Agent Payment Guard MCP server
io.github.dagu3371/agent-payment-guarddagu3371streamable-httpv1.0.0Scanned
Check wallets and tokens before an agent pays or trades: sanctions, honeypots, taxes, reputation.
3 tools: 1 do something that can't be undone and 2 change things.
- Reads private data · 0
- Reads text others write · 2
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- 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 Agent Payment Guard MCP server can do
The Agent Payment Guard MCP server is published by the GitHub account dagu3371. It has 3 tools. It can do things that cannot be undone, such as sending, paying or publishing (check_payment_counterparty) and create or change data (2 tools: check_token and verify_receipt), but cannot delete data. None of its tools only reads.
2 tools bring in text other people can write (check_payment_counterparty and check_token).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 17, 2026, version 1.0.0.
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.
3 tools
Can't be undone 1Claude Code: ask
check_payment_counterpartyCheck a wallet/payTo address before paying it: sanctioned crypto address (OFAC/UK/EU), x402 seller reputation, live Base facts, optional counterparty-name screening, signed receipt…Reads text others write1 finding
Why it is in this group
- The name "check_payment_counterparty" 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 "check_payment_counterparty" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "check_payment_counterparty" says "payment": a word that usually means money moves, which cannot be taken back.
Description, as the server wrote it Check a wallet/payTo address before paying it: sanctioned crypto address (OFAC/UK/EU), x402 seller reputation, live Base facts, optional counterparty-name screening, signed receipt. Verdict block/review/clear. $0.005 per call after the free daily quota.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
Changes things 2Claude Code: ask
check_tokenBefore buying or accepting a token: simulates a buy and sell (Uniswap V2, Base/Ethereum) to detect honeypots and taxes, and checks owner powers (mint/pause/blacklist/fees), upgrade…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 Before buying or accepting a token: simulates a buy and sell (Uniswap V2, Base/Ethereum) to detect honeypots and taxes, and checks owner powers (mint/pause/blacklist/fees), upgradeable proxy, liquidity and sanctioned owner. Verdict avoid/caution/ok with a signed receipt. $0.01 per call after the free daily quota.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: true
verify_receiptFree.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Free. Verify that a receipt (payload_json + signature) was issued by Agent Payment Guard and has not been altered.
Annotations the server declares
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
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 write2
- 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 18, 2026, 16:19 UTC, unchanged since Nov 18, 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
- 3
- 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 3 tools that change things (1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://agent-payment-guard.agent-data-apis.workers.dev/mcp: tools/list returned 3 tools to an anonymous client, including check_payment_counterparty (irreversible), check_token (write), verify_receipt (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "check_payment_counterparty" read-only (readOnlyHint: true), and its own name, description or input give the class "irreversible".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"openWorldHint":true}; The name "check_payment_counterparty" 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 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agent-payment-guard https://agent-payment-guard.agent-data-apis.workers.dev/mcpclaude mcp add --transport http agent-payment-guard https://agent-payment-guard.agent-data-apis.workers.dev/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__agent-payment-guard__check_payment_counterparty",
"mcp__agent-payment-guard__check_token",
"mcp__agent-payment-guard__verify_receipt"
],
"deny": []
}
}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 agent-payment-guard. Review it before you use it.
Capability tags behind 2 rules
- mcp__agent-payment-guard__check_payment_counterparty untrusted-input
- mcp__agent-payment-guard__check_token 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.dagu3371/agent-payment-guard/verify?hash=bb51edc04d99e98edcada6d817f818107ee2531472ea09c40e927b3ce845b3f1" | jq -e '.changed == false'Pinned hash bb51edc04d99, from Nov 17, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.dagu3371/agent-payment-guard/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.dagu3371/agent-payment-guard)Source: MCP Registry. Synced Nov 17, 2026, 18:17 UTC.
Agent Payment Guard MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Agent Payment Guard MCP server safe?
- No scan can promise that. What its definitions show: 3 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Agent Payment Guard MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Agent Payment Guard MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: check_payment_counterparty.
What tools does the Agent Payment Guard MCP server have?
- 3 tools: 1 irreversible, 2 write. check_payment_counterparty, check_token and verify_receipt.
Does the Agent Payment Guard MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Agent Payment Guard MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Agent Payment Guard MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.