Skip to content

seekrit — secrets for agents MCP server

dev.seekrit/remote-mcpseekrit.devstreamable-httpv0.1.0Scanned

Encrypted store for API keys and database URLs your code needs. Use them without reading them.

40 tools: 11 can delete or cancel things, 1 do something that can't be undone, 8 change things and 20 only read.

Tools: 11 delete, 1 irreversible, 8 write, 20 read.

Tools listed without sign-in. Remote posture

With Anlyon

11 tools here can delete or cancel things and 1 does 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 seekrit — secrets for agents MCP server can do

The seekrit — secrets for agents MCP server is published by seekrit.dev, a domain the MCP Registry verified. It has 40 tools. It can delete or cancel things (11 tools: uncompose_group, delete_secret, revoke_token, revoke_invite and 7 more), do things that cannot be undone, such as sending, paying or publishing (invite_member) and create or change data (8 tools: signup, local_tool_for, create_app, create_group and 4 more). 20 tools only read.

12 tools read private data (setup_local_crypto, list_orgs, list_apps and 9 more); 38 tools bring in text other people can write (signup, local_tool_for, whoami and 35 more); 1 tool can send data out of your system (invite_member). 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 50 findings, 1 of them high severity (credentials-mention, tool-shadowing, sensitive-path and annotation-conflict). Each one comes with the text it matched.

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

Last scanned Nov 11, 2026, version 0.1.0.

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.

40 tools

Deletes or cancels 11Claude Code: deny
  • delete_appDelete an application together with all of its environments and their secrets, discarding the ciphertext.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Delete an application together with all of its environments and their secrets, discarding the ciphertext. Irreversible — there is no undo and no export. This is the widest-blast-radius tool here; prefer delete_env for a single environment, or rename_app if the name is the only problem. Confirm intent with a human before calling. Returns { ok, app }.

    Annotations the server declares

    • title: delete_app
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • delete_branchTear down an ephemeral branch config and every value it overrode.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Tear down an ephemeral branch config and every value it overrode. The parent environment is untouched — only the branch's own overrides go — which makes this the routine cleanup when a PR merges. Irreversible; creating a branch mints a data key, so create_branch stays on the local crypto plane. Find the slug with list_branches. Returns { ok, branch }.

    Annotations the server declares

    • title: delete_branch
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • delete_envDelete one application environment and the secrets it owns, discarding the ciphertext.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Delete one application environment and the secrets it owns, discarding the ciphertext. Irreversible, and the environment's data key goes with it — recreating the environment means setting every value again on the local crypto plane. Sibling environments and the application itself are untouched; use delete_app to remove all of them. Confirm intent before calling. Returns { ok, env }.

    Annotations the server declares

    • title: delete_env
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • delete_groupDelete a shared group together with its environments and their secrets, discarding the ciphertext.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Delete a shared group together with its environments and their secrets, discarding the ciphertext. Irreversible. Every application environment that composed this group loses those names — check list_env_groups (or use uncompose_group) before deciding the group is unused. Confirm intent before calling. Returns { ok, group }.

    Annotations the server declares

    • title: delete_group
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • delete_secretDelete a secret from an environment, discarding its ciphertext and every version.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Delete a secret from an environment, discarding its ciphertext and every version. Irreversible — restore_secret CANNOT bring it back (that only rolls back within a surviving secret's history), and re-creating it means setting the value again on the local crypto plane. Prefer restore_secret to undo a bad write. Confirm intent before calling. Returns { ok, name } — or { ok, queued: true, changeRequestId } if the environment requires approval, in which case NOTHING was deleted until a human approves.

    Annotations the server declares

    • title: delete_secret
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • kms_disable_keyDisable a managed KMS key: new encrypt/sign operations are blocked, while data already encrypted under it stays decryptable locally by existing grantees.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Disable a managed KMS key: new encrypt/sign operations are blocked, while data already encrypted under it stays decryptable locally by existing grantees. Reversible only by an operator re-enabling the key — there is no enable tool here. Use kms_revoke_grant instead to cut off ONE principal while the key stays in service. Find the id with kms_list_keys. Returns the updated key, with `disabledAt` now set.

    Annotations the server declares

    • title: kms_disable_key
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • kms_revoke_grantRevoke one principal's grant on a managed KMS key, across all its versions — that user or service token can no longer use the key, while everyone else keeps working.Reads text others write2 findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    • Info

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

      Matched text

      inputSchema.properties.principalType.description: "...mbers) or "service_token" for a machine credential (list_tokens)."

      What this check looks for
    Description, as the server wrote it
    Revoke one principal's grant on a managed KMS key, across all its versions — that user or service token can no longer use the key, while everyone else keeps working. Use kms_disable_key instead to stop the key entirely. Removing a grant needs no key material, which is why it runs here. Returns { ok, keyId, principalId }.

    Annotations the server declares

    • title: kms_revoke_grant
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • revoke_inviteCancel a pending organization invitation before it is accepted.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Cancel a pending organization invitation before it is accepted. Use this for an invite sent in error; once someone has accepted, they are a member and this no longer applies. Find the id with list_invites. Returns { ok, inviteId }.

    Annotations the server declares

    • title: revoke_invite
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • revoke_leaseRevoke a temporary-access lease now instead of waiting for it to expire — the leased database credential is dropped at the target immediately, so anything still holding it fails on…Reads text others write2 findings

    Why it is in this group

    • The name "revoke_lease" says "revoke": a word for removing or ending something.
    • The description says "Irreversible".
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...for it to expire — the leased database credential is dropped at the target immediately, s..."

      What this check looks for
    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Revoke a temporary-access lease now instead of waiting for it to expire — the leased database credential is dropped at the target immediately, so anything still holding it fails on its next connection. Irreversible: a new lease must be minted on the local crypto plane. Check list_leases first, since an already-expired lease needs no revoking. Returns { ok, leaseId }.

    Annotations the server declares

    • title: revoke_lease
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • revoke_tokenRevoke a service token by id.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Revoke a service token by id. Future key fetches by that token stop immediately, so any workload still using it loses access on its next read. If the holder may have cached the key already, also rotate the environment on the local crypto plane — revocation alone does not re-encrypt anything. Find the id with list_tokens. Returns { ok, tokenId }.

    Annotations the server declares

    • title: revoke_token
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: true
    • openWorldHint: true
  • uncompose_groupRemove a composed group from an application environment.Reads text others write2 findings

    Why it is in this group

    • The description's first verb is "remove": a word for removing or ending something.
    • The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    • Warn

      The server marks "uncompose_group" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "remove": a word for removing or ending something.

      What this check looks for
    Description, as the server wrote it
    Remove a composed group from an application environment. The group and its secrets are untouched — only the link is dropped — but the environment stops resolving every name it inherited from that group, which will break a workload still reading one. Check list_env_groups first, and use delete_group to destroy the group itself. Safe to repeat. Returns { ok: true }.

    Annotations the server declares

    • title: uncompose_group
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Can't be undone 1Claude Code: ask
  • invite_memberInvite a human to the organization by email (admin only).Reads text others writeCan send data out1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "invite_member" says "invite": it sends or publishes something to other people.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Invite a human to the organization by email (admin only). They join at the given role once they sign in. Use this to hand a project off to a person — then grant them decryption with `grant_env` on the LOCAL crypto plane, since an invite alone conveys no ability to read values. Returns the pending { id, orgId, email, role, invitedById, createdAt }; revoke_invite cancels it.

    Annotations the server declares

    • title: invite_member
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Changes things 8Claude Code: ask
  • compose_groupCompose a shared group into an application environment, so that environment resolves the group's secrets as well as its own.Reads text others write1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Compose a shared group into an application environment, so that environment resolves the group's secrets as well as its own. Safe to repeat — composing an already-composed group just updates its position. Use uncompose_group to undo, and list_env_groups to see the current order. When app access or sync requires new wrapped keys, use the local CLI to compose the group; this remote tool cannot wrap keys. Returns the composed { groupId, slug, name, position }.

    Annotations the server declares

    • title: compose_group
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • create_appCreate an application — the container that will own environments and secrets.Reads text others write2 findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    • Warn

      The input schema at properties.slug.description contains "every other tool", wording about other tools or servers.

      Matched text

      inputSchema.properties.slug.description: "URL-safe identifier used by every other tool to refer to this app: lowercase letters..."

      What this check looks for
    Description, as the server wrote it
    Create an application — the container that will own environments and secrets. This step needs no key material, so it runs here. Creating its environments does NOT: create_env mints a data key and lives on the local crypto plane (call setup_local_crypto). Returns the new { id, orgId, name, slug, createdAt }.

    Annotations the server declares

    • title: create_app
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • create_groupCreate a shared group — a reusable bag of secrets (a shared datastore, a vendor account) that many application environments compose in rather than each keeping a copy.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Create a shared group — a reusable bag of secrets (a shared datastore, a vendor account) that many application environments compose in rather than each keeping a copy. Use create_app instead for a deployable service. No key material involved, so it runs here; the group's environments are minted locally by create_group_env. Returns the new { id, orgId, name, slug, createdAt }.

    Annotations the server declares

    • title: create_group
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • local_tool_forLook up how to perform one crypto-plane operation locally — the targeted answer for "the tool I expected is not on this server".Reads text others writeNo 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

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Look up how to perform one crypto-plane operation locally — the targeted answer for "the tool I expected is not on this server". Returns { operation, where, how } for a known operation, or a note explaining the plane boundary for an unrecognised one. Use setup_local_crypto instead when you need the whole local setup rather than one command.

    Annotations the server declares

    • title: local_tool_for
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • rename_appChange an application's display name.Reads text others write2 findings

    Why it is in this group

    • The name "rename_app" says "rename": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    • Warn

      The description contains "every other tool", wording about other tools or servers.

      Matched text

      description: "...s display name. The slug is immutable — every other tool refers to the app by slug, so a rename..."

      What this check looks for
    Description, as the server wrote it
    Change an application's display name. The slug is immutable — every other tool refers to the app by slug, so a rename breaks nothing. Use delete_app + create_app only if the slug itself must change. Returns the updated { id, orgId, name, slug, createdAt }.

    Annotations the server declares

    • title: rename_app
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • rename_groupChange a shared group's display name.Reads text others write1 finding

    Why it is in this group

    • The name "rename_group" says "rename": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Change a shared group's display name. The slug is immutable — references from composed environments are by slug, so a rename breaks nothing. Returns the updated { id, orgId, name, slug, createdAt }.

    Annotations the server declares

    • title: rename_group
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • restore_secretRoll a secret back to an earlier version — the undo for a bad write.Reads text others write1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Roll a secret back to an earlier version — the undo for a bad write. The stored ciphertext is replayed as a NEW version, so history is append-only and nothing is overwritten. Read list_secret_versions first to choose the version. No decryption happens, which is why this works here and not only on the local crypto plane. Returns { ok, name, restoredFrom, version } where `version` is the new head.

    Annotations the server declares

    • title: restore_secret
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • signupCreate a seekrit workspace and your own machine credential — one call, no human, no browser.Reads text others write3 findings

    Why it is in this group

    • The description's first verb is "create": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...seekrit workspace and your own machine credential — one call, no human, no browser. Binds..."

      What this check looks for
    • Info

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

      Matched text

      inputSchema.properties.clientName.description: "Optional label for this machine credential (defaults to <slug>-agent)."

      What this check looks for
    • Warn

      The description contains "every other tool", wording about other tools or servers.

      Matched text

      description: "...inds the credential to this session, so every other tool works on your next call with no config..."

      What this check looks for
    Description, as the server wrote it
    Create a seekrit workspace and your own machine credential — one call, no human, no browser. Binds the credential to this session, so every other tool works on your next call with no config change and no reconnect. Returns { org, credential: { clientId, clientSecret }, sessionBound, next }. Save the clientId + clientSecret: the secret is shown once, is not retrievable, and is how you reconnect later. Call this if a tool says you have no credential.

    Annotations the server declares

    • title: signup
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 20Show 20 read-only tools
  • auditRead the organization's append-only audit trail, most recent first — every mutation across apps, environments, secrets, members, and tokens.Reads private dataReads text others write1 finding

    Why it is in this group

    • The description's first verb is "read": a word for reading.

    What it can reach

    • private-dataThe description's first sentence says "read" and "secret": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Read the organization's append-only audit trail, most recent first — every mutation across apps, environments, secrets, members, and tokens. Use it to answer "what changed and who did it"; for one secret's history specifically, list_secret_versions is narrower and cheaper. Returns [{ id, action, actorType, actorId, resourceType, resourceId, metadata, ipAddress, createdAt }].

    Annotations the server declares

    • title: audit
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • billingShow the org's plan, effective entitlements, current usage, and which upgrade actions are available.Reads text others write1 finding

    Why it is in this group

    • The description's first verb is "show": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    Show the org's plan, effective entitlements, current usage, and which upgrade actions are available. Read this if a create action was refused with a plan limit — it names the limit you hit and how to lift it. Returns { plan, subscription, promo, entitlements, usage, overrides, enforced, manage } — `enforced: false` means plan limits are not currently applied, and `manage` carries the upgrade paths.

    Annotations the server declares

    • title: billing
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • get_startedRead the recommended first-project recipe end to end: which steps run here and which need the local crypto plane.No findings

    Why it is in this group

    • The name "get_started" says "get": a word for reading.
    Description, as the server wrote it
    Read the recommended first-project recipe end to end: which steps run here and which need the local crypto plane. Takes no arguments and returns a prose walkthrough. Call this before provisioning anything — it is cheaper than discovering the plane boundary one failed tool at a time.

    Annotations the server declares

    • title: get_started
    • readOnlyHint: true
    • openWorldHint: false
  • kms_list_keysList the managed KMS keys the caller can see — symmetric and signing keys seekrit stores wrapped, for encrypting data outside the secret store.Reads private dataReads text others write1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "secret": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List the managed KMS keys the caller can see — symmetric and signing keys seekrit stores wrapped, for encrypting data outside the secret store. Metadata only: key material is fetched and used on the local crypto plane (kms_encrypt / kms_decrypt / kms_sign live there, not here). Use it to find a `keyId` for kms_disable_key or kms_revoke_grant. Returns [{ id, name, purpose, spec, currentVersion, applicationId, groupId, disabledAt, createdAt }] — a non-null `disabledAt` means the key is already disabled.

    Annotations the server declares

    • title: kms_list_keys
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_appsList the applications in an organization — an application is the top-level container that owns environments, which in turn own secrets.Reads private dataReads text others write1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "secret": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List the applications in an organization — an application is the top-level container that owns environments, which in turn own secrets. Start here when you know the org but not the app slug the other tools need. Returns [{ id, orgId, name, slug, createdAt }]; use list_envs next to descend into one.

    Annotations the server declares

    • title: list_apps
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_branchesList ephemeral branch configs (per-PR / preview environments) across an application, or just those forked from one environment.Reads private dataReads text others write1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe name "list_branches" says "list" and "branch": it reads repositories.
    • private-dataThe description's first sentence says "list" and "branch": it reads repositories.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List ephemeral branch configs (per-PR / preview environments) across an application, or just those forked from one environment. Names, parents, and expiry only — never values. Use it before delete_branch to find a branch slug, or to spot branches that have already expired. Returns Environment rows with `parentEnvironmentId` set: [{ id, name, slug, parentEnvironmentId, expiresAt, createdAt }] — `expiresAt` is null for a branch with no TTL.

    Annotations the server declares

    • title: list_branches
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_env_groupsList the shared groups composed INTO one application environment, in precedence order (higher position wins a name clash).Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List the shared groups composed INTO one application environment, in precedence order (higher position wins a name clash). Read this to explain where a secret name actually comes from, or to pick the next `position` for compose_group. The inverse direction of list_group_envs. Returns [{ groupId, slug, name, position }], highest position last.

    Annotations the server declares

    • title: list_env_groups
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_envsList the environments an application owns (production, staging, …).Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List the environments an application owns (production, staging, …). Names and slugs only — never values. Use this to find the `env` slug that list_secrets and the delete/restore tools take. Returns [{ id, name, slug, applicationId, groupId, parentEnvironmentId, expiresAt, createdAt }]. Not to be confused with list_env_groups (which groups feed INTO an app environment) or list_group_envs (the environments of a shared GROUP).

    Annotations the server declares

    • title: list_envs
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_group_envsList the environments belonging to one shared GROUP — a group holds a separate value set per slug, so its `production` differs from its `staging`.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List the environments belonging to one shared GROUP — a group holds a separate value set per slug, so its `production` differs from its `staging`. Use this when you already have a group and want its own environments; use list_envs for an application's, and list_env_groups to see which groups an application environment pulls from. Returns Environment rows with `groupId` set: [{ id, name, slug, groupId, createdAt }].

    Annotations the server declares

    • title: list_group_envs
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_groupsList the shared groups in an organization — a group is a reusable bag of secrets (a shared datastore, a vendor account) that many application environments can compose in rather tha…Reads private dataReads text others write1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "secret": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List the shared groups in an organization — a group is a reusable bag of secrets (a shared datastore, a vendor account) that many application environments can compose in rather than duplicating. Use it to find the `group` slug compose_group and list_group_envs take. Returns [{ id, orgId, name, slug, createdAt }]; not paginated.

    Annotations the server declares

    • title: list_groups
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_invitesList invitations to the organization that have been sent but not yet accepted.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List invitations to the organization that have been sent but not yet accepted. Use it to confirm an invite_member call landed, or to find an `inviteId` for revoke_invite. Accepted invitations become members — see list_members. Returns [{ id, orgId, email, role, invitedById, createdAt }].

    Annotations the server declares

    • title: list_invites
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_lease_targetsList the registered temporary-access targets — the databases (Postgres, MySQL, …) against which short-lived credentials can be minted on demand instead of storing a standing passwo…Reads private dataReads text others write2 findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "database": it reads databases.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...es, MySQL, …) against which short-lived credentials can be minted on demand instead of stor..."

      What this check looks for
    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List the registered temporary-access targets — the databases (Postgres, MySQL, …) against which short-lived credentials can be minted on demand instead of storing a standing password. Use it to see what can be leased before minting one (create_pg_lease / create_mysql_lease run on the LOCAL crypto plane), and see list_leases for what has actually been issued. Returns [{ id, orgId, provider, name, config, createdAt }], where `provider` names the kind of target (postgres, mysql, …) and `config` is non-secret connection settings.

    Annotations the server declares

    • title: list_lease_targets
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_leasesList temporary-access leases that have been issued — the ledger of who got a short-lived credential against which target and until when.Reads private dataReads text others write2 findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "credential": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...d — the ledger of who got a short-lived credential against which target and until when. Ne..."

      What this check looks for
    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List temporary-access leases that have been issued — the ledger of who got a short-lived credential against which target and until when. Never includes the credential itself. Use it to find a `leaseId` for revoke_lease, or to check whether a lease has already expired before revoking it; list_lease_targets shows what CAN be leased. Returns [{ id, targetId, provider, status, principalType, principalId, expiresAt, endedAt, endedReason, createdAt }] — only `status: "active"` leases are worth revoking.

    Annotations the server declares

    • title: list_leases
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_membersList organization members with their public keys.Reads text others write1 finding

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List organization members with their public keys. The public keys are what you pass to `grant_env` on the LOCAL crypto plane to give a human the ability to decrypt — so call this when handing a project off to a person. Returns [{ userId, email, name, role, publicKeyJwk }]; `publicKeyJwk` is null for a member who has not finished key setup, and such a member cannot be granted decryption yet.

    Annotations the server declares

    • title: list_members
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_orgsList the organizations this credential can access.Reads private dataReads text others write2 findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "credential": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "List the organizations this credential can access. Use it to find the `org` sl..."

      What this check looks for
    • Warn

      The description contains "every other tool", wording about other tools or servers.

      Matched text

      description: "...n access. Use it to find the `org` slug every other tool takes; prefer whoami if you also want t..."

      What this check looks for
    Description, as the server wrote it
    List the organizations this credential can access. Use it to find the `org` slug every other tool takes; prefer whoami if you also want to confirm which client you are. Returns [{ id, name, slug, role, createdAt }].

    Annotations the server declares

    • title: list_orgs
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_secret_versionsList one secret's version history: who wrote each version, when, and which ones were restores.Reads private dataReads text others write1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe name "list_secret_versions" says "list" and "secret": it reads secrets.
    • private-dataThe description's first sentence says "list" and "secret": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List one secret's version history: who wrote each version, when, and which ones were restores. Metadata only — never values. Pair with restore_secret to undo a bad write: read the history here, then pass the version number you want back. Returns { currentVersion, versions: [{ version, createdAt, createdBy, restoredFromVersion }] }, newest first.

    Annotations the server declares

    • title: list_secret_versions
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_secretsList the secret NAMES and versions in an environment.Reads private dataReads text others write1 finding

    Why it is in this group

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

    What it can reach

    • private-dataThe name "list_secrets" says "list" and "secret": it reads secrets.
    • private-dataThe description's first sentence says "list" and "secret": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List the secret NAMES and versions in an environment. NEVER returns values: this server cannot decrypt. Use it to discover which names exist before referencing them; to read a value, run the local crypto plane (see setup_local_crypto) — no tool here will ever return one. Returns [{ name, version, updatedAt }].

    Annotations the server declares

    • title: list_secrets
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • list_tokensList an organization's service tokens — the long-lived credentials that let a deployed workload fetch secrets.Reads private dataReads text others write2 findings

    Why it is in this group

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

    What it can reach

    • private-dataThe description's first sentence says "list" and "credential": it reads secrets.
    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...ation's service tokens — the long-lived credentials that let a deployed workload fetch secr..."

      What this check looks for
    • Info

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

      Matched text

      inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

      What this check looks for
    Description, as the server wrote it
    List an organization's service tokens — the long-lived credentials that let a deployed workload fetch secrets. Metadata only: the token strings are shown once at creation (on the local crypto plane) and are never retrievable here. Use it to find a `tokenId` for revoke_token, or to audit what still has access. Returns [{ id, name, role, environmentId, expiresAt, lastUsedAt, revokedAt, createdAt }] — `environmentId` is null for an org-admin token, and a non-null `revokedAt` means it is already revoked.

    Annotations the server declares

    • title: list_tokens
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • setup_local_cryptoGet the exact commands for running the local crypto plane (the `@seekrit/mcp` npm server, the `@seekrit/cli` CLI, seekrit-run, seekrit-proxy), including a copy-paste .mcp.json that…Reads private data2 findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.

    What it can reach

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

    Findings

    • High

      The description refers to ".mcp.json".

      Matched text

      description: "...seekrit-proxy), including a copy-paste .mcp.json that reuses this session's credential...."

      What this check looks for
    • Info

      The description mentions "credential".

      Matched text

      description: "...te .mcp.json that reuses this session's credential. Takes no arguments and returns prose p..."

      What this check looks for
    Description, as the server wrote it
    Get the exact commands for running the local crypto plane (the `@seekrit/mcp` npm server, the `@seekrit/cli` CLI, seekrit-run, seekrit-proxy), including a copy-paste .mcp.json that reuses this session's credential. Takes no arguments and returns prose plus config. Call this the moment you need to SET or READ a secret value — no tool on this server will ever return one. Use local_tool_for instead when you want the single command for one named operation.

    Annotations the server declares

    • title: setup_local_crypto
    • readOnlyHint: true
    • openWorldHint: false
  • whoamiShow the authenticated machine client and the org it can access.Reads text others write1 finding

    Why it is in this group

    • The name "whoami" says "whoami": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...ccess. Call this first: it confirms the credential works and tells you which org slug to p..."

      What this check looks for
    Description, as the server wrote it
    Show the authenticated machine client and the org it can access. Call this first: it confirms the credential works and tells you which org slug to pass (or that you can omit `org` entirely). Returns { kind, clientId, orgs: [{ id, name, slug, role, createdAt }] }.

    Annotations the server declares

    • title: whoami
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: 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.

456 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads text others write38
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__remote__invite_member"
    ]
  }
}

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, 18:52 UTC, unchanged since Oct 22, 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
20
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 20 tools that change things (11 destructive, 1 irreversible, 8 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.seekrit.dev/mcp: tools/list returned 40 tools to an anonymous client, including uncompose_group (destructive), delete_secret (destructive), revoke_token (destructive), revoke_invite (destructive), revoke_lease (destructive) and 15 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 high5 warn44 info
  • The description refers to ".mcp.json".

    Matched text

    description: "...seekrit-proxy), including a copy-paste .mcp.json that reuses this session's credential...."

    What this check looks for
  • Warnsignup

    The description contains "every other tool", wording about other tools or servers.

    Matched text

    description: "...inds the credential to this session, so every other tool works on your next call with no config..."

    What this check looks for
  • The description contains "every other tool", wording about other tools or servers.

    Matched text

    description: "...n access. Use it to find the `org` slug every other tool takes; prefer whoami if you also want t..."

    What this check looks for
  • The input schema at properties.slug.description contains "every other tool", wording about other tools or servers.

    Matched text

    inputSchema.properties.slug.description: "URL-safe identifier used by every other tool to refer to this app: lowercase letters..."

    What this check looks for
  • The server marks "uncompose_group" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The description's first verb is "remove": a word for removing or ending something.

    What this check looks for
  • The description contains "every other tool", wording about other tools or servers.

    Matched text

    description: "...s display name. The slug is immutable — every other tool refers to the app by slug, so a rename..."

    What this check looks for
Show 44 more findings
  • Infosignup

    The description mentions "credential".

    Matched text

    description: "...seekrit workspace and your own machine credential — one call, no human, no browser. Binds..."

    What this check looks for
  • Infosignup

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

    Matched text

    inputSchema.properties.clientName.description: "Optional label for this machine credential (defaults to <slug>-agent)."

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "...te .mcp.json that reuses this session's credential. Takes no arguments and returns prose p..."

    What this check looks for
  • Infowhoami

    The description mentions "credential".

    Matched text

    description: "...ccess. Call this first: it confirms the credential works and tells you which org slug to p..."

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "List the organizations this credential can access. Use it to find the `org` sl..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...ation's service tokens — the long-lived credentials that let a deployed workload fetch secr..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The description mentions "credentials".

    Matched text

    description: "...es, MySQL, …) against which short-lived credentials can be minted on demand instead of stor..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "...d — the ledger of who got a short-lived credential against which target and until when. Ne..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • Infoaudit

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

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The description mentions "credential".

    Matched text

    description: "...for it to expire — the leased database credential is dropped at the target immediately, s..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.principalType.description mentions "credential".

    Matched text

    inputSchema.properties.principalType.description: "...mbers) or "service_token" for a machine credential (list_tokens)."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for
  • The input schema at properties.org.description mentions "credential".

    Matched text

    inputSchema.properties.org.description: "...ganization slug or id. Omit it when the credential can reach exactly one org — that org is..."

    What this check looks for

History

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

  1. Tools1 changed.~1 changedView diff

Install

Pinned to version 0.1.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http remote https://mcp.seekrit.dev/mcp
claude mcp add --transport http remote https://mcp.seekrit.dev/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__remote__get_started",
      "mcp__remote__setup_local_crypto",
      "mcp__remote__whoami",
      "mcp__remote__list_orgs",
      "mcp__remote__list_apps",
      "mcp__remote__list_envs",
      "mcp__remote__list_branches",
      "mcp__remote__list_groups",
      "mcp__remote__list_group_envs",
      "mcp__remote__list_env_groups",
      "mcp__remote__list_members",
      "mcp__remote__list_secrets",
      "mcp__remote__list_secret_versions",
      "mcp__remote__list_tokens",
      "mcp__remote__list_invites",
      "mcp__remote__kms_list_keys",
      "mcp__remote__list_lease_targets",
      "mcp__remote__list_leases",
      "mcp__remote__audit",
      "mcp__remote__billing"
    ],
    "ask": [
      "mcp__remote__signup",
      "mcp__remote__local_tool_for",
      "mcp__remote__create_app",
      "mcp__remote__create_group",
      "mcp__remote__compose_group",
      "mcp__remote__invite_member",
      "mcp__remote__rename_app",
      "mcp__remote__rename_group",
      "mcp__remote__restore_secret"
    ],
    "deny": [
      "mcp__remote__uncompose_group",
      "mcp__remote__delete_secret",
      "mcp__remote__revoke_token",
      "mcp__remote__revoke_invite",
      "mcp__remote__revoke_lease",
      "mcp__remote__kms_disable_key",
      "mcp__remote__kms_revoke_grant",
      "mcp__remote__delete_app",
      "mcp__remote__delete_group",
      "mcp__remote__delete_env",
      "mcp__remote__delete_branch"
    ]
  }
}

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 remote. Review it before you use it.

Capability tags behind 39 rules
  • mcp__remote__signup untrusted-input
  • mcp__remote__setup_local_crypto private-data
  • mcp__remote__local_tool_for untrusted-input
  • mcp__remote__whoami untrusted-input
  • mcp__remote__list_orgs private-data, untrusted-input
  • mcp__remote__list_apps private-data, untrusted-input
  • mcp__remote__list_envs untrusted-input
  • mcp__remote__list_branches private-data, untrusted-input
  • mcp__remote__list_groups private-data, untrusted-input
  • mcp__remote__list_group_envs untrusted-input
  • mcp__remote__list_env_groups untrusted-input
  • mcp__remote__list_members untrusted-input
  • mcp__remote__list_secrets private-data, untrusted-input
  • mcp__remote__list_secret_versions private-data, untrusted-input
  • mcp__remote__list_tokens private-data, untrusted-input
  • mcp__remote__list_invites untrusted-input
  • mcp__remote__kms_list_keys private-data, untrusted-input
  • mcp__remote__list_lease_targets private-data, untrusted-input
  • mcp__remote__list_leases private-data, untrusted-input
  • mcp__remote__audit private-data, untrusted-input
  • mcp__remote__billing untrusted-input
  • mcp__remote__create_app untrusted-input
  • mcp__remote__create_group untrusted-input
  • mcp__remote__compose_group untrusted-input
  • mcp__remote__uncompose_group untrusted-input
  • mcp__remote__invite_member untrusted-input, outbound
  • mcp__remote__rename_app untrusted-input
  • mcp__remote__rename_group untrusted-input
  • mcp__remote__restore_secret untrusted-input
  • mcp__remote__delete_secret untrusted-input
  • mcp__remote__revoke_token untrusted-input
  • mcp__remote__revoke_invite untrusted-input
  • mcp__remote__revoke_lease untrusted-input
  • mcp__remote__kms_disable_key untrusted-input
  • mcp__remote__kms_revoke_grant untrusted-input
  • mcp__remote__delete_app untrusted-input
  • mcp__remote__delete_group untrusted-input
  • mcp__remote__delete_env untrusted-input
  • mcp__remote__delete_branch untrusted-input

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/dev.seekrit/remote-mcp/verify?hash=0cc8f0adbf60ba18099900adc9cd21be694d061b67a10b91041961117d0550d8" | jq -e '.changed == false'

Pinned hash 0cc8f0adbf60, from Nov 11, 2026, 10:17 UTC.

Watch

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

https://radar.anlyon.com/servers/dev.seekrit/remote-mcp/changes.xml

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

Badge

Anlyon Radar badge for dev.seekrit/remote-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/dev.seekrit/remote-mcp.svg)](https://radar.anlyon.com/servers/dev.seekrit/remote-mcp)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:12 UTC.

seekrit — secrets for agents MCP server: questions and answers

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

Is the seekrit — secrets for agents MCP server safe?

No scan can promise that. What its definitions show: 40 tools, 20 of which can change, send or delete something, and 50 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 seekrit — secrets for agents MCP server delete data?

Yes. 11 tools can delete, cancel or revoke something: uncompose_group, delete_secret, revoke_token, revoke_invite, revoke_lease, kms_disable_key and 5 more.

Can the seekrit — secrets for agents MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: invite_member.

What tools does the seekrit — secrets for agents MCP server have?

40 tools: 11 destructive, 1 irreversible, 8 write, 20 read. uncompose_group, delete_secret, revoke_token, revoke_invite, revoke_lease, kms_disable_key, kms_revoke_grant, delete_app and 32 more.

Does the seekrit — secrets for agents MCP server need sign-in or OAuth?

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

Does the seekrit — secrets for agents MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): invite_member.

Has the seekrit — secrets for agents MCP server changed its tools?

Yes, once since Anlyon Radar started tracking it, most recently on Oct 29, 2026. Every change is on this page and in its Atom feed.