PHANTOM ID — agent payments (USDC on Base) MCP server
io.github.Arbromagency-Sato/phantom-mcp-serverArbromagency-Satostreamable-httpv0.3.2Scanned
PHANTOM ID MCP payment server: agent-to-agent USDC payments on Base.
7 tools: 1 can delete or cancel things, 3 do something that can't be undone and 3 change things.
- Reads private data · 0
- Reads text others write · 7
- Can send data out · 0
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 3 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.
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 PHANTOM ID — agent payments (USDC on Base) MCP server can do
The PHANTOM ID — agent payments (USDC on Base) MCP server is published by the GitHub account Arbromagency-Sato. It has 7 tools. It can delete or cancel things (1 tool: submit_payment), do things that cannot be undone, such as sending, paying or publishing (quote_payment, authorize_payment and verify_payment) and create or change data (3 tools: phantom_register, phantom_authorize_budget and phantom_bind_identity). None of its tools only reads.
7 tools bring in text other people can write (phantom_register, phantom_authorize_budget, phantom_bind_identity and 4 more).
The fixed checks matched 2 findings (base64-blob and annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 8, 2026, version 0.3.2.
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.
7 tools
Deletes or cancels 1Claude Code: deny
submit_paymentBroadcast an authorized payment intent through IDPHANTOM.Reads text others writeNo findings
Why it is in this group
- The name "submit_payment" says "submit": a word for a change.
- The name "submit_payment" also says "payment": a word that usually means money moves, which cannot be taken back.
- 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.
Description, as the server wrote it Broadcast an authorized payment intent through IDPHANTOM. The platform relays the on-chain transaction; exactly one broadcast per intent is enforced server-side (retries return the already-submitted transaction hash). This is the step that settles funds.
Annotations the server declares
- title: Submit a payment
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: true
Can't be undone 3Claude Code: ask
authorize_paymentAttach the payer's EIP-712 PaymentAuthorization signature to a quoted payment intent.Reads text others writeNo findings
Why it is in this group
- The name "authorize_payment" says "payment": a word that usually means money moves, which cannot be taken back.
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 Attach the payer's EIP-712 PaymentAuthorization signature to a quoted payment intent. The signature is produced locally by the payer's wallet; it authorizes up to maximumTotalAuthorized, expiring at expiresAt. No funds move until submit_payment.
Annotations the server declares
- title: Authorize a payment
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
quote_paymentCreate an IDPHANTOM payment quote with transparent platform fee (0.5%, min $0.01 USDC).Reads text others write1 finding
Why it is in this group
- The name "quote_payment" says "payment": a word that usually means money moves, which cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The input schema at properties.asset_contract.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.asset_contract.description: "...e.g. USDC on Base: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913."
Description, as the server wrote it Create an IDPHANTOM payment quote with transparent platform fee (0.5%, min $0.01 USDC). Returns a payment intent ready for the payer's EIP-712 signature. Free: quoting never moves funds.
Annotations the server declares
- title: Quote a payment
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
verify_paymentVerify an IDPHANTOM payment receipt: cryptographic checks (EIP-712 signature, payer recovery), expiry, and the on-chain state of the authorization (free/used/cancelled).Reads text others write1 finding
Why it is in this group
- The name "verify_payment" says "payment": a word that usually means money moves, which cannot be taken back.
- 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.
Findings
- Warn
The server marks "verify_payment" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "verify_payment" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Verify an IDPHANTOM payment receipt: cryptographic checks (EIP-712 signature, payer recovery), expiry, and the on-chain state of the authorization (free/used/cancelled). Free for receipts of payments the caller participated in; paid via the receipt-verifier for third-party receipts.
Annotations the server declares
- title: Verify a payment receipt
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 3Claude Code: ask
phantom_authorize_budgetFunder-signed EIP-712 AgentWalletAuthorization: lets an account spend up to max_units of USDC (6-decimal units, e.g.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.
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 Funder-signed EIP-712 AgentWalletAuthorization: lets an account spend up to max_units of USDC (6-decimal units, e.g. '1000000' = $1) with an optional daily cap, without giving away the wallet. Requires PHANTOM_FUNDER_PRIVATE_KEY in the environment; the signature is produced locally. Policy templates: 'micro' ($1/tx, $5/day, 30d) and 'subscriptions' ($2/tx, $5/day, 30d) — pilot caps kept deliberately low; explicit max_units/daily_cap_units/expires_in_days override any template. The account's own api_key is sent as authentication (first binding requires it).
Annotations the server declares
- title: Authorize a spending budget for an account
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
phantom_bind_identityRegisters an agent_id as a portable identity for this account via POST /v1/identity/bind.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.
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 Registers an agent_id as a portable identity for this account via POST /v1/identity/bind. The proof-of-possession is an EIP-712 IdentityBinding signature produced LOCALLY with PHANTOM_IDENTITY_PRIVATE_KEY (environment variable only, never a command-line flag — AGP-057); the private key never leaves this process, only the signature is sent. Idempotent: replaying the same bind returns the existing binding. attestation_address comes from GET /.well-known/phantom-identity.json of the PHANTOM deployment (field attestation_address) — pass it here together with the chain_id so the local signature domain matches the server's. Key rotation is NOT exposed here (it needs the old AND new keys); call POST /v1/identity/rotate directly instead.
Annotations the server declares
- title: Bind a portable agent identity (AGP-123)
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
phantom_registerOne-line onboarding: creates an IDPHANTOM account for the configured payer wallet, pays the $2 USDC registration with a locally-signed EIP-712 authorization and returns the api_key…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.
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 One-line onboarding: creates an IDPHANTOM account for the configured payer wallet, pays the $2 USDC registration with a locally-signed EIP-712 authorization and returns the api_key. Requires PHANTOM_PAYER_PRIVATE_KEY and PHANTOM_ROUTER_ADDRESS in the environment. The api_key is shown exactly ONCE in this response — store it as PHANTOM_API_KEY immediately. Without a payer key configured, pass payer_wallet to get manual instructions instead.
Annotations the server declares
- title: Register an IDPHANTOM account (self-serve)
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- 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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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.
Looked at Nov 16, 2026, 14:21 UTC, unchanged since Nov 9, 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
- 7
- 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 7 tools that change things (1 destructive, 3 irreversible, 3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://pay.idphantom.com/mcp: tools/list returned 7 tools to an anonymous client, including submit_payment (destructive), quote_payment (irreversible), authorize_payment (irreversible), verify_payment (irreversible), phantom_register (write) and 2 more
Findings
Matches of fixed checks, with the text they matched.
- Warnquote_payment
The input schema at properties.asset_contract.description contains a 42-character base64 string.
What this check looks forMatched text
inputSchema.properties.asset_contract.description: "...e.g. USDC on Base: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913."
- Warnverify_payment
The server marks "verify_payment" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "verify_payment" says "payment": a word that usually means money moves, which cannot be taken back.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.3.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http phantom https://pay.idphantom.com/mcpclaude mcp add --transport http phantom https://pay.idphantom.com/mcpRun 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.
{
"permissions": {
"allow": [],
"ask": [
"mcp__phantom__phantom_register",
"mcp__phantom__phantom_authorize_budget",
"mcp__phantom__phantom_bind_identity",
"mcp__phantom__quote_payment",
"mcp__phantom__authorize_payment",
"mcp__phantom__verify_payment"
],
"deny": [
"mcp__phantom__submit_payment"
]
}
}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 phantom. Review it before you use it.
Capability tags behind 7 rules
- mcp__phantom__phantom_register untrusted-input
- mcp__phantom__phantom_authorize_budget untrusted-input
- mcp__phantom__phantom_bind_identity untrusted-input
- mcp__phantom__quote_payment untrusted-input
- mcp__phantom__authorize_payment untrusted-input
- mcp__phantom__submit_payment untrusted-input
- mcp__phantom__verify_payment 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/io.github.Arbromagency-Sato/phantom-mcp-server/verify?hash=6ec5347140780cf9a1e7fcb97688399d5c9cf5b21b9f0ac0568587523c9e0407" | jq -e '.changed == false'Pinned hash 6ec534714078, from Nov 8, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Arbromagency-Sato/phantom-mcp-server/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Arbromagency-Sato/phantom-mcp-server)Source: MCP Registry · repository. Synced Nov 8, 2026, 20:18 UTC.
PHANTOM ID — agent payments (USDC on Base) MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the PHANTOM ID — agent payments (USDC on Base) MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 7 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the PHANTOM ID — agent payments (USDC on Base) MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: submit_payment.
Can the PHANTOM ID — agent payments (USDC on Base) MCP server do things that cannot be undone?
- Yes. 3 tools can send, pay, publish or merge: quote_payment, authorize_payment and verify_payment.
What tools does the PHANTOM ID — agent payments (USDC on Base) MCP server have?
- 7 tools: 1 destructive, 3 irreversible, 3 write. submit_payment, quote_payment, authorize_payment, verify_payment, phantom_register, phantom_authorize_budget and phantom_bind_identity.
Does the PHANTOM ID — agent payments (USDC on Base) MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the PHANTOM ID — agent payments (USDC on Base) MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the PHANTOM ID — agent payments (USDC on Base) MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 8, 2026.