdate which verified proofs are visible on the public page of the primary sub-account (the one get_current_sub_account reads), including visibility, masking, and display order.No findings

    Why it is in this group

    • The name "update_public_page_proofs" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Update which verified proofs are visible on the public page of the primary sub-account (the one get_current_sub_account reads), including visibility, masking, and display order. Needs a signed-in session. To do the same for a named sub-account, use update_sub_account_page_proofs. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_public_proofsDeprecated: use update_public_page_proofsNo findings

    Why it is in this group

    • The name "update_public_proofs" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use update_public_page_proofs

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_settingsUpdate account settings: the outbound webhook endpoint with its event subscriptions, and the default proof lifetime.No findings

    Why it is in this group

    • The name "update_settings" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Update account settings: the outbound webhook endpoint with its event subscriptions, and the default proof lifetime. Branding belongs to each sub-account: change it with update_sub_account. Setting the first webhook endpoint creates the signing secret and returns it in this response; the value is returned only when this call created or rotated it, so record it then. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_sub_accountUpdate a sub-account by ID.No findings

    Why it is in this group

    • The name "update_sub_account" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Update a sub-account by ID. Supports changing display info, email branding (theme, support email), theme, custom links, and verification display settings. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_sub_account_page_proofsUpdate which verified assets (proofs) are displayed on one named sub-account.No findings

    Why it is in this group

    • The name "update_sub_account_page_proofs" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Update which verified assets (proofs) are displayed on one named sub-account. Controls visibility, privacy masking, ordering, and labels. For the primary sub-account in a signed-in session, update_public_page_proofs does the same. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_templateCreate or update a sub-account's custom template for a channel and message type, replacing the default for that sub-account only.No findings

    Why it is in this group

    • The name "update_template" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Create or update a sub-account's custom template for a channel and message type, replacing the default for that sub-account only. Name the brand with {{business_name}}: a template spelling out a sub-account's own name is refused (template_hardcoded_name). A template for a channel and message type no message is sent for, or using a variable that message never fills, is still saved, with an entry in `warnings` (template_not_sent / template_variable_not_filled) saying why it will not be sent as written (an API that predates `warnings` omits the field). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • update_webhook_endpointUpdate a webhook endpoint: its URL, events, scope, sub-accounts, status or description.No findings

    Why it is in this group

    • The name "update_webhook_endpoint" says "update": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Update a webhook endpoint: its URL, events, scope, sub-accounts, status or description. Every field is optional, but send at least one. Changing the scope to "selected" without profile_ids keeps the stored list. The signing secret is unchanged (rotate it with rotate_webhook_endpoint_secret). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • upload_approval_channel_keysUpload an encryption keypair for an approval channel.No findings

    Why it is in this group

    • The name "upload_approval_channel_keys" says "upload": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Upload an encryption keypair for an approval channel. The server validates the RSA-4096 public key and computes the key ID. Note: the encrypted_private_key is already encrypted client-side with the user's password — the server never sees the password. The owner sets that password in the dashboard under Settings → Approvals password (https://proof.holdings/dev). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
  • upload_hitl_keysDeprecated: use upload_approval_channel_keysNo findings

    Why it is in this group

    • The name "upload_hitl_keys" says "upload": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Deprecated: use upload_approval_channel_keys

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: true
Can't be undone 10Claude Code: ask
  • create_authorizationCreate a new authorization request.Can send data outNo findings

    Why it is in this group

    • The name "create_authorization" says "create": a word for a change.
    • The input addresses people (input.recipient): what it sends cannot be taken back.

    What it can reach

    • outboundThe input takes a destination (input.recipient): what the tool writes goes there.
    Description, as the server wrote it
    Create a new authorization request. Authorizations grant permission to send confirmations to a user via a specific channel. The user must approve the authorization before confirmations can be sent; get_authorization reads its status, which stays pending until they answer. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_user_requestCreate a new verification request to ask another user to share verified assets; list_my_requests shows its progress and cancel_user_request withdraws it.Can send data outNo findings

    Why it is in this group

    • The name "create_user_request" says "create": a word for a change.
    • The input carries an amount (input.action_context.amount) and a currency, so it moves money.

    What it can reach

    • outboundThe input takes a URL (input.callback_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Create a new verification request to ask another user to share verified assets; list_my_requests shows its progress and cancel_user_request withdraws it. Each asset is an object naming its type, e.g. { "type": "email" }. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • export_authorizationsExport authorizations as CSV or JSON.Can send data out1 finding

    Why it is in this group

    • The input addresses people (input.to): what it sends cannot be taken back.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe input takes a destination (input.to): what the tool writes goes there.

    Findings

    • Warn

      The server marks "export_authorizations" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

      Matched text

      annotations: {"readOnlyHint":true}; The input addresses people (input.to): what it sends cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    Export authorizations as CSV or JSON. Supports date range and status filtering. Maximum 10,000 records. CSV comes back as `{ content_type, body, truncated }` with the file in `body`; a body over 100,000 characters is cut at the last full line (`truncated: true`, `total_chars`) — narrow `from`/`to` or `status` and export again for the rest. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • invite_circle_memberMint a single-use enrollment invite for a Circle member.Can send data outNo findings

    Why it is in this group

    • The name "invite_circle_member" says "invite": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "invite_circle_member" says "invite": it sends or publishes something to other people.
    Description, as the server wrote it
    Mint a single-use enrollment invite for a Circle member. Returns Telegram + WhatsApp deep links and a QR code; the member taps the channel-matched link to bind their messenger identity to the Circle. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • resend_confirmationSend a pending confirmation again to the people it went to: each recipient gets a fresh link bound to them, through their own channel, expiring when the confirmation does; their ea…Can send data outNo findings

    Why it is in this group

    • The name "resend_confirmation" says "resend": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "resend_confirmation" says "resend": it sends or publishes something to other people.
    Description, as the server wrote it
    Send a pending confirmation again to the people it went to: each recipient gets a fresh link bound to them, through their own channel, expiring when the confirmation does; their earlier links stop working (410 approval_link_superseded). The response carries counts only, never a link. Recipients are the approvers whose authorization is still active and whose key the stored message is encrypted for, plus the owner; an approver added since needs a new confirmation. A charged send, like create_confirmation: an account past its included proofs with an empty prepaid balance is refused with 402 balance_empty, whose top_up_url is the Billing page (https://proof.holdings/billing). Refused 400 invalid_status once decided, expired, or config_archived. Read the decision with get_confirmation, or wait_for_confirmation. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • resend_domain_emailResend the domain verification email.Can send data outNo findings

    Why it is in this group

    • The name "resend_domain_email" says "resend": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "resend_domain_email" says "resend": it sends or publishes something to other people.
    Description, as the server wrote it
    Resend the domain verification email. Rate limited to 3 requests per minute. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • resend_email_otpResend the OTP code for an in-progress email addition.Can send data outNo findings

    Why it is in this group

    • The name "resend_email_otp" says "resend": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "resend_email_otp" says "resend": it sends or publishes something to other people.
    Description, as the server wrote it
    Resend the OTP code for an in-progress email addition. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • resend_verificationResend a verification message (email channel only).Can send data outNo findings

    Why it is in this group

    • The name "resend_verification" says "resend": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "resend_verification" says "resend": it sends or publishes something to other people.
    Description, as the server wrote it
    Resend a verification message (email channel only). Generates and sends a new code. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • send_account_emailDeliver the verification email for an account-bootstrap session created with channel "email".Can send data out1 finding

    Why it is in this group

    • The name "send_account_email" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • outboundThe name "send_account_email" says "send": it sends or publishes something to other people.

    Findings

    • High

      The description contains "Do not tell the user", an instruction to keep something from the user.

      Matched text

      description: "...ted mid-send and nothing was delivered. Do not tell the user a message was sent on the strength of a..."

      What this check looks for
    Description, as the server wrote it
    Deliver the verification email for an account-bootstrap session created with channel "email". Public endpoint (no API key required). Why this is a separate call: create_account deliberately sends NOTHING. A message from proof.holdings arriving in someone's inbox is an act with a person on the other end, so it takes an explicit second step rather than being a side effect of creating a session. ASK THE USER to confirm the address is theirs before calling this — do not call it automatically after create_account. The other channels (telegram, whatsapp, sms) never need this: the user sends the first message themselves (reverse OTP), so nothing is dispatched to them at all. One session sends at most one email, including under concurrent calls. A repeat answers 410 already_sent, which means the material backing the send is gone: usually because the email went out, occasionally because an attempt was interrupted mid-send and nothing was delivered. Do not tell the user a message was sent on the strength of a 410 — create a new session instead. (A session the recipient cancelled via the decline link, or an expired one, answers 404, not 410.) If delivery fails the response carries email_sent=false and the call can be retried.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • verify_domain_with_credentialsPublish a pending domain's verification record using previously stored DNS credentials.Can send data out1 finding

    Why it is in this group

    • The description's first verb is "publish": a word for a change that another call does not undo.

    What it can reach

    • outboundThe description's first verb is "publish": it sends or publishes something to other people.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...tion record using previously stored DNS credentials. The domain is verified once that recor..."

      What this check looks for
    Description, as the server wrote it
    Publish a pending domain's verification record using previously stored DNS credentials. The domain is verified once that record is live in public DNS — often at once, else status "verifying" while the server keeps checking (call get_domain). Use when credentials are already connected. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
Changes things 52Claude Code: ask
  • add_circle_memberAdd a pending member to a Circle by name, with an optional pre-declared WhatsApp phone.No findings

    Why it is in this group

    • The name "add_circle_member" says "add": a word for a change.
    Description, as the server wrote it
    Add a pending member to a Circle by name, with an optional pre-declared WhatsApp phone. The Telegram chat id is captured later when the member taps the enrollment deep link. Agent usage: after adding a member, call invite_circle_member to mint the single-use enrollment link the member taps to bind their messenger identity. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • add_circle_member_channelDeclare a channel for a Circle member.Can send data outNo findings

    Why it is in this group

    • The name "add_circle_member_channel" says "add": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.
    Description, as the server wrote it
    Declare a channel for a Circle member. Returns 409 if that channel type already exists on the member. The identifier is a Telegram chat id or an E.164 WhatsApp phone (per-channel format validated server-side). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • add_domainAdd a new domain to verify ownership.No findings

    Why it is in this group

    • The name "add_domain" says "add": a word for a change.
    Description, as the server wrote it
    Add a new domain to verify ownership. Optionally specify email sending intent and verification method. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • check_domain_credentialsCheck if stored DNS credentials have access to a domain.2 findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "Check if stored DNS credentials have access to a domain. Use before tri..."

      What this check looks for
    • Info

      The input schema at properties.id.description mentions "credentials".

      Matched text

      inputSchema.properties.id.description: "Domain ID to check credentials for"

      What this check looks for
    Description, as the server wrote it
    Check if stored DNS credentials have access to a domain. Use before triggering verification to confirm the credentials work. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • check_domain_verificationCheck the status of a pending domain verification.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Check the status of a pending domain verification. Triggers a DNS/HTTP check and returns the updated status. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • check_user_domain_verificationTrigger a check on the domain verification challenge.No findings

    Why it is in this group

    • The description's first verb is "trigger": a word for a change.
    Description, as the server wrote it
    Trigger a check on the domain verification challenge. Call after placing DNS record or HTTP file. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • claim_usernameClaim a unique username for the authenticated user's Public page.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Claim a unique username for the authenticated user's Public page. Usernames must be 3-30 characters, alphanumeric and underscores only. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • confirm_domain_email_codeConfirm domain email verification by submitting the code sent to the corporate email address.No findings

    Why it is in this group

    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    Description, as the server wrote it
    Confirm domain email verification by submitting the code sent to the corporate email address. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_accountCreate an account-bootstrap session for agent-driven onboarding.Can send data out1 finding

    Why it is in this group

    • The name "create_account" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.

    Findings

    • Info

      The description is 2,380 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...sentence announcing it), the SMS text and number, or a note to check their inbox."

      What this check looks for
    Description, as the server wrote it
    Create an account-bootstrap session for agent-driven onboarding. Public endpoint (no API key required). Returns a session id, channel-specific instructions, and — FOR TELEGRAM AND WHATSAPP ONLY — deep_link, qr_code (base64 PNG) and qr_text (UTF-8 text QR). The endpoint is safe to call regardless of whether the submitted identity is new: completing verification transparently creates a User when none exists, or logs the user in when one already does. The response is intentionally uniform — the server does NOT reveal whether the identity is already registered (this would be a user-enumeration oracle). If the agent needs to distinguish new-vs-returning users, call `get_current_user` after verification and inspect the user's `created_at`. EMAIL CHANNEL SENDS NOTHING HERE. The response carries email_sent=false and send_required=true: confirm with the user that the address is theirs, then call send_account_email. The other channels dispatch nothing either way — the user sends the first message themselves (reverse OTP). Agent usage: (1) Call create_account with the user's chosen channel. (2) For email, confirm with the user and call send_account_email. On telegram/whatsapp pass `deep_link` to render_auth_link, which returns the clickable link with a QR code beneath it to you. On sms `deep_link` is an EMPTY STRING and render_auth_link will reject it — show `sms_message`, which is what the user sends; this response carries no destination number, so do not invent one. Do not hand `qr_text` to a link renderer either — it is the link already rendered as QR art; print it verbatim inside a fenced code block if a real terminal needs the QR. (3) Once your reply shows the user the challenge, call wait_for_account_creation with the session id until verification completes. On email the user must press "Sign in the browser that requested this" on the link's page — "Sign in here" signs in the browser they clicked from, and the wait then ends with "completed_elsewhere". (4) On verified, JWT + refresh cookies are set; proceed with whatever follow-up the agent was asked to do. The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_api_keyCreate a new API key.No findings

    Why it is in this group

    • The name "create_api_key" says "create": a word for a change.
    Description, as the server wrote it
    Create a new API key. The secret key value is returned ONLY in this response — store it securely. Note: the secret will be visible in the AI conversation context. Optionally bind the key to a sub-account via profile_id — outbound messages sent with the key are then branded as that sub-account. Agent usage: This operation requires 2FA. Before calling, complete the 2FA flow: (1) call start_2fa with action_type "api_key_create" and the user's preferred channel, (2) tell the user a code was sent and wait for them to verify, (3) poll get_2fa_status until status is "verified", (4) then call create_api_key — the backend session will be elevated. If you get a 403, the 2FA session has expired — restart the flow. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_approval_channelCreate a HITL (Human-in-the-Loop) config.Can send data outNo findings

    Why it is in this group

    • The name "create_approval_channel" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channels): what the tool writes goes there.
    Description, as the server wrote it
    Create a HITL (Human-in-the-Loop) config. Defines which messaging channels receive approval requests and the default timeout. Agent usage: After creating an approval channel, you must call request_approval_channel_authorization before it can be used with create_confirmation. For Telegram channels, use create_chat_id_discovery first to discover the user's chat ID, then include it in the channel config. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_chat_id_discoveryCreate a Telegram chat ID discovery token.No findings

    Why it is in this group

    • The name "create_chat_id_discovery" says "create": a word for a change.
    Description, as the server wrote it
    Create a Telegram chat ID discovery token. Returns a deep_link, qr_code (base64 PNG), and qr_text (UTF-8 text QR for terminal display). The user opens the link in Telegram, which reveals their chat ID for approval channel setup. Agent usage: pass the response's `deep_link` to render_auth_link so the user can click or scan it. Never hand `qr_text` to a link renderer — it is that same link already rendered as QR art. Print it verbatim inside a fenced code block only when a real terminal needs the QR. Then poll poll_chat_id_discovery with the returned token until the chat_id appears. Use the discovered chat_id when creating an approval channel with a Telegram channel. The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_circleCreate a Circle — a named group of trusted contacts (the people-primitive powering Proof of Me and Approvals-on-Circle).No findings

    Why it is in this group

    • The name "create_circle" says "create": a word for a change.
    Description, as the server wrote it
    Create a Circle — a named group of trusted contacts (the people-primitive powering Proof of Me and Approvals-on-Circle). Optionally seed initial members; each member's declared channels are stored so they can be invited to enroll. Agent usage: after creating a Circle, add members with add_circle_member (or seed them here), then invite_circle_member to mint the enrollment deep link each contact taps to bind their messenger identity. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_circle_member_drillFire an on-demand Proof of Me drill against one enrolled member — a real cross-channel identity challenge carrying the scheduled-safety-check label (the account owner practices con…No findings

    Why it is in this group

    • The name "create_circle_member_drill" says "create": a word for a change.
    Description, as the server wrote it
    Fire an on-demand Proof of Me drill against one enrolled member — a real cross-channel identity challenge carrying the scheduled-safety-check label (the account owner practices confirming). Complements the automated daily drill + monthly reinforcement sweeps. On Pay as you go a live key is refused `422 plan_upgrade_required`; a test key is not, and its drill reaches the member on Telegram only (`400 no_channel` when they have no verified Telegram channel). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_confirmationCreate a HITL confirmation request.No findings

    Why it is in this group

    • The name "create_confirmation" says "create": a word for a change.
    Description, as the server wrote it
    Create a HITL confirmation request. Sends an approval request to the channels configured on the referenced approval channel. First response wins. Agent usage: The approval channel referenced by hitl_id must be authorized before you can create confirmations. If this returns a 403 or "not authorized" error, call request_approval_channel_authorization on the approval channel first, then wait for the user to approve via the messaging channel. After creating a confirmation, poll get_confirmation to check for approval/denial, or, if the user (the approval channel owner) will decide it themselves, use get_confirmation_approval_link for their own approval link. Encryption is NOT optional: an approval channel cannot send confirmations without a keypair (protected by the owner's approvals password, set in the dashboard under Settings → Approvals password, https://proof.holdings/dev), the human approves by decrypting in their browser, and `message` must be a JSON ciphertext envelope. Plaintext is refused with 400 `message_not_encrypted`; an envelope sealed to another key with 400 `message_key_mismatch`. Choose the version by who must be able to decrypt: - v1 (single-recipient): wraps the content key for the config owner only. Use ONLY when there are no enrolled non-owner approvers — with approvers enrolled it is refused with 400 `envelope_missing_approvers`. - v2 (multi-recipient): additionally wraps the content key for each enrolled approver via an `approver_ek` map, so every approver can decrypt. Build it with the SDK `encryptMessageV2(plaintext, ownerPublicKey, hitlId, approverKeys)` after fetching the approvers via the SDK `getApproverKeys(hitlId)` (`GET /api/v1/hitl/:id/approver-keys`). AAD is the `hitlId`. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_delegationCreate a delegation (Proof of Delegation): a control-proven domain authorizes a typed url/purl artifact and receives a publishable signed token.No findings

    Why it is in this group

    • The name "create_delegation" says "create": a word for a change.
    Description, as the server wrote it
    Create a delegation (Proof of Delegation): a control-proven domain authorizes a typed url/purl artifact and receives a publishable signed token. The attestation is that the domain's controller authorized this artifact — nothing more; it says nothing about the artifact or the business behind it. Each mint is a billable proof. A requested lifetime longer than the control proof's remainder is rejected, never truncated. The result carries the publishable token AND the DERIVED effective_status/is_valid — the same pair the list and get tools return, so the shape does not depend on which verb produced it. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_hitlDeprecated: use create_approval_channelCan send data outNo findings

    Why it is in this group

    • The name "create_hitl" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channels): what the tool writes goes there.
    Description, as the server wrote it
    Deprecated: use create_approval_channel

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_identity_challengeCreate a Proof of Me cross-channel identity challenge (CONFIRM) for an enrolled Circle member.No findings

    Why it is in this group

    • The name "create_identity_challenge" says "create": a word for a change.
    Description, as the server wrote it
    Create a Proof of Me cross-channel identity challenge (CONFIRM) for an enrolled Circle member. The account holder approves/denies on a channel different from the one the suspicious contact reached the member on. Agent usage: poll get_identity_challenge with the returned ID until it leaves pending (confirmed, denied, cancelled, failed, expired or revoked). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_multi_channel_verificationCreate a multi-channel phone verification: one phone number challenged over several channels at once (OR / first-wins).Can send data outNo findings

    Why it is in this group

    • The name "create_multi_channel_verification" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channels): what the tool writes goes there.
    Description, as the server wrote it
    Create a multi-channel phone verification: one phone number challenged over several channels at once (OR / first-wins). The first channel the user completes wins, yields a single proof token, and cancels the losing siblings. Exactly one proof is billed, at the winning channel's completion — not one per channel, and nothing at creation. Agent usage: the response includes a `group_id` (format vg_<hex>) and a `channels` array — each block carries a `deep_link` (WhatsApp/Telegram) or an `sms_message` to present to the user — pass the `deep_link` to render_auth_link. A block's `qr_text` is that same link already rendered as QR art, not an alternative address: print it verbatim inside a fenced code block or leave it out. Poll get_multi_channel_verification_status with the group_id to track completion and retrieve the proof token when a channel verifies. The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_sessionCreate a new phone verification session.Can send data outNo findings

    Why it is in this group

    • The name "create_session" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.
    Description, as the server wrote it
    Create a new phone verification session. Returns deep_link, qr_code (base64 PNG), and qr_text (UTF-8 text QR for terminal display). Sessions provide a hosted verification flow with callbacks. Agent usage: After creating a session, pass the response's `deep_link` to render_auth_link so the user can open or scan it. Never hand `qr_text` to a link renderer — it is that link already rendered as QR art. Print it verbatim inside a fenced code block only when a real terminal needs the QR. On sms the person texts a short code from the number being proven, as in SMS login: `deep_link` is an `sms:` link to our default number with the message pre-filled, so render it the same way, and also show `sms_message` (what they send) with the numbers in `sms_dids` (one per region, each with its own QR), because a person reading on a computer texts from their phone. They get no reply SMS. An SMS proof can still be revoked about a minute after the session completes, if the delayed spoof check finds the sender was not a real mobile line, so before relying on it check it with validate_proof. Then use wait_for_session to poll until the session reaches a terminal state (verified, failed, or expired). The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_verificationCreate a new identity verification.Can send data out1 finding

    Why it is in this group

    • The name "create_verification" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.

    Findings

    • Info

      The input schema at properties.dns_provider.description mentions "credentials".

      Matched text

      inputSchema.properties.dns_provider.description: "DNS provider credentials (required for channel "auto")"

      What this check looks for
    Description, as the server wrote it
    Create a new identity verification. Initiates a verification flow for an asset identifier (phone number, email, domain, social handle, wallet address, account, or Telegram bot). Agent usage: pass the asset `type`, the delivery `channel`, and the `identifier` (e.g. type "phone", channel "sms", identifier "+37060000000"; or type "email", channel "email", identifier "user@example.com"). The response carries a `challenge` object with the instruction for the chosen channel — except a `telegram_bot` verification made with a LIVE key, which the server completes on the spot and answers with `status: verified` plus a proof token and no challenge at all; with a `pk_test_` key that same call stays pending and does carry a challenge. On the messenger channels it also carries `challenge.deep_link` — pass THAT to render_auth_link to give the user a clickable link and a QR code. This endpoint returns no `qr_text` at all. For OTP-based flows (sms/email), the user receives a code — poll get_verification or use wait_for_verification to track completion. For Telegram/WhatsApp, the user clicks the deep link to verify. The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_verification_requestCreate a multi-asset verification request.Can send data outNo findings

    Why it is in this group

    • The name "create_verification_request" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.callback_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Create a multi-asset verification request. Allows verifying multiple assets (phone, email, domain, social, wallet, account, telegram_bot) in a single flow. Give the recipient the returned verification_url; wait_for_request or get_verification_request then reads its progress until it is completed, expired or cancelled. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • create_webhook_endpointAdd a webhook endpoint.Can send data outNo findings

    Why it is in this group

    • The name "create_webhook_endpoint" says "create": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Add a webhook endpoint. An event reaches every active endpoint whose scope includes the event's sub-account and whose events match; an account-level event reaches "all"-scope endpoints only. An account still delivering to the single webhook URL in its settings is moved onto endpoints by this call (that URL becomes an "all"-scope endpoint with the same secret and events). The response carries the endpoint's signing secret — this and rotate_webhook_endpoint_secret are the only times it is returned, so store it now. Deliveries carry an HMAC-SHA256 X-Proof-Signature over "<X-Proof-Timestamp>.<body>" made with it. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • export_dataExport a complete copy of your account's data (GDPR Articles 15 and 20), or check on one.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Export a complete copy of your account's data (GDPR Articles 15 and 20), or check on one. Owner only: sign in with start_login first (a connection with only an API key is refused user_session_required). The first call starts the export; it is prepared in the background, and the account owner is told by email (or on their login channel) with a link that downloads it only while they are signed in — this tool never returns the data itself. Call again to see whether it is ready: an export already preparing or ready is reported instead of starting another. One new export per 24 hours (no limit while the account is scheduled for deletion); the file is kept for 7 days. Pass export_id to read one export's status. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • extend_requestExtend the expiration time of a pending verification request.No findings

    Why it is in this group

    • The name "extend_request" says "request": a word for a change.
    Description, as the server wrote it
    Extend the expiration time of a pending verification request. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • poll_chat_id_discoveryPoll a chat ID discovery token.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Poll a chat ID discovery token. Returns the discovered Telegram chat ID, user ID, and username once the user interacts with the bot. Before calling this for a challenge you created, make sure your reply text already shows the user what to act on — the link itself, the SMS text and number, or a note to check their inbox; a link that appeared only in a tool result is one they never saw. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • render_templateRender the template a sub-account sends — its custom template, otherwise the default — with provided variables.Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.
    • outboundThe input takes a URL (input.variables.callback_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Render the template a sub-account sends — its custom template, otherwise the default — with provided variables. Returns the fully rendered message content. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • request_approval_channel_authorizationRequest authorization for an approval channel.No findings

    Why it is in this group

    • The name "request_approval_channel_authorization" says "request": a word for a change.
    Description, as the server wrote it
    Request authorization for an approval channel. Sends consent requests to all configured channels (Telegram/WhatsApp). Users must approve before confirmations can be sent. Agent usage: This must be completed before create_confirmation will work for this approval channel. The consent request is DELIVERED to each channel — the response carries no link to show. It returns `authorizations` — one entry per resolved recipient, each with its `channel`, `recipient`, `authorization_id` and `status` — plus a `message`. Read the entries rather than assuming: `status: 'pending'` means consent was just sent and the user must approve in Telegram/WhatsApp itself, while `status: 'active'` means that recipient had already authorized and nothing was sent to them. An EMPTY array does not mean everyone is authorized — it means no recipient could be resolved at all (usually an approval channel bound to a missing or inactive circle, or channels whose recipient is blank), so nobody was asked and waiting for an approval would hang forever. Do not relay `message` on that branch: it reads 'All channels already have active or pending authorizations', which is exactly the wrong conclusion. Read the array. After requesting, you can proceed once the user confirms they have approved; get_authorization with an entry's authorization_id reads whether it has turned active. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • request_hitl_authorizationDeprecated: use request_approval_channel_authorizationNo findings

    Why it is in this group

    • The name "request_hitl_authorization" says "request": a word for a change.
    Description, as the server wrote it
    Deprecated: use request_approval_channel_authorization

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • retry_webhook_deliveryRetry a failed webhook delivery.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Retry a failed webhook delivery. Creates a new delivery attempt with the same payload to the configured endpoint. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • setup_domain_emailRegister a verified domain with Proof's email provider (Resend) for sending.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Register a verified domain with Proof's email provider (Resend) for sending. The result carries the DKIM/SPF DNS records to publish (`resend.dkim_records`) and their status. `from_email`, if given, must be on this domain and is stored as the preferred sender. Proof does not send from customer domains yet: verification emails still come from Proof's own address, and the stored `from_email` is not used. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • share_request_emailEmail the link of a pending verification request to a recipient.Can send data outNo findings

    Why it is in this group

    • The name "share_request_email" says "request": a word for a change.

    What it can reach

    • outboundThe name "share_request_email" says "request" and "email": it writes something other people read.
    Description, as the server wrote it
    Email the link of a pending verification request to a recipient. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • start_2faStart a two-factor authentication challenge for a sensitive operation.Can send data out1 finding

    Why it is in this group

    • The name "start_2fa" says "start": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.

    Findings

    • Info

      The description is 2,004 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...n call this tool again. Authenticating this client alone does NOT open this tool."

      What this check looks for
    Description, as the server wrote it
    Start a two-factor authentication challenge for a sensitive operation. Sends a verification code via the chosen channel. Returns a session ID, and for messaging channels: deep_link, qr_code (base64 PNG), and qr_text (UTF-8 text QR for terminal display). Agent usage — full 2FA flow: (1) Call start_2fa with the appropriate action_type and channel. (2) Present the challenge, and do NOT announce a message the server did not send: email is the ONLY channel it dispatches on. On telegram/whatsapp the user opens `deep_link` and sends the message themselves; on sms they send `sms_message` to a number from `sms_dids`; the response's own `instructions` field says which. On email, a 200 carrying `requires_email_selection: true` and `available_emails` means nothing was sent and no session exists — ask which address and call again with `email_id`. For telegram/whatsapp, pass `deep_link` to render_auth_link; for sms, show `sms_message`. Never hand `qr_text` to a link renderer — it is the link already rendered as QR art, so print it verbatim inside a fenced code block only when a real terminal needs the QR. (3) Poll get_2fa_status with the returned session_id until status is "verified" (the user enters the code on their device) or "expired". (4) If verified, proceed with the protected operation (e.g. create_api_key). If expired, inform the user and offer to restart. Typical channels: "telegram" or "email". For email, the user may receive a magic link instead of a code — the backend handles this automatically. The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • start_2fa_for_actionStart a 2FA challenge that grants the authenticated user permission to perform a sensitive action.Can send data out1 finding

    Why it is in this group

    • The name "start_2fa_for_action" says "start": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.

    Findings

    • Info

      The description is 2,369 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...→ Authenticate), then call this tool again. start_login does NOT open this tool."

      What this check looks for
    Description, as the server wrote it
    Start a 2FA challenge that grants the authenticated user permission to perform a sensitive action. The 2FA must complete on a channel DIFFERENT from the user's last login channel (the backend enforces this). On success a grant is stored keyed by the user id and action_type; middleware on the protected endpoint reads the grant and allows the mutation. Destructive action types (api_key_create, api_key_revoke, api_key_regenerate, api_key_view, account_delete, phone_remove, email_remove, phone_primary, email_primary, revocation_bulk, domain_remove, profile_delete) are capped at 5min TTL and forced single-use by server policy. A step-up for revocation_bulk, phone_remove, email_remove, domain_remove, profile_delete or account_delete is bound to `targets` — the exact ids the protected call will carry. Configuration scopes (settings_write, profile_update, templates_write) allow up to 24h TTL and caller-chosen single_use — useful for agents making multiple settings mutations in one session. Agent usage: (1) Attempt the sensitive call; if you get `403 2fa_required` note the `action_type`. (2) Call start_2fa_for_action with that action_type and a channel different from the login channel. (3) Present the challenge: on telegram/whatsapp pass `deep_link` to render_auth_link; on sms show `sms_message` and the number to send it to; on email check the response first: with more than one verified email and no `email_id` given, it answers 200 with `requires_email_selection: true` and `available_emails` — NO session was started and nothing was sent, so ask the user which address and call again with `email_id` rather than telling them to open a mailbox. Never hand `qr_text` to a link renderer — it is the link already rendered as QR art. Print it verbatim inside a fenced code block only when a real terminal needs the QR. (4) Call wait_for_2fa until the session is verified. (5) Retry the original sensitive call. The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • start_add_emailStart adding a new email address.Can send data outNo findings

    Why it is in this group

    • The name "start_add_email" says "start": a word for a change.

    What it can reach

    • outboundThe name "start_add_email" says "start" and "email": it writes something other people read.
    Description, as the server wrote it
    Start adding a new email address. Sends an OTP code to the email. Returns a session ID: when the user has the code, pass it with that session ID to verify_email_otp (resend_email_otp if it did not arrive; get_add_email_status reads the session). ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • start_add_phoneStart adding a new phone number by reverse OTP: the user starts the exchange themselves and nothing is sent before they do; the response's `instructions` field says what they do (o…Can send data outNo findings

    Why it is in this group

    • The name "start_add_phone" says "start": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.
    Description, as the server wrote it
    Start adding a new phone number by reverse OTP: the user starts the exchange themselves and nothing is sent before they do; the response's `instructions` field says what they do (on telegram the bot then asks them to tap a button that shares their number). Returns a session ID; on telegram/whatsapp also deep_link, qr_code (base64 PNG) and qr_text (UTF-8 text QR), and on sms sms_message and sms_dids (one entry per region; a region with no number configured has an empty `did`) with no deep_link. Agent usage: on telegram/whatsapp pass `deep_link` to render_auth_link for the link and a QR code. On sms there is no deep_link — show `sms_message` and a number from an `sms_dids` entry whose `did` is non-empty. Never hand a `qr_text` to a link renderer — it is a link already rendered as QR art. Then poll get_add_phone_status with the session ID. The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • start_domain_email_verificationStart domain verification via corporate email.Can send data outNo findings

    Why it is in this group

    • The name "start_domain_email_verification" says "start": a word for a change.

    What it can reach

    • outboundThe name "start_domain_email_verification" says "start" and "email": it writes something other people read.
    Description, as the server wrote it
    Start domain verification via corporate email. Sends a verification code to a standard admin email address at the domain. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • start_domain_verificationStart a B2B domain verification.No findings

    Why it is in this group

    • The name "start_domain_verification" says "start": a word for a change.
    Description, as the server wrote it
    Start a B2B domain verification. Creates a verification record and returns DNS/HTTP instructions for the customer to complete. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • start_loginStart a login session by sending an authentication challenge to the user's chosen channel (Telegram, WhatsApp, SMS, or email).Can send data out1 finding

    Why it is in this group

    • The name "start_login" says "start": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.

    Findings

    • Info

      The description is 2,739 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...sentence announcing it), the SMS text and number, or a note to check their inbox."

      What this check looks for
    Description, as the server wrote it
    Start a login session by sending an authentication challenge to the user's chosen channel (Telegram, WhatsApp, SMS, or email). Returns a session ID and, FOR TELEGRAM AND WHATSAPP ONLY, deep_link, qr_code (base64 PNG) and qr_text (UTF-8 text QR for terminal display); on sms it returns sms_message with sms_dids instead, and on email nothing to display. Agent usage: (1) Call start_login with the desired channel and phone_number (for SMS) or email (for email). (2) Present the challenge, and WHICH FIELD depends on the channel. On telegram/whatsapp pass `deep_link` to render_auth_link, which returns the clickable link and a QR code to you; in a chat client the link is what the user acts on, since they are usually on the same machine. On sms `deep_link` is an EMPTY STRING and render_auth_link will reject it — show `sms_message` and let the user pick a number from `sms_dids`. `suggested_region` is always set, but the matching ENTRY in `sms_dids` may be missing (europe and israel appear only when a number is configured) or present with an empty `did`, so offer that region first only when `sms_dids[suggested_region]` exists and carries a number, and otherwise offer whatever the object does. On email there is nothing to display at all, and nothing to check either: a result means the mail was accepted for delivery, so tell the user to open their inbox. A delivery failure is an ERROR here, not a field — the tool answers `challenge_delivery_failed` and NO session exists, so do not call wait_for_login; retry, or offer another channel. Never hand `qr_text` to a link renderer — it is the link already rendered as QR art, so print it verbatim inside a fenced code block or not at all, because its rows stop scanning the moment one wraps or a blank line lands between them. (3) Once your reply shows the user the challenge, call wait_for_login with the returned session ID to poll until the user completes authentication. On email, tell the user to open the link and press "Sign in the browser that requested this": the page also offers "Sign in here", which signs in the browser they clicked from instead of this connection. Terminal states: "verified" (login succeeded), "failed", "expired", "completed_elsewhere" (email only: the user pressed "Sign in here" on the email link's page, so the browser they clicked from is signed in and this connection never will be — tell them so, and start a new login if this connection still needs one). The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • start_user_domain_verificationStart a self-service domain verification session.Can send data outNo findings

    Why it is in this group

    • The name "start_user_domain_verification" says "start": a word for a change.

    What it can reach

    • outboundThe input takes a destination (input.channel): what the tool writes goes there.
    Description, as the server wrote it
    Start a self-service domain verification session. The user proves ownership of a domain via DNS or HTTP challenge. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • submit_verification_codeSubmit an OTP/challenge code for a pending verification.No findings

    Why it is in this group

    • The name "submit_verification_code" says "submit": a word for a change.
    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    Description, as the server wrote it
    Submit an OTP/challenge code for a pending verification. Accepted ONLY where we delivered the code out-of-band to the party being verified: type "email", and type "domain" with channel "email". Any other pair answers 400 unsupported_for_type and completes elsewhere — use trigger_verification (POST /verifications/:id/verify) for a domain over dns/http/auto; a phone completes when the code reaches us FROM that number; social completes through its OAuth callback; a telegram_bot is already verified at creation. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • subscribe_lookalike_watchTurn on Lookalike Watch: newly published npm, PyPI, Packagist, Go module and MCP-registry artifacts are watched for names confusable with your brand tokens, with alerts and a month…No findings

    Why it is in this group

    • The name "subscribe_lookalike_watch" says "subscribe": a word for a change.
    Description, as the server wrote it
    Turn on Lookalike Watch: newly published npm, PyPI, Packagist, Go module and MCP-registry artifacts are watched for names confusable with your brand tokens, with alerts and a monthly report (list_lookalike_alerts, list_lookalike_reports). Not a billed proof: no quota is charged. Lookalike Watch is part of the €29 plan and above (enforced while billing is live). Refused 422 when not eligible, with the reason as the code: plan_upgrade_required, no_verified_domain, no_active_delegation, delegation_sample_exhausted, account_scheduled_for_deletion, or for the delivery address notify_email_not_owned / no_notify_email; 409 when already on; 503 eligibility_unavailable means unknown, not no, so retry. Needs lookalike-watch:write on an account-wide key (a key bound to one sub-account is refused). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • test_verifyAuto-complete a verification in test mode (pk_test_* API keys only).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Auto-complete a verification in test mode (pk_test_* API keys only). Useful for testing flows without real OTP delivery. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • trigger_verificationTrigger a DNS/HTTP verification check for a pending domain verification.No findings

    Why it is in this group

    • The name "trigger_verification" says "trigger": a word for a change.
    Description, as the server wrote it
    Trigger a DNS/HTTP verification check for a pending domain verification. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • verify_2faSubmit a verification code to complete a 2FA challenge.No findings

    Why it is in this group

    • The description's first verb is "submit": a word for a change.
    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    Description, as the server wrote it
    Submit a verification code to complete a 2FA challenge. Rate limited to 10 attempts per minute. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • verify_delegationVerify a Proof of Delegation — the attestation that a domain authorized a specific agent artifact.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Verify a Proof of Delegation — the attestation that a domain authorized a specific agent artifact. Pass either the artifact's card (MCP server.json / A2A agent card) or a raw delegation token, PLUS two facts you established yourself: the artifact identity you resolved (the package you are installing, the endpoint you are calling) and the domain you expect to stand behind it. Both are required — a token can be copied into someone else's card, and any domain owner can mint a valid delegation naming someone else's package, so a verdict without both pins would mean 'some domain said something about some artifact'. WHERE THE IDENTITY MAY COME FROM: it is the artifact you are acting on, and never a value read from inside the artifact you are checking. A name in the artifact's own package.json, card or manifest is self-declared and editable by whoever ships it, so checking it against the delegation compares the artifact with itself. Resolve it afresh at call time instead of reusing a value from earlier in this conversation, which may already be stale. When no independently resolvable identity exists — a local or unpublished artifact — you have nothing to compare against, and that is the honest answer: report it rather than a mismatch, because a mismatch here reads as an accusation against the domain named in the delegation. The verifier walks signature → principal → delegate → revocation status, including the cascade down to the domain control proof. Requires no API key. What a verified result means: the expected domain's controller authorized this artifact — NOT that the artifact is safe, audited or endorsed.

    Annotations the server declares

    • readOnlyHint: true
  • verify_delegationsBatch-verify up to 50 Proof of Delegation artifacts in one call — the inventory half of the checker (h-proof-checker-mcp): re-check everything you already trust instead of one veri…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Batch-verify up to 50 Proof of Delegation artifacts in one call — the inventory half of the checker (h-proof-checker-mcp): re-check everything you already trust instead of one verify_delegation call per artifact. Each item takes the same shape verify_delegation requires (card XOR token, delegate, expected_principal) and follows the same rule about where identity comes from: each `delegate` is the artifact you are acting on, never a value read from inside the artifact you are checking, and resolved afresh at call time. Items are verified INDEPENDENTLY — no cross-item state, nothing persisted, one item failing never affects another item's result. This tool does NOT discover what you have installed and does NOT fetch anything on your behalf: it verifies material you already hold, the same trust boundary verify_delegation draws. Revocation is always checked (there is no check_status:false here — the point of a batch re-check is to see what changed since you last looked). Each result carries an `outcome`: confirmed_valid (verified), confirmed_invalid (a genuine negative verdict — revoked, expired, mismatched, malformed, and similar), no_claim_found (the artifact publishes no delegation at all — an absence, never an accusation), or unconfirmed (we could not reach the issuer or otherwise get a confident answer right now — NEVER treat this as a bad verdict). Requires no API key. `checked_at` on each result is the moment THAT item's own check completed, not one timestamp shared across the call.

    Annotations the server declares

    • readOnlyHint: true
  • verify_domainTrigger domain verification.No findings

    Why it is in this group

    • The description's first verb is "trigger": a word for a change.
    Description, as the server wrote it
    Trigger domain verification. Checks DNS records or other verification method to confirm domain ownership. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
  • verify_email_otpSubmit the OTP code to verify an email addition.No findings

    Why it is in this group

    • The description's first verb is "submit": a word for a change.
    • The input takes a statement or command to run (input.code), which can change anything it can reach.
    Description, as the server wrote it
    Submit the OTP code to verify an email addition. Completes the add-email flow if the code is correct. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: false
    • destructiveHint: false
Only reads 97Show 97 read-only tools
  • check_domain_email_statusCheck the email sending setup status for a domain, including DNS record configuration progress.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "check_domain_email_status" says "status": a word for reading.

    What it can reach

    • private-dataThe name "check_domain_email_status" says "status" and "email": it reads mail.
    • private-dataThe description's first sentence says "email": it reads mail.
    • untrusted-inputThe name "check_domain_email_status" says "status" and "email": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Check the email sending setup status for a domain, including DNS record configuration progress. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_2fa_statusCheck the status of a 2FA session by session ID.No findings

    Why it is in this group

    • The name "get_2fa_status" says "get": a word for reading.
    Description, as the server wrote it
    Check the status of a 2FA session by session ID. Returns whether the challenge has been completed, is pending, or has expired. Agent usage: Poll this after calling start_2fa. Check every few seconds. Terminal states: "verified" (proceed with protected operation), "expired" (restart with start_2fa). While "pending", the user has not yet entered their code. Before calling this for a challenge you created, make sure your reply text already shows the user what to act on — the link itself, the SMS text and number, or a note to check their inbox; a link that appeared only in a tool result is one they never saw. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_add_email_statusCheck the status of an in-progress email addition by session ID.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_add_email_status" says "get": a word for reading.

    What it can reach

    • private-dataThe name "get_add_email_status" says "get" and "email": it reads mail.
    • private-dataThe description's first sentence says "email": it reads mail.
    • untrusted-inputThe name "get_add_email_status" says "get" and "email": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Check the status of an in-progress email addition by session ID. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_add_phone_statusCheck the status of an in-progress phone addition by session ID.No findings

    Why it is in this group

    • The name "get_add_phone_status" says "get": a word for reading.
    Description, as the server wrote it
    Check the status of an in-progress phone addition by session ID. Poll until terminal state. Before calling this for a challenge you created, make sure your reply text already shows the user what to act on — the link itself, the SMS text and number, or a note to check their inbox; a link that appeared only in a tool result is one they never saw. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_api_key_usageGet per-API-key usage for a given key id: verification counts by type/channel/status, plus verification-request/confirmation/authorization totals, and attribution context (attribut…No findings

    Why it is in this group

    • The name "get_api_key_usage" says "get": a word for reading.
    Description, as the server wrote it
    Get per-API-key usage for a given key id: verification counts by type/channel/status, plus verification-request/confirmation/authorization totals, and attribution context (attribution_cutoff_at, attributed_fraction). The counts cover the key and every key it replaced (api_key.replaced_key_ids). Counts only — no recipient identifiers. Scoped to the authenticated account; an API-key caller may read only its own key. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), or sign in with start_login — either opens this tool — then call this tool again.

    Annotations the server declares

    • readOnlyHint: true
  • get_approval_channelGet an approval channel by ID.No findings

    Why it is in this group

    • The name "get_approval_channel" says "get": a word for reading.
    Description, as the server wrote it
    Get an approval channel by ID. Returns the config including channels, timeout, and status. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_approval_channel_keysGet the encryption keypair for an approval channel.No findings

    Why it is in this group

    • The name "get_approval_channel_keys" says "get": a word for reading.
    Description, as the server wrote it
    Get the encryption keypair for an approval channel. With `hitl:read` it returns the public key, encrypted private key, KDF salt, and key ID (kid). A key holding `confirmations:create` without `hitl:read` receives only `public_key` and `kid` — what a confirmation message is sealed to, never the private-key material. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_assetDeprecated: use get_my_proofNo findings

    Why it is in this group

    • The name "get_asset" says "get": a word for reading.
    Description, as the server wrote it
    Deprecated: use get_my_proof

    Annotations the server declares

    • readOnlyHint: true
  • get_authorizationGet an authorization by ID.No findings

    Why it is in this group

    • The name "get_authorization" says "get": a word for reading.
    Description, as the server wrote it
    Get an authorization by ID. Returns the current state of the authorization including status and usage statistics. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_balanceGet the prepaid balance (in euro cents and mills), the low-balance threshold, the top-up amounts on offer and the auto top-up setting.No findings

    Why it is in this group

    • The name "get_balance" says "get": a word for reading.
    Description, as the server wrote it
    Get the prepaid balance (in euro cents and mills), the low-balance threshold, the top-up amounts on offer and the auto top-up setting. Proofs past the plan's included amount are drawn from this balance; once billing is live, an account whose balance is at or below zero is refused new proof requests (402 balance_empty) until it tops up. billing_enabled says whether billing is live. Topping up and changing auto top-up are done by the owner in the dashboard, on the Billing page (https://proof.holdings/billing). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_circleGet a Circle by ID.No findings

    Why it is in this group

    • The name "get_circle" says "get": a word for reading.
    Description, as the server wrote it
    Get a Circle by ID. Returns the Circle including its members and per-member channel presence booleans (an identifier is NEVER returned — SEC-PM-006). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_companyGet the account company profile: legal name, registration code, country, EU VAT number, billing address and billing email, with the state of the VAT number VIES check.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_company" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "get" and "email": it reads mail.
    • untrusted-inputThe description's first sentence says "get" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Get the account company profile: legal name, registration code, country, EU VAT number, billing address and billing email, with the state of the VAT number VIES check. company is null before one is saved. Needs settings:read on an account-wide key; a key bound to one sub-account is refused account_key_required, since this is the account itself. The owner edits it in the dashboard on the Billing page (https://proof.holdings/billing). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_confirmationGet a confirmation by ID.No findings

    Why it is in this group

    • The name "get_confirmation" says "get": a word for reading.
    Description, as the server wrote it
    Get a confirmation by ID. Returns the full confirmation including status, response, and proof token. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_current_sub_accountGet the current sub-account record: with a sub-account key, that key's own sub-account; otherwise the account's primary sub-account.No findings

    Why it is in this group

    • The name "get_current_sub_account" says "get": a word for reading.
    Description, as the server wrote it
    Get the current sub-account record: with a sub-account key, that key's own sub-account; otherwise the account's primary sub-account. The first call creates a primary sub-account if the account has none (never for a sub-account key, which gets profile_not_found). Returns profile details, theme, custom links, and public proof display settings. Its write twin is update_public_page (the same record). In the dashboard, the Profile page (https://proof.holdings/profile) edits whichever sub-account is selected there. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_current_userGet the signed-in user's account details, plan and settings.No findings

    Why it is in this group

    • The name "get_current_user" says "get": a word for reading.
    Description, as the server wrote it
    Get the signed-in user's account details, plan and settings. Needs a login session: call start_login, then wait_for_login until it reports success. An API key alone cannot read this — for the key's own account use get_self_api_key or get_settings. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_default_templatesGet the default message templates — one for each channel and message type a message is actually sent for.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_default_templates" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "get" and "message": it reads messages.
    • untrusted-inputThe description's first sentence says "get" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Get the default message templates — one for each channel and message type a message is actually sent for. These are the built-in templates a sub-account sends when it has no custom template of its own. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_delegationGet one of your delegations by Mongo id or ph_dlg_* handle.No findings

    Why it is in this group

    • The name "get_delegation" says "get": a word for reading.
    Description, as the server wrote it
    Get one of your delegations by Mongo id or ph_dlg_* handle. Returns the stored publishable token plus the DERIVED effective_status/is_valid — the delegation is only as live as the control proof it stands on (a revoked, suspended or expired domain proof invalidates it) and never outlives its own expires_at, whichever comes first. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_delegation_carriersReport where a delegation is still visible to a third party, which matters after a revocation: the _mcp.<principal> DNS pointer and, for a url delegate, a direct card fetch.Reads text others writeNo findings

    Why it is in this group

    • The name "get_delegation_carriers" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Report where a delegation is still visible to a third party, which matters after a revocation: the _mcp.<principal> DNS pointer and, for a url delegate, a direct card fetch. Takes the delegation id or its ph_dlg_* handle; the same read scope as get_delegation (delegations:read), with no revoked-only gate. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_delegation_tokenGet the current token of an active delegation by its public ph_dlg_* handle — after a signing-key rotation, the re-signed token to publish in place of the old one.No findings

    Why it is in this group

    • The name "get_delegation_token" says "get": a word for reading.
    Description, as the server wrote it
    Get the current token of an active delegation by its public ph_dlg_* handle — after a signing-key rotation, the re-signed token to publish in place of the old one. Public endpoint — no API key required, since the token is already published with the delegation. Any handle that is not an active delegation (revoked, suspended, expired or unknown) answers the same not_found.

    Annotations the server declares

    • readOnlyHint: true
  • get_dns_providersGet metadata for all supported DNS providers, including required credential fields and documentation links.Reads private data1 finding

    Why it is in this group

    • The name "get_dns_providers" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "get" and "credential": it reads secrets.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...orted DNS providers, including required credential fields and documentation links. ACCESS..."

      What this check looks for
    Description, as the server wrote it
    Get metadata for all supported DNS providers, including required credential fields and documentation links. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_domainGet details of a specific domain by ID, including verification status, DNS records, and provider connections.No findings

    Why it is in this group

    • The name "get_domain" says "get": a word for reading.
    Description, as the server wrote it
    Get details of a specific domain by ID, including verification status, DNS records, and provider connections. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_hitlDeprecated: use get_approval_channelNo findings

    Why it is in this group

    • The name "get_hitl" says "get": a word for reading.
    Description, as the server wrote it
    Deprecated: use get_approval_channel

    Annotations the server declares

    • readOnlyHint: true
  • get_hitl_keysDeprecated: use get_approval_channel_keysNo findings

    Why it is in this group

    • The name "get_hitl_keys" says "get": a word for reading.
    Description, as the server wrote it
    Deprecated: use get_approval_channel_keys

    Annotations the server declares

    • readOnlyHint: true
  • get_identity_challengeGet a Proof of Me identity challenge by ID.No findings

    Why it is in this group

    • The name "get_identity_challenge" says "get": a word for reading.
    Description, as the server wrote it
    Get a Proof of Me identity challenge by ID. Returns its status (pending, confirmed, denied, cancelled, failed, expired, revoked or suspended), the channel the CONFIRM ran on, and — once the person being checked decided — the proof token and its proof_id. Poll this for resolution. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_lookalike_watchGet the Lookalike Watch subscription, in the shape subscribe_lookalike_watch returned it.No findings

    Why it is in this group

    • The name "get_lookalike_watch" says "get": a word for reading.
    Description, as the server wrote it
    Get the Lookalike Watch subscription, in the shape subscribe_lookalike_watch returned it. 404 when the account never subscribed. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_multi_channel_verification_statusGet the status of a multi-channel verification group by its group_id.No findings

    Why it is in this group

    • The name "get_multi_channel_verification_status" says "get": a word for reading.
    Description, as the server wrote it
    Get the status of a multi-channel verification group by its group_id. Returns the aggregate status (pending/verified/expired), the winning_channel once one completes, per-channel statuses, and the proof token (with expires_at) when the group is verified. Before calling this for a challenge you created, make sure your reply text already shows the user what to act on — the link itself, the SMS text and number, or a note to check their inbox; a link that appeared only in a tool result is one they never saw. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_my_profileDeprecated: use get_current_sub_accountNo findings

    Why it is in this group

    • The name "get_my_profile" says "get": a word for reading.
    Description, as the server wrote it
    Deprecated: use get_current_sub_account

    Annotations the server declares

    • readOnlyHint: true
  • get_my_proofGet a single verified asset by ID.No findings

    Why it is in this group

    • The name "get_my_proof" says "get": a word for reading.
    Description, as the server wrote it
    Get a single verified asset by ID. Returns details including type, value, status, and verification timestamps. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_platform_summaryGet a one-call account snapshot: quota with end-of-month projection, request health (pending/completed/expired counts + success rate), per-channel completion rates, approval channe…No findings

    Why it is in this group

    • The name "get_platform_summary" says "get": a word for reading.
    Description, as the server wrote it
    Get a one-call account snapshot: quota with end-of-month projection, request health (pending/completed/expired counts + success rate), per-channel completion rates, approval channel counts, and active API key count. The same data the dashboard home renders. The hitl_channels sub-object requires the hitl:read scope. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_profileDeprecated: use get_sub_accountNo findings

    Why it is in this group

    • The name "get_profile" says "get": a word for reading.
    Description, as the server wrote it
    Deprecated: use get_sub_account

    Annotations the server declares

    • readOnlyHint: true
  • get_profile_assetsDeprecated: use list_public_page_proof_optionsNo findings

    Why it is in this group

    • The name "get_profile_assets" says "get": a word for reading.
    Description, as the server wrote it
    Deprecated: use list_public_page_proof_options

    Annotations the server declares

    • readOnlyHint: true
  • get_proof_statusGet the status of a proof by its public handle (ph_ctl_* / ph_dlg_*) or a verification ID.No findings

    Why it is in this group

    • The name "get_proof_status" says "get": a word for reading.
    Description, as the server wrote it
    Get the status of a proof by its public handle (ph_ctl_* / ph_dlg_*) or a verification ID. Returns whether the proof is active, suspended, expired, or revoked — a live proof reads "active". ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_proof_tokenGet the current token of a proof you own, by its public ph_ctl_* handle.No findings

    Why it is in this group

    • The name "get_proof_token" says "get": a word for reading.
    Description, as the server wrote it
    Get the current token of a proof you own, by its public ph_ctl_* handle. After a signing-key rotation this is the re-signed token, which replaces any older copy you hold. Each read is audited. A revoked or expired proof answers proof_not_live; a suspended one is still served. The proof of one of the account's own verified assets (a domain, phone or email verified on the account itself) answers owner_session_required here whatever its status (with a live key; a test key gets not_found): this tool sends the API key, and such a token is read by the signed-in owner in the dashboard. A key bound to a sub-account reads only that sub-account's proofs; another's answers not_found. For a delegation (ph_dlg_*) use get_delegation_token or get_delegation instead. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_request_by_referenceGet a verification request by its reference ID (your unique identifier).No findings

    Why it is in this group

    • The name "get_request_by_reference" says "get": a word for reading.
    Description, as the server wrote it
    Get a verification request by its reference ID (your unique identifier). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_request_proofsGet proof tokens for verified assets in a verification request.No findings

    Why it is in this group

    • The name "get_request_proofs" says "get": a word for reading.
    Description, as the server wrote it
    Get proof tokens for verified assets in a verification request. Returns proof tokens that can be used for offline verification. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_self_api_keyGet the calling API key's own redacted metadata (id, name, key_prefix, environment, scopes, last_used_at, revoked_at, created_at) for agent self-inspection.No findings

    Why it is in this group

    • The name "get_self_api_key" says "get": a word for reading.
    Description, as the server wrote it
    Get the calling API key's own redacted metadata (id, name, key_prefix, environment, scopes, last_used_at, revoked_at, created_at) for agent self-inspection. Never returns the key hash or full secret. Requires API-key auth — a JWT session has no single-key context (returns 400 api_key_required). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_sessionGet a session by ID.No findings

    Why it is in this group

    • The name "get_session" says "get": a word for reading.
    Description, as the server wrote it
    Get a session by ID. Returns the session status, verification details, and proof token if verified. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_settingsGet account settings: the outbound webhook endpoint with its event subscriptions, and the default proof lifetime.No findings

    Why it is in this group

    • The name "get_settings" says "get": a word for reading.
    Description, as the server wrote it
    Get account settings: the outbound webhook endpoint with its event subscriptions, and the default proof lifetime. Branding (name, logo, colour, email theme, support email) belongs to each sub-account: read it with get_sub_account. The webhook signing secret is NOT returned to an API key — the response reports webhook.secret_set instead, and the value is shown only when it is made: in the update_settings response that created or rotated it, or to the owner rotating it on the Webhooks page in the dashboard (https://proof.holdings/webhooks). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_sub_accountGet one sub-account by ID, with its full details including theme, custom links, and verification display settings.No findings

    Why it is in this group

    • The name "get_sub_account" says "get": a word for reading.
    Description, as the server wrote it
    Get one sub-account by ID, with its full details including theme, custom links, and verification display settings. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_subscriptionGet the current subscription details including plan, status, billing period, and usage limits.No findings

    Why it is in this group

    • The name "get_subscription" says "get": a word for reading.
    Description, as the server wrote it
    Get the current subscription details including plan, status, billing period, and usage limits. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_templateGet the template a sub-account sends for a channel and message type: its custom template if set (scope "project"), otherwise the default (scope "default").Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "get_template" says "get": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "get" and "message": it reads messages.
    • untrusted-inputThe description's first sentence says "get" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    Get the template a sub-account sends for a channel and message type: its custom template if set (scope "project"), otherwise the default (scope "default"). The response names the sub-account in profile_id. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_usageGet usage metrics for the authenticated account.No findings

    Why it is in this group

    • The name "get_usage" says "get": a word for reading.
    Description, as the server wrote it
    Get usage metrics for the authenticated account. Shows verification counts, API calls, and quota usage. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_user_domain_verification_statusGet the current status of a domain verification session, including challenge details.No findings

    Why it is in this group

    • The name "get_user_domain_verification_status" says "get": a word for reading.
    Description, as the server wrote it
    Get the current status of a domain verification session, including challenge details. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_verificationGet a verification by ID.No findings

    Why it is in this group

    • The name "get_verification" says "get": a word for reading.
    Description, as the server wrote it
    Get a verification by ID. Returns the full verification object including status, channel, and proof token if verified. Before calling this for a challenge you created, make sure your reply text already shows the user what to act on — the link itself, the SMS text and number, or a note to check their inbox; a link that appeared only in a tool result is one they never saw. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_verification_requestGet a verification request by ID.No findings

    Why it is in this group

    • The name "get_verification_request" says "get": a word for reading.
    Description, as the server wrote it
    Get a verification request by ID. Returns the request with all its asset verification statuses. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_verified_userGet a single verified user and their verifications by external user ID.No findings

    Why it is in this group

    • The name "get_verified_user" says "get": a word for reading.
    Description, as the server wrote it
    Get a single verified user and their verifications by external user ID. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_webhook_deliveryGet details of a single webhook delivery attempt including request/response payloads and retry history.No findings

    Why it is in this group

    • The name "get_webhook_delivery" says "get": a word for reading.
    Description, as the server wrote it
    Get details of a single webhook delivery attempt including request/response payloads and retry history. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_webhook_endpointGet one webhook endpoint by ID.No findings

    Why it is in this group

    • The name "get_webhook_endpoint" says "get": a word for reading.
    Description, as the server wrote it
    Get one webhook endpoint by ID. The signing secret is not returned (only create_webhook_endpoint and rotate_webhook_endpoint_secret return it). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • get_webhook_statsGet webhook delivery statistics including total deliveries, success/failure counts, and recent activity.No findings

    Why it is in this group

    • The name "get_webhook_stats" says "get": a word for reading.
    Description, as the server wrote it
    Get webhook delivery statistics including total deliveries, success/failure counts, and recent activity. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_api_keysList all API keys for the authenticated account.No findings

    Why it is in this group

    • The name "list_api_keys" says "list": a word for reading.
    Description, as the server wrote it
    List all API keys for the authenticated account. Returns key metadata (not the secret key values). ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_approval_channelsList approval channels with optional filters.No findings

    Why it is in this group

    • The name "list_approval_channels" says "list": a word for reading.
    Description, as the server wrote it
    List approval channels with optional filters. Returns paginated results. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_assetsDeprecated: use list_my_proofsNo findings

    Why it is in this group

    • The name "list_assets" says "list": a word for reading.
    Description, as the server wrote it
    Deprecated: use list_my_proofs

    Annotations the server declares

    • readOnlyHint: true
  • list_auth_sessionsList the current user's signed-in devices: every session that can still renew, idle ones included.No findings

    Why it is in this group

    • The name "list_auth_sessions" says "list": a word for reading.
    Description, as the server wrote it
    List the current user's signed-in devices: every session that can still renew, idle ones included. Each shows its channel, user agent and expires_at, which is when the session stops being able to renew (not when its current access token expires). When called via API key, no session is marked is_current. NOT AVAILABLE HERE: This tool is not available on the hosted Proof MCP server: it needs the auth:read or auth:write scope, which the hosted server never grants (an agent holding it could list and sign out the owner's devices). The account owner manages signed-in devices in the dashboard: Settings → Signed-in devices (https://proof.holdings/dev). A local (stdio) Proof MCP server run with an API key that holds the scope can call it.

    Annotations the server declares

    • readOnlyHint: true
  • list_authorizationsList authorizations with optional filters.No findings

    Why it is in this group

    • The name "list_authorizations" says "list": a word for reading.
    Description, as the server wrote it
    List authorizations with optional filters. Returns paginated results. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_balance_ledgerList the prepaid balance history, newest first: every top-up, refund and adjustment, and one usage row per month for that month's deductions.No findings

    Why it is in this group

    • The name "list_balance_ledger" says "list": a word for reading.
    Description, as the server wrote it
    List the prepaid balance history, newest first: every top-up, refund and adjustment, and one usage row per month for that month's deductions. Amounts are signed euro cents (credits positive). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_circle_member_channelsList a Circle member's channels.No findings

    Why it is in this group

    • The name "list_circle_member_channels" says "list": a word for reading.
    Description, as the server wrote it
    List a Circle member's channels. Returns channel metadata only (channel, status, verified_at) — an identifier is NEVER returned (SEC-PM-006). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_circle_membersList a Circle's members.No findings

    Why it is in this group

    • The name "list_circle_members" says "list": a word for reading.
    Description, as the server wrote it
    List a Circle's members. Each member carries channel-presence booleans (has_telegram / has_whatsapp) and the masked phone they enrolled from (enrolled_phone_hint, e.g. +9••••••4171) — a full identifier is NEVER returned (SEC-PM-006). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_circlesList Circles with optional filters.No findings

    Why it is in this group

    • The name "list_circles" says "list": a word for reading.
    Description, as the server wrote it
    List Circles with optional filters. Archived Circles are excluded by default; pass status="archived" to surface them. Returns paginated results. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_confirmationsList confirmations with optional filters.No findings

    Why it is in this group

    • The name "list_confirmations" says "list": a word for reading.
    Description, as the server wrote it
    List confirmations with optional filters. Returns paginated results with status, approval channel and sub-account (profile_id) filtering. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_delegationsList your own delegations with optional filters.No findings

    Why it is in this group

    • The name "list_delegations" says "list": a word for reading.
    Description, as the server wrote it
    List your own delegations with optional filters. Each item carries the DERIVED effective_status/is_valid beside its stored status — read effective_status, since status records only whether the owner revoked the delegation themselves, so a delegation still reads active there after its domain control proof was revoked, suspended or expired, and after its OWN lifetime ran out. effective_status accounts for all of those: it reports expired once either lifetime has passed, whichever is earlier. Tokens are not included in the list — use get_delegation for the stored token. There is no public enumeration of third-party delegations. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_dns_credentialsList all stored DNS provider credentials for the authenticated account.Reads private data1 finding

    Why it is in this group

    • The name "list_dns_credentials" says "list": a word for reading.

    What it can reach

    • private-dataThe name "list_dns_credentials" says "list" and "credential": it reads secrets.
    • private-dataThe description's first sentence says "list" and "credential": it reads secrets.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "List all stored DNS provider credentials for the authenticated account. Returns..."

      What this check looks for
    Description, as the server wrote it
    List all stored DNS provider credentials for the authenticated account. Returns credential metadata (not secret values). ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_domainsList all domains for the authenticated account.No findings

    Why it is in this group

    • The name "list_domains" says "list": a word for reading.
    Description, as the server wrote it
    List all domains for the authenticated account. Returns domain metadata including verification status. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_emailsList all email addresses associated with the authenticated account.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_emails" says "list": a word for reading.

    What it can reach

    • private-dataThe name "list_emails" says "list" and "email": it reads mail.
    • private-dataThe description's first sentence says "list" and "email": it reads mail.
    • untrusted-inputThe name "list_emails" says "list" and "email": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "list" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    List all email addresses associated with the authenticated account. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_hitlsDeprecated: use list_approval_channelsNo findings

    Why it is in this group

    • The name "list_hitls" says "list": a word for reading.
    Description, as the server wrote it
    Deprecated: use list_approval_channels

    Annotations the server declares

    • readOnlyHint: true
  • list_incoming_requestsList incoming verification requests where the authenticated user is the subject.No findings

    Why it is in this group

    • The name "list_incoming_requests" says "list": a word for reading.
    Description, as the server wrote it
    List incoming verification requests where the authenticated user is the subject. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_lookalike_alertsList Lookalike Watch alerts, newest first: artifacts whose names resemble one of your brand tokens, with the evidence for each.No findings

    Why it is in this group

    • The name "list_lookalike_alerts" says "list": a word for reading.
    Description, as the server wrote it
    List Lookalike Watch alerts, newest first: artifacts whose names resemble one of your brand tokens, with the evidence for each. A caller who never subscribed gets an empty page, not a 404. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_lookalike_reportsList the monthly Lookalike Watch reports, newest first.No findings

    Why it is in this group

    • The name "list_lookalike_reports" says "list": a word for reading.
    Description, as the server wrote it
    List the monthly Lookalike Watch reports, newest first. A month with no alerts still has a report, carrying the per-source coverage figures. A caller who never subscribed gets an empty page, not a 404. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_my_proofsList all verified assets for the authenticated user.No findings

    Why it is in this group

    • The name "list_my_proofs" says "list": a word for reading.
    Description, as the server wrote it
    List all verified assets for the authenticated user. Assets are verified identities (phones, emails, domains). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_my_requestsList verification requests created by the authenticated user.No findings

    Why it is in this group

    • The name "list_my_requests" says "list": a word for reading.
    Description, as the server wrote it
    List verification requests created by the authenticated user. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), or sign in with start_login — either opens this tool — then call this tool again.

    Annotations the server declares

    • readOnlyHint: true
  • list_phonesList all phone numbers associated with the authenticated account.No findings

    Why it is in this group

    • The name "list_phones" says "list": a word for reading.
    Description, as the server wrote it
    List all phone numbers associated with the authenticated account. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_profilesDeprecated: use list_sub_accountsNo findings

    Why it is in this group

    • The name "list_profiles" says "list": a word for reading.
    Description, as the server wrote it
    Deprecated: use list_sub_accounts

    Annotations the server declares

    • readOnlyHint: true
  • list_public_page_proof_optionsList the verified proofs that can be shown on the Public page (each one eligible to be listed with update_public_page_proofs).No findings

    Why it is in this group

    • The name "list_public_page_proof_options" says "list": a word for reading.
    Description, as the server wrote it
    List the verified proofs that can be shown on the Public page (each one eligible to be listed with update_public_page_proofs). ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_reissued_proofsList your proofs whose token was re-signed at or after an instant, oldest first — what to re-fetch after a signing-key rotation, for example when a webhook was missed.No findings

    Why it is in this group

    • The name "list_reissued_proofs" says "list": a word for reading.
    Description, as the server wrote it
    List your proofs whose token was re-signed at or after an instant, oldest first — what to re-fetch after a signing-key rotation, for example when a webhook was missed. Items are references {proof_id, reissued_at, token_url}, never tokens: pull a ph_ctl_* item with get_proof_token and a ph_dlg_* item with get_delegation_token. Proofs of the account's own verified assets are not listed here (the API key cannot read their tokens); the dashboard shows them. A key bound to a sub-account lists only that sub-account's proofs and the account's delegations. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_revoked_proofsGet the revocation list for offline proof validation.No findings

    Why it is in this group

    • The name "list_revoked_proofs" says "list": a word for reading.
    Description, as the server wrote it
    Get the revocation list for offline proof validation. Returns a signed list of all revoked proof IDs. Reuse a fetched list for up to 5 minutes (its cache lifetime), then fetch it again to see new revocations; if you cannot, its signature stays verifiable offline for 1 hour.

    Annotations the server declares

    • readOnlyHint: true
  • list_sub_accountsList every sub-account of the authenticated account, the primary one included.No findings

    Why it is in this group

    • The name "list_sub_accounts" says "list": a word for reading.
    Description, as the server wrote it
    List every sub-account of the authenticated account, the primary one included. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_templatesList the custom message templates of one sub-account, organized by channel and message type.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "list_templates" says "list": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "list" and "message": it reads messages.
    • untrusted-inputThe description's first sentence says "list" and "message": it reads messages, which other people can write.
    Description, as the server wrote it
    List the custom message templates of one sub-account, organized by channel and message type. Templates belong to a sub-account, not to the account: profile_id picks it — omitted, a sub-account key lists its own sub-account and an account-wide key the primary sub-account. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_verification_requestsList verification requests with optional filters.No findings

    Why it is in this group

    • The name "list_verification_requests" says "list": a word for reading.
    Description, as the server wrote it
    List verification requests with optional filters. Returns paginated results. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_verificationsList verifications with optional filters.No findings

    Why it is in this group

    • The name "list_verifications" says "list": a word for reading.
    Description, as the server wrote it
    List verifications with optional filters. Returns paginated results. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_verified_usersList verified users grouped by external_user_id.No findings

    Why it is in this group

    • The name "list_verified_users" says "list": a word for reading.
    Description, as the server wrote it
    List verified users grouped by external_user_id. Shows all verifications per user. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_webhook_deliveriesList webhook delivery attempts with pagination and filtering.No findings

    Why it is in this group

    • The name "list_webhook_deliveries" says "list": a word for reading.
    Description, as the server wrote it
    List webhook delivery attempts with pagination and filtering. Shows delivery status, response codes, and timestamps. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • list_webhook_endpointsList the account's webhook endpoints (URL, events, scope, sub-accounts, status).Reads text others writeNo findings

    Why it is in this group

    • The name "list_webhook_endpoints" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "url": it reads web pages, which anyone can write.
    Description, as the server wrote it
    List the account's webhook endpoints (URL, events, scope, sub-accounts, status). Secrets are never listed. A sub-account key sees only the endpoints scoped to exactly its own sub-account. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • preview_email_removalPreview what remove_email would do to one email address, without changing anything: the counts the dashboard Remove dialog shows, or the reason removal would be refused.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "preview_email_removal" says "preview": a word for reading.

    What it can reach

    • private-dataThe name "preview_email_removal" says "preview" and "email": it reads mail.
    • private-dataThe description's first sentence says "preview" and "email": it reads mail.
    • untrusted-inputThe name "preview_email_removal" says "preview" and "email": it reads inbound email, which other people can write.
    • untrusted-inputThe description's first sentence says "preview" and "email": it reads inbound email, which other people can write.
    Description, as the server wrote it
    Preview what remove_email would do to one email address, without changing anything: the counts the dashboard Remove dialog shows, or the reason removal would be refused. Needs a signed-in session, like remove_email. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • preview_phone_removalPreview what remove_phone would do to one phone, without changing anything: the counts the dashboard Remove dialog shows, or the reason removal would be refused.No findings

    Why it is in this group

    • The name "preview_phone_removal" says "preview": a word for reading.
    Description, as the server wrote it
    Preview what remove_phone would do to one phone, without changing anything: the counts the dashboard Remove dialog shows, or the reason removal would be refused. Needs a signed-in session, like remove_phone. ACCESS: needs a Proof account, signed in: call start_login, show the user its challenge, then wait_for_login, then call this tool again. Authenticating this client alone does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • preview_profile_deletionDeprecated: use preview_sub_account_deletionNo findings

    Why it is in this group

    • The name "preview_profile_deletion" says "preview": a word for reading.
    Description, as the server wrote it
    Deprecated: use preview_sub_account_deletion

    Annotations the server declares

    • readOnlyHint: true
  • preview_sub_account_deletionPreview what delete_sub_account would do to one sub-account, without changing anything: the counts the dashboard Delete sub-account dialog shows and the sub-account that would take…No findings

    Why it is in this group

    • The name "preview_sub_account_deletion" says "preview": a word for reading.
    Description, as the server wrote it
    Preview what delete_sub_account would do to one sub-account, without changing anything: the counts the dashboard Delete sub-account dialog shows and the sub-account that would take its place, or why deletion is refused (allowed: false). Needs profiles:read; a key bound to a sub-account previews only its own. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • preview_templatePreview a template with sample data before saving, as a sub-account would send it.No findings

    Why it is in this group

    • The name "preview_template" says "preview": a word for reading.
    Description, as the server wrote it
    Preview a template with sample data before saving, as a sub-account would send it. Shows how the message will look with placeholder variables filled in. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • proof_holdings_statusReports whether this server's Proof of Delegation holds, as answered by proof.holdings, its issuer: the status, the delegating principal, the delegate and the expiry.No findings

    Why it is in this group

    • The name "proof_holdings_status" says "status": a word for reading.
    Description, as the server wrote it
    Reports whether this server's Proof of Delegation holds, as answered by proof.holdings, its issuer: the status, the delegating principal, the delegate and the expiry. Read-only; takes no arguments.

    Annotations the server declares

    • readOnlyHint: true
  • validate_proofValidate a proof token online.No findings

    Why it is in this group

    • The name "validate_proof" says "validate": a word for reading.
    Description, as the server wrote it
    Validate a proof token online. Checks the token signature, expiry, and revocation status against the server, and optionally that the proof is about the identifier you expect. Public endpoint — no API key required.

    Annotations the server declares

    • readOnlyHint: true
  • wait_for_2faPoll a 2FA session until the user completes the challenge.No findings

    Why it is in this group

    • The name "wait_for_2fa" says "wait": a word for reading.
    Description, as the server wrote it
    Poll a 2FA session until the user completes the challenge. Uses exponential backoff (2s initial, 1.5x, 30s max) with jitter. Agent usage: Call this after start_2fa with the returned session_id. Terminal states: "verified" (challenge completed — proceed with the protected operation), "expired" (offer to restart with start_2fa). Before polling, present start_2fa's challenge: pass its `deep_link` to render_auth_link on telegram/whatsapp, or show its `sms_message` on sms. The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • wait_for_account_creationPoll an account-bootstrap session until the user completes verification.No findings

    Why it is in this group

    • The name "wait_for_account_creation" says "wait": a word for reading.
    Description, as the server wrote it
    Poll an account-bootstrap session until the user completes verification. Uses exponential backoff (2s initial, 1.5x, 30s max) with jitter. Agent usage: Call this after create_account with the returned session id. Terminal states: "verified" (this server keeps the session for this connection; the `user_id` field in the terminal body identifies the authenticated user), "expired", "completed_elsewhere" (email only: the user pressed "Sign in here" on the email link's page, so the browser they clicked from is signed in and this connection never will be — tell them so, and start a new login if this connection still needs one), "account_access_off" (WhatsApp, Telegram or SMS only: the number signs in to an account that turned its Account access off, so nobody is signed in and no account is created — tell the user to sign in with an email or phone that has account access). A result with status "pending" means the wait ran out before the user finished — call this tool again with the same id. Works identically whether the underlying flow created a new User or logged in an existing one. Before calling this for a challenge you created, make sure your reply text already shows the user what to act on — the link itself, the SMS text and number, or a note to check their inbox; a link that appeared only in a tool result is one they never saw.

    Annotations the server declares

    • readOnlyHint: true
  • wait_for_chat_id_discoveryPoll a chat ID discovery token until the user interacts with the Telegram bot.Reads private dataReads text others writeNo findings

    Why it is in this group

    • The name "wait_for_chat_id_discovery" says "wait": a word for reading.

    What it can reach

    • private-dataThe name "wait_for_chat_id_discovery" says "wait" and "chat": it reads messages.
    • private-dataThe description's first sentence says "chat": it reads messages.
    • untrusted-inputThe name "wait_for_chat_id_discovery" says "wait" and "chat": it reads messages, which other people can write.
    • untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
    Description, as the server wrote it
    Poll a chat ID discovery token until the user interacts with the Telegram bot. Uses exponential backoff (2s initial, 1.5x, 30s max) with jitter. Agent usage: Call this after create_chat_id_discovery. Present the discovery response's `deep_link` with render_auth_link first, then poll with the returned token. Terminal states: "completed" (chat_id discovered — use it when creating an approval channel with a Telegram channel), "expired". While "pending", the user has not yet opened the Telegram link. The user does not see tool results — most clients fold them away, render_auth_link's output included. Before you wait or poll, put what the user must act on into your own reply text: the link itself (not a sentence announcing it), the SMS text and number, or a note to check their inbox. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • wait_for_confirmationPoll a confirmation until the approver responds.No findings

    Why it is in this group

    • The name "wait_for_confirmation" says "wait": a word for reading.
    Description, as the server wrote it
    Poll a confirmation until the approver responds. Uses exponential backoff (2s initial, 1.5x, 30s max) with jitter. Agent usage: Call this after create_confirmation with the returned confirmation ID. Terminal states: "approved" (action authorized — check the proof_token), "denied" (action rejected). While "pending", the approver has not yet responded. This poll returns no link — the approval request is delivered to the approver's own channel, and only the owner's "Send again" (`POST /api/v1/confirmations/{id}/resend`, which no tool calls yet) delivers it there again. If the owner will decide instead, call get_confirmation_approval_link for the owner's `approval_url`; it needs the confirmation to be still pending — the state this tool waits in — and also refuses once `timeout_at` has passed, so a long wait can outlive the link even while the status has not moved. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • wait_for_loginPoll a login session until the user completes authentication.1 finding

    Why it is in this group

    • The name "wait_for_login" says "wait": a word for reading.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...ls, phones, domains, API keys, 2FA, DNS credentials, verification requests, your Public pag..."

      What this check looks for
    Description, as the server wrote it
    Poll a login session until the user completes authentication. Uses exponential backoff (2s initial, 1.5x, 30s max) with jitter. Agent usage: Call this after start_login with the returned session ID. Terminal states: "verified" (login succeeded — this server keeps the session for this connection and signs your own account records with it: emails, phones, domains, API keys, 2FA, DNS credentials, verification requests, your Public page's username and proof list), "failed", "expired", "completed_elsewhere" (email only: the user pressed "Sign in here" on the email link's page, so the browser they clicked from is signed in and this connection never will be — tell them so, and start a new login if this connection still needs one), "account_access_off" (WhatsApp, Telegram or SMS only: the number signs in to an account that turned its Account access off, so nobody is signed in and no account is created — tell the user to sign in with an email or phone that has account access). A result with status "pending" means the wait ran out before the user finished — call this tool again with the same id. Before calling this for a challenge you created, make sure your reply text already shows the user what to act on — the link itself, the SMS text and number, or a note to check their inbox; a link that appeared only in a tool result is one they never saw.

    Annotations the server declares

    • readOnlyHint: true
  • wait_for_requestPoll a verification request until it reaches a terminal state (completed, expired, or cancelled).No findings

    Why it is in this group

    • The name "wait_for_request" says "wait": a word for reading.
    Description, as the server wrote it
    Poll a verification request until it reaches a terminal state (completed, expired, or cancelled). Uses exponential backoff (2s initial, 1.5x, 30s max) with jitter. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • wait_for_sessionPoll a session until it reaches a terminal state (verified, failed, or expired).No findings

    Why it is in this group

    • The name "wait_for_session" says "wait": a word for reading.
    Description, as the server wrote it
    Poll a session until it reaches a terminal state (verified, failed, or expired). Uses exponential backoff (2s initial, 1.5x, 30s max) with jitter. Before calling this for a challenge you created, make sure your reply text already shows the user what to act on — the link itself, the SMS text and number, or a note to check their inbox; a link that appeared only in a tool result is one they never saw. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true
  • wait_for_verificationPoll a verification until it reaches a terminal state (verified, failed, expired, revoked, or cancelled).No findings

    Why it is in this group

    • The name "wait_for_verification" says "wait": a word for reading.
    Description, as the server wrote it
    Poll a verification until it reaches a terminal state (verified, failed, expired, revoked, or cancelled). Uses exponential backoff (2s initial, 1.5x, 30s max) with jitter. A multi-channel verification that lost the race is "cancelled" and one whose proof was withdrawn is "revoked"; both are final, so the wait returns rather than polling on. Before calling this for a challenge you created, make sure your reply text already shows the user what to act on — the link itself, the SMS text and number, or a note to check their inbox; a link that appeared only in a tool result is one they never saw. ACCESS: needs a Proof account. Authenticate this client (Claude Code: /mcp → Authenticate), then call this tool again. start_login does NOT open this tool.

    Annotations the server declares

    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

3751 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 11 untrusted-input tools breaks every one.

deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__proof__check_domain_email_status",
      "mcp__proof__get_add_email_status",
      "mcp__proof__get_company",
      "mcp__proof__get_default_templates",
      "mcp__proof__get_delegation_carriers",
      "mcp__proof__get_template",
      "mcp__proof__list_emails",
      "mcp__proof__list_templates",
      "mcp__proof__list_webhook_endpoints",
      "mcp__proof__preview_email_removal",
      "mcp__proof__wait_for_chat_id_discovery"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:54 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
122
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://api.proof.holdings/.well-known/oauth-protected-resource/mcp
Authorization servers
https://api.proof.holdings
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 122 tools that change things (60 destructive, 10 irreversible, 52 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://api.proof.holdings/mcp: tools/list returned 219 tools to an anonymous client, including delete_domain_verification (destructive), cancel_verification_request (destructive), revoke_proof (destructive), pause_proof (destructive), resume_proof (destructive) and 117 more

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 120 to 122
  2. Nov 13, 2026
    • Tools that change things, listed without credentials: 101 to 120
  3. Nov 6, 2026
    • Tools that change things, listed without credentials: 96 to 101

Findings

Matches of fixed checks, with the text they matched.

1 high3 warn23 info
  • The description contains "Do not tell the user", an instruction to keep something from the user.

    Matched text

    description: "...ted mid-send and nothing was delivered. Do not tell the user a message was sent on the strength of a..."

    What this check looks for
  • The server marks "export_authorizations" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".

    Matched text

    annotations: {"readOnlyHint":true}; The input addresses people (input.to): what it sends cannot be taken back.

    What this check looks for
  • The server marks "get_confirmation_approval_link" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false}; The name "get_confirmation_approval_link" says "get": a word for reading.

    What this check looks for
  • The server marks "render_auth_link" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true}; The name "render_auth_link" says "link": a word for a change.

    What this check looks for
  • The input schema at properties.dns_provider.description mentions "credentials".

    Matched text

    inputSchema.properties.dns_provider.description: "DNS provider credentials (required for channel "auto")"

    What this check looks for
  • The description is 2,004 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...n call this tool again. Authenticating this client alone does NOT open this tool."

    What this check looks for
Show 21 more findings

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 120 -> 122.View diff
    • Tools that change things, listed without credentials: 120 to 122
  2. Tools3 added, 6 changed.+3 added~6 changedView diff
  3. Tools36 added, 103 changed.+36 added~103 changedView diff
  4. PostureRemote posture changed. Tools that change things, listed without credentials: 101 -> 120.View diff
    • Tools that change things, listed without credentials: 101 to 120
  5. Tools5 changed.~5 changedView diff
  6. Tools1 changed.~1 changedView diff
  7. Tools1 added, 1 changed.+1 added~1 changedView diff
  8. PostureRemote posture changed. Tools that change things, listed without credentials: 96 -> 101.View diff
    • Tools that change things, listed without credentials: 96 to 101
  9. Tools3 added, 3 changed.+3 added~3 changedView diff
  10. Tools9 added, 46 changed.+9 added~46 changedView diff

Install

Pinned to version 1.13.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http proof https://api.proof.holdings/mcp
claude mcp add --transport http proof https://api.proof.holdings/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__proof__get_verification",
      "mcp__proof__list_verifications",
      "mcp__proof__list_verified_users",
      "mcp__proof__get_verified_user",
      "mcp__proof__wait_for_verification",
      "mcp__proof__get_multi_channel_verification_status",
      "mcp__proof__get_verification_request",
      "mcp__proof__get_request_proofs",
      "mcp__proof__list_verification_requests",
      "mcp__proof__get_request_by_reference",
      "mcp__proof__wait_for_request",
      "mcp__proof__validate_proof",
      "mcp__proof__get_proof_status",
      "mcp__proof__list_revoked_proofs",
      "mcp__proof__get_proof_token",
      "mcp__proof__list_reissued_proofs",
      "mcp__proof__get_delegation_token",
      "mcp__proof__get_session",
      "mcp__proof__wait_for_session",
      "mcp__proof__list_my_proofs",
      "mcp__proof__list_assets",
      "mcp__proof__get_my_proof",
      "mcp__proof__get_asset",
      "mcp__proof__get_current_user",
      "mcp__proof__list_auth_sessions",
      "mcp__proof__get_usage",
      "mcp__proof__get_platform_summary",
      "mcp__proof__get_settings",
      "mcp__proof__search",
      "mcp__proof__get_self_api_key",
      "mcp__proof__get_api_key_usage",
      "mcp__proof__get_company",
      "mcp__proof__list_templates",
      "mcp__proof__get_default_templates",
      "mcp__proof__get_template",
      "mcp__proof__preview_template",
      "mcp__proof__get_webhook_stats",
      "mcp__proof__list_webhook_deliveries",
      "mcp__proof__get_webhook_delivery",
      "mcp__proof__list_webhook_endpoints",
      "mcp__proof__get_webhook_endpoint",
      "mcp__proof__get_subscription",
      "mcp__proof__get_balance",
      "mcp__proof__list_balance_ledger",
      "mcp__proof__list_sub_accounts",
      "mcp__proof__list_profiles",
      "mcp__proof__get_sub_account",
      "mcp__proof__get_profile",
      "mcp__proof__get_current_sub_account",
      "mcp__proof__get_my_profile",
      "mcp__proof__list_public_page_proof_options",
      "mcp__proof__get_profile_assets",
      "mcp__proof__preview_sub_account_deletion",
      "mcp__proof__preview_profile_deletion",
      "mcp__proof__list_emails",
      "mcp__proof__get_add_email_status",
      "mcp__proof__preview_email_removal",
      "mcp__proof__list_phones",
      "mcp__proof__get_add_phone_status",
      "mcp__proof__preview_phone_removal",
      "mcp__proof__list_api_keys",
      "mcp__proof__get_2fa_status",
      "mcp__proof__wait_for_2fa",
      "mcp__proof__list_domains",
      "mcp__proof__get_domain",
      "mcp__proof__get_dns_providers",
      "mcp__proof__check_domain_email_status",
      "mcp__proof__list_dns_credentials",
      "mcp__proof__list_my_requests",
      "mcp__proof__list_incoming_requests",
      "mcp__proof__get_user_domain_verification_status",
      "mcp__proof__get_authorization",
      "mcp__proof__list_authorizations",
      "mcp__proof__get_confirmation",
      "mcp__proof__list_confirmations",
      "mcp__proof__wait_for_confirmation",
      "mcp__proof__get_approval_channel",
      "mcp__proof__get_hitl",
      "mcp__proof__list_approval_channels",
      "mcp__proof__list_hitls",
      "mcp__proof__wait_for_chat_id_discovery",
      "mcp__proof__get_approval_channel_keys",
      "mcp__proof__get_hitl_keys",
      "mcp__proof__get_identity_challenge",
      "mcp__proof__list_circles",
      "mcp__proof__get_circle",
      "mcp__proof__list_circle_members",
      "mcp__proof__list_circle_member_channels",
      "mcp__proof__list_delegations",
      "mcp__proof__get_delegation",
      "mcp__proof__get_delegation_carriers",
      "mcp__proof__get_lookalike_watch",
      "mcp__proof__list_lookalike_alerts",
      "mcp__proof__list_lookalike_reports",
      "mcp__proof__wait_for_login",
      "mcp__proof__wait_for_account_creation",
      "mcp__proof__proof_holdings_status"
    ],
    "ask": [
      "mcp__proof__create_verification",
      "mcp__proof__trigger_verification",
      "mcp__proof__submit_verification_code",
      "mcp__proof__resend_verification",
      "mcp__proof__test_verify",
      "mcp__proof__start_domain_verification",
      "mcp__proof__check_domain_verification",
      "mcp__proof__create_multi_channel_verification",
      "mcp__proof__create_verification_request",
      "mcp__proof__create_session",
      "mcp__proof__export_data",
      "mcp__proof__render_template",
      "mcp__proof__retry_webhook_delivery",
      "mcp__proof__create_webhook_endpoint",
      "mcp__proof__start_add_email",
      "mcp__proof__verify_email_otp",
      "mcp__proof__resend_email_otp",
      "mcp__proof__start_add_phone",
      "mcp__proof__create_api_key",
      "mcp__proof__start_2fa",
      "mcp__proof__verify_2fa",
      "mcp__proof__verify_2fa_magic_link",
      "mcp__proof__add_domain",
      "mcp__proof__verify_domain",
      "mcp__proof__verify_domain_with_credentials",
      "mcp__proof__check_domain_credentials",
      "mcp__proof__start_domain_email_verification",
      "mcp__proof__confirm_domain_email_code",
      "mcp__proof__resend_domain_email",
      "mcp__proof__setup_domain_email",
      "mcp__proof__create_user_request",
      "mcp__proof__extend_request",
      "mcp__proof__share_request_email",
      "mcp__proof__start_user_domain_verification",
      "mcp__proof__check_user_domain_verification",
      "mcp__proof__claim_username",
      "mcp__proof__create_authorization",
      "mcp__proof__export_authorizations",
      "mcp__proof__create_confirmation",
      "mcp__proof__get_confirmation_approval_link",
      "mcp__proof__resend_confirmation",
      "mcp__proof__create_approval_channel",
      "mcp__proof__create_hitl",
      "mcp__proof__request_approval_channel_authorization",
      "mcp__proof__request_hitl_authorization",
      "mcp__proof__create_chat_id_discovery",
      "mcp__proof__poll_chat_id_discovery",
      "mcp__proof__create_identity_challenge",
      "mcp__proof__create_circle",
      "mcp__proof__add_circle_member",
      "mcp__proof__invite_circle_member",
      "mcp__proof__create_circle_member_drill",
      "mcp__proof__add_circle_member_channel",
      "mcp__proof__create_delegation",
      "mcp__proof__subscribe_lookalike_watch",
      "mcp__proof__verify_delegation",
      "mcp__proof__verify_delegations",
      "mcp__proof__start_login",
      "mcp__proof__create_account",
      "mcp__proof__send_account_email",
      "mcp__proof__start_2fa_for_action",
      "mcp__proof__render_auth_link"
    ],
    "deny": [
      "mcp__proof__delete_domain_verification",
      "mcp__proof__cancel_verification_request",
      "mcp__proof__revoke_proof",
      "mcp__proof__pause_proof",
      "mcp__proof__resume_proof",
      "mcp__proof__revoke_my_proof",
      "mcp__proof__revoke_asset",
      "mcp__proof__revoke_auth_session",
      "mcp__proof__update_settings",
      "mcp__proof__update_template",
      "mcp__proof__delete_template",
      "mcp__proof__update_webhook_endpoint",
      "mcp__proof__delete_webhook_endpoint",
      "mcp__proof__rotate_webhook_endpoint_secret",
      "mcp__proof__create_sub_account",
      "mcp__proof__create_profile",
      "mcp__proof__update_sub_account",
      "mcp__proof__update_profile",
      "mcp__proof__delete_sub_account",
      "mcp__proof__delete_profile",
      "mcp__proof__set_primary_sub_account",
      "mcp__proof__set_primary_profile",
      "mcp__proof__update_sub_account_page_proofs",
      "mcp__proof__update_profile_proofs",
      "mcp__proof__update_public_page",
      "mcp__proof__update_my_profile",
      "mcp__proof__rotate_callback_secret",
      "mcp__proof__remove_email",
      "mcp__proof__set_email_account_access",
      "mcp__proof__set_primary_email",
      "mcp__proof__remove_phone",
      "mcp__proof__set_phone_account_access",
      "mcp__proof__set_primary_phone",
      "mcp__proof__revoke_api_key",
      "mcp__proof__regenerate_api_key",
      "mcp__proof__delete_domain",
      "mcp__proof__connect_cloudflare",
      "mcp__proof__connect_godaddy",
      "mcp__proof__connect_dns_provider",
      "mcp__proof__add_verification_provider",
      "mcp__proof__create_dns_credential",
      "mcp__proof__delete_dns_credential",
      "mcp__proof__cancel_user_request",
      "mcp__proof__update_public_page_proofs",
      "mcp__proof__update_public_proofs",
      "mcp__proof__revoke_authorization",
      "mcp__proof__update_approval_channel",
      "mcp__proof__update_hitl",
      "mcp__proof__archive_approval_channel",
      "mcp__proof__delete_hitl",
      "mcp__proof__upload_approval_channel_keys",
      "mcp__proof__upload_hitl_keys",
      "mcp__proof__delete_approval_channel_keys",
      "mcp__proof__delete_hitl_keys",
      "mcp__proof__update_circle",
      "mcp__proof__delete_circle",
      "mcp__proof__remove_circle_member",
      "mcp__proof__remove_circle_member_channel",
      "mcp__proof__revoke_delegation",
      "mcp__proof__cancel_lookalike_watch"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as proof. Review it before you use it.

Capability tags behind 44 rules
  • mcp__proof__create_verification outbound
  • mcp__proof__resend_verification outbound
  • mcp__proof__create_multi_channel_verification outbound
  • mcp__proof__create_verification_request outbound
  • mcp__proof__create_session outbound
  • mcp__proof__get_company private-data, untrusted-input
  • mcp__proof__list_templates private-data, untrusted-input
  • mcp__proof__get_default_templates private-data, untrusted-input
  • mcp__proof__get_template private-data, untrusted-input
  • mcp__proof__render_template outbound
  • mcp__proof__list_webhook_endpoints untrusted-input
  • mcp__proof__create_webhook_endpoint outbound
  • mcp__proof__list_emails private-data, untrusted-input
  • mcp__proof__set_email_account_access outbound
  • mcp__proof__set_primary_email outbound
  • mcp__proof__start_add_email outbound
  • mcp__proof__get_add_email_status private-data, untrusted-input
  • mcp__proof__resend_email_otp outbound
  • mcp__proof__preview_email_removal private-data, untrusted-input
  • mcp__proof__start_add_phone outbound
  • mcp__proof__start_2fa outbound
  • mcp__proof__get_dns_providers private-data
  • mcp__proof__verify_domain_with_credentials outbound
  • mcp__proof__start_domain_email_verification outbound
  • mcp__proof__resend_domain_email outbound
  • mcp__proof__check_domain_email_status private-data, untrusted-input
  • mcp__proof__list_dns_credentials private-data
  • mcp__proof__create_user_request outbound
  • mcp__proof__share_request_email outbound
  • mcp__proof__start_user_domain_verification outbound
  • mcp__proof__create_authorization outbound
  • mcp__proof__export_authorizations outbound
  • mcp__proof__resend_confirmation outbound
  • mcp__proof__create_approval_channel outbound
  • mcp__proof__create_hitl outbound
  • mcp__proof__wait_for_chat_id_discovery private-data, untrusted-input
  • mcp__proof__invite_circle_member outbound
  • mcp__proof__add_circle_member_channel outbound
  • mcp__proof__get_delegation_carriers untrusted-input
  • mcp__proof__start_login outbound
  • mcp__proof__create_account outbound
  • mcp__proof__send_account_email outbound
  • mcp__proof__start_2fa_for_action outbound
  • mcp__proof__render_auth_link outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/holdings.proof/mcp-server/verify?hash=c8eb9a3503b30623f122754b3c580c60a359a7e24f5f2d56d2aa4536d1d2c0c7" | jq -e '.changed == false'

Pinned hash c8eb9a3503b3, from Nov 16, 2026, 18:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/holdings.proof/mcp-server/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for holdings.proof/mcp-server
[![Anlyon Radar](https://radar.anlyon.com/badge/holdings.proof/mcp-server.svg)](https://radar.anlyon.com/servers/holdings.proof/mcp-server)

Source: MCP Registry · repository. Synced Nov 16, 2026, 18:17 UTC.

Proof Holdings MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Proof Holdings MCP server safe?

No scan can promise that. What its definitions show: 219 tools, 122 of which can change, send or delete something, and 27 findings (1 high) from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Proof Holdings MCP server delete data?

Yes. 60 tools can delete, cancel or revoke something: delete_domain_verification, cancel_verification_request, revoke_proof, pause_proof, resume_proof, revoke_my_proof and 54 more.

Can the Proof Holdings MCP server do things that cannot be undone?

Yes. 10 tools can send, pay, publish or merge: resend_verification, resend_email_otp, verify_domain_with_credentials, resend_domain_email, create_user_request, create_authorization and 4 more.

What tools does the Proof Holdings MCP server have?

219 tools: 60 destructive, 10 irreversible, 52 write, 97 read. delete_domain_verification, cancel_verification_request, revoke_proof, pause_proof, resume_proof, revoke_my_proof, revoke_asset, revoke_auth_session and 211 more.

Does the Proof Holdings MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Proof Holdings MCP server send data to outside services?

31 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): create_verification, resend_verification, create_multi_channel_verification, create_verification_request, create_session, render_template and 25 more.

Has the Proof Holdings MCP server changed its tools?

Yes, 8 times since Anlyon Radar started tracking it, most recently on Nov 16, 2026. Every change is on this page and in its Atom feed.