Skip to content

Agent402.Tools: payments and trust for AI agents MCP server

io.github.MikeyPetrillo/agent402MikeyPetrillostreamable-httpv0.14.1Scanned

Payment and trust layer for agent commerce (Agentic Finance): pay and verify calls over x402 and MPP

16 tools: 2 can delete or cancel things, 1 do something that can't be undone, 10 change things and 3 only read.

Tools: 2 delete, 1 irreversible, 10 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 11
  • Can send data out · 2
  • 3 findings

Tools listed without sign-in. Remote posture

With Anlyon

2 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 Agent402.Tools: payments and trust for AI agents MCP server can do

The Agent402.Tools: payments and trust for AI agents MCP server is published by the GitHub account MikeyPetrillo. It has 16 tools. It can delete or cancel things (2 tools: catalog.call and memory.write), do things that cannot be undone, such as sending, paying or publishing (payment.info) and create or change data (10 tools: web.search, web.answer, web.news, browser.render and 6 more). 3 tools only read.

11 tools bring in text other people can write (catalog.call, web.search, web.answer and 8 more); 2 tools can send data out of your system (browser.render and audio.transcribe).

The fixed checks matched 3 findings (annotation-conflict). Each one comes with the text it matched.

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

Last scanned Nov 21, 2026, version 0.14.1.

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.

16 tools

Deletes or cancels 2Claude Code: deny
  • catalog.callRun an Agent402 tool by slug, with params matching that tool's inputSchema; find slugs with catalog.find or catalog.search.Reads text others writeNo findings

    Why it is in this group

    • The name "catalog.call" says "call": 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.
    Description, as the server wrote it
    Run an Agent402 tool by slug, with params matching that tool's inputSchema; find slugs with catalog.find or catalog.search. The 177 pure-CPU tools run free here, rate-limited, through proof-of-work. Paid tools are payable here, in the call, over x402 or MPP (the first answer carries the ask). An unknown slug returns an error.

    Annotations the server declares

    • title: Run an Agent402 tool
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
  • memory.writePaid ($0.001/call): Persistent key-value memory for agents, scoped to the paying wallet.No findings

    Why it is in this group

    • The name "memory.write" says "write": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Paid ($0.001/call): Persistent key-value memory for agents, scoped to the paying wallet. Your x402 payment IS your authentication: the wallet that pays owns the namespace. No signup, no API keys. Exact-key storage for structured state. For retrieval by MEANING rather than key, use the catalog slugs memory-remember and memory-recall (on MCP, through catalog.call with that slug).

    Annotations the server declares

    • title: Memory write
    • readOnlyHint: false
    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: false
Can't be undone 1Claude Code: ask
  • payment.infoHow paying for Agent402 tools works.1 finding

    Why it is in this group

    • The name "payment.info" 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.

    Findings

    • Warn

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

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "payment.info" says "payment": a word that usually means money moves, which cannot be taken back.

      What this check looks for
    Description, as the server wrote it
    How paying for Agent402 tools works. This connector holds no wallet: 177 pure-CPU tools run free through proof-of-work, and the rest settle in USDC over x402 or MPP (payable here, in the call, over x402 or MPP). Covers wallet setup, per-call and session spend caps, the payment rails, and checking a wallet's balance. Returns { connector, freeTier, pay, spendControls, balanceAndHistory }.

    Annotations the server declares

    • title: Payment and wallet setup
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Changes things 10Claude Code: ask
  • audio.transcribePaid ($0.030/call): Transcribe audio to text with the gpt-transcribe model.Reads text others writeCan send data outNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Paid ($0.030/call): Transcribe audio to text with the gpt-transcribe model. Provide a URL to an audio file (mp3, wav, m4a, etc.) and get back the transcript. Add diarize:true for speaker labels, word timestamps and a language confidence score (the scribe-v2 model, same price). No API key needed; pay per call via x402.

    Annotations the server declares

    • title: Speech-to-text
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • browser.renderPaid ($0.003/call): Read a page as clean markdown, rendering it in a real headless Chromium browser (JavaScript executed) when the page needs it.Reads text others writeCan send data outNo findings

    Why it is in this group

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

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Paid ($0.003/call): Read a page as clean markdown, rendering it in a real headless Chromium browser (JavaScript executed) when the page needs it. Use this for SPAs and JS-heavy sites where plain fetching returns an empty shell; a page whose served HTML already carries its content is read without the browser, faster, and answers rendered: false.

    Annotations the server declares

    • title: Browser render
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • decide.executePaid ($0.001/call): Run a decision's plan (decisionId from POST /api/decide), or a free plan sketch (steps), through Agent402: first-party steps run directly, third-party steps are…Reads text others writeNo findings

    Why it is in this group

    • The name "decide.execute" says "execute": 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.
    Description, as the server wrote it
    Paid ($0.001/call): Run a decision's plan (decisionId from POST /api/decide), or a free plan sketch (steps), through Agent402: first-party steps run directly, third-party steps are bought from the seller and resold to you at Agent402's price (paid with a wallet on Base; prepaid credits and cards do not pay this route).

    Annotations the server declares

    • title: Decide: execute a plan
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • decide.feedback[free] Report whether one step of a decide.plan decision worked (success or failure, optional 1-5 quality and latency).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
    [free] Report whether one step of a decide.plan decision worked (success or failure, optional 1-5 quality and latency). Needs the decisionId and feedbackToken that decide.plan returned; one verdict per step, a later report replaces it. Reports feed tool reliability in future rankings.

    Annotations the server declares

    • title: Report how a decide plan step went
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • decide.planPaid ($0.010/call): Describe a job and get a call-ready plan: which tools, across this catalog and outside x402 sellers with a recently verified 402, solve it end to end, in what o…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
    Paid ($0.010/call): Describe a job and get a call-ready plan: which tools, across this catalog and outside x402 sellers with a recently verified 402, solve it end to end, in what order, with fallbacks and input params that validate against each tool's schema.

    Annotations the server declares

    • title: Decide: tool plan for a task
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • demand.request[free] Report a capability the 500+ tools do not cover, after catalog.search or catalog.find found nothing that fits.Reads text others writeNo findings

    Why it is in this group

    • The name "demand.request" says "request": 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.
    Description, as the server wrote it
    [free] Report a capability the 500+ tools do not cover, after catalog.search or catalog.find found nothing that fits. Requests are clustered by need, and frequent ones get built. Records demand only: it runs nothing. Same intake as POST https://agent402.tools/api/wish; aggregate demand is public at https://agent402.tools/api/wishes.

    Annotations the server declares

    • title: Request a tool Agent402 does not have
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • memory.readPaid ($0.001/call): Read from a wallet-scoped namespace.Reads text others write1 finding

    Why it is in this group

    • The name "memory.read" says "read": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    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 "memory.read" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "memory.read" says "read": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Paid ($0.001/call): Read from a wallet-scoped namespace. ?key=… returns the stored value; omit key to list keys. The read half of memory-write's exact-key store. For similarity retrieval over remembered text, call the catalog slug memory-recall (on MCP, through catalog.call). Reads your own namespace by default; add ?owner=0x… to read a namespace you've been granted access to.

    Annotations the server declares

    • title: Memory read
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • web.answerPaid ($0.08/call): AI-generated answer to a natural-language question, grounded in live web search results with source citations.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
    Paid ($0.08/call): AI-generated answer to a natural-language question, grounded in live web search results with source citations. Returns clean prose plus a structured citations array (URL, snippet, favicon) - backed by an independent search index, not the model's training data. Useful when an agent needs a synthesized answer plus the receipts to verify or follow up.

    Annotations the server declares

    • title: Web answer
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • web.newsPaid ($0.01/call): Live news search: ranked recent articles as results[] of {title, url, description (the snippet, plain text), age, publishedAt (ISO), source (publisher hostname),…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
    Paid ($0.01/call): Live news search: ranked recent articles as results[] of {title, url, description (the snippet, plain text), age, publishedAt (ISO), source (publisher hostname), breaking} from an independent search index as clean JSON. Same freshness filter as web search (pd/pw/pm/py = past day/week/month/year).

    Annotations the server declares

    • title: News search
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • web.searchPaid ($0.01/call): Live web search: ranked results[] of {title, url, description (the snippet, plain text), age, publishedAt (ISO)} from an independent search index as clean JSON -…Reads text others write1 finding

    Why it is in this group

    • The name "web.search" says "search": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • untrusted-inputThe name "web.search" says "search" and "web": it reads web pages, which anyone can write.
    • untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.

    Findings

    • Warn

      The server marks "web.search" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "web.search" says "search": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Paid ($0.01/call): Live web search: ranked results[] of {title, url, description (the snippet, plain text), age, publishedAt (ISO)} from an independent search index as clean JSON - fresh pages your model's training cutoff has never seen. Optional freshness filter (pd/pw/pm/py = past day/week/month/year). It DISCOVERS pages; extract then reads the winner.

    Annotations the server declares

    • title: Web search
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • catalog.findResolve a plain-language task to the single best-matching Agent402 tool, returned call-ready: slug, price, input schema and a worked example.No findings

    Why it is in this group

    • The name "catalog.find" says "find": a word for reading.
    Description, as the server wrote it
    Resolve a plain-language task to the single best-matching Agent402 tool, returned call-ready: slug, price, input schema and a worked example. Use catalog.search to compare several candidates. Returns { task, results } with the top pick first; run it with catalog.call and the slug and params it lists.

    Annotations the server declares

    • title: Resolve a task to the one best Agent402 tool
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • catalog.searchKeyword search over the Agent402 catalog of 500+ tools (630 loaded by this connector).No findings

    Why it is in this group

    • The name "catalog.search" says "search": a word for reading.
    Description, as the server wrote it
    Keyword search over the Agent402 catalog of 500+ tools (630 loaded by this connector). Returns { results, workflows }; run one with catalog.call. 177 pure-CPU tools run free here (proof-of-work). The others are paid per call, payable here in the call over x402 or MPP (the payment rides in _meta), or through npx agent402-mcp with a wallet.

    Annotations the server declares

    • title: Search the Agent402 tool catalog
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • server.describe[free] Describe this connector: the tools it lists, how to install (Claude Code / Cursor / npm), free vs paid tiers, and discovery URLs.No findings

    Why it is in this group

    • The name "server.describe" says "describe": a word for reading.
    Description, as the server wrote it
    [free] Describe this connector: the tools it lists, how to install (Claude Code / Cursor / npm), free vs paid tiers, and discovery URLs.

    Annotations the server declares

    • title: About this Agent402 connector
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write11
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:59 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
13
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 13 tools that change things (2 destructive, 1 irreversible, 10 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://agent402.tools/mcp: tools/list returned 16 tools to an anonymous client, including catalog.call (destructive), memory.write (destructive), payment.info (irreversible), web.search (write), web.answer (write) and 8 more

    What this check looks for

Posture changes

  1. Nov 20, 2026
    • Tools that change things, listed without credentials: 14 to 13
  2. Nov 13, 2026
    • Tools that change things, listed without credentials: 16 to 14
  3. Oct 29, 2026
    • Tools that change things, listed without credentials: 12 to 16

Findings

Matches of fixed checks, with the text they matched.

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

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "payment.info" says "payment": a word that usually means money moves, which cannot be taken back.

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

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "web.search" says "search": a word for reading.

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

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "memory.read" says "read": a word for reading.

    What this check looks for

History

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

  1. Tools1 removed, 5 changed.−1 removed~5 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 14 -> 13.View diff
    • Tools that change things, listed without credentials: 14 to 13
  3. Tools3 changed.~3 changedView diff
  4. Tools3 changed.~3 changedView diff
  5. PostureRemote posture changed. Tools that change things, listed without credentials: 16 -> 14.View diff
    • Tools that change things, listed without credentials: 16 to 14
  6. Tools1 changed.~1 changedView diff
  7. PostureRemote posture changed. Tools that change things, listed without credentials: 12 -> 16.View diff
    • Tools that change things, listed without credentials: 12 to 16
  8. Tools1 changed.~1 changedView diff
  9. Tools1 removed, 17 changed.−1 removed~17 changedView diff
  10. Tools1 changed.~1 changedView diff

Install

Pinned to version 0.14.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http agent402 https://agent402.tools/mcp
claude mcp add --transport http agent402 https://agent402.tools/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__agent402__catalog_search",
      "mcp__agent402__catalog_find",
      "mcp__agent402__server_describe"
    ],
    "ask": [
      "mcp__agent402__payment_info",
      "mcp__agent402__web_search",
      "mcp__agent402__web_answer",
      "mcp__agent402__web_news",
      "mcp__agent402__browser_render",
      "mcp__agent402__audio_transcribe",
      "mcp__agent402__memory_read",
      "mcp__agent402__decide_plan",
      "mcp__agent402__decide_execute",
      "mcp__agent402__demand_request",
      "mcp__agent402__decide_feedback"
    ],
    "deny": [
      "mcp__agent402__catalog_call",
      "mcp__agent402__memory_write"
    ]
  }
}

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 agent402. Review it before you use it.

Capability tags behind 11 rules
  • mcp__agent402__catalog_call untrusted-input
  • mcp__agent402__web_search untrusted-input
  • mcp__agent402__web_answer untrusted-input
  • mcp__agent402__web_news untrusted-input
  • mcp__agent402__browser_render untrusted-input, outbound
  • mcp__agent402__audio_transcribe untrusted-input, outbound
  • mcp__agent402__memory_read untrusted-input
  • mcp__agent402__decide_plan untrusted-input
  • mcp__agent402__decide_execute untrusted-input
  • mcp__agent402__demand_request untrusted-input
  • mcp__agent402__decide_feedback 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.MikeyPetrillo/agent402/verify?hash=7e185e968e08975f5fe408e47f5150aaa11ada0c79c66c7e17f340a654d510aa" | jq -e '.changed == false'

Pinned hash 7e185e968e08, from Nov 21, 2026, 05:18 UTC.

Watch

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

https://radar.anlyon.com/servers/io.github.MikeyPetrillo/agent402/changes.xml

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

Badge

Anlyon Radar badge for io.github.MikeyPetrillo/agent402
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.MikeyPetrillo/agent402.svg)](https://radar.anlyon.com/servers/io.github.MikeyPetrillo/agent402)

Source: MCP Registry · repository. Synced Nov 21, 2026, 05:17 UTC.

Agent402.Tools: payments and trust for AI agents MCP server: questions and answers

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

Is the Agent402.Tools: payments and trust for AI agents MCP server safe?

No scan can promise that. What its definitions show: 16 tools, 13 of which can change, send or delete something, and 3 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 Agent402.Tools: payments and trust for AI agents MCP server delete data?

Yes. 2 tools can delete, cancel or revoke something: catalog.call and memory.write.

Can the Agent402.Tools: payments and trust for AI agents MCP server do things that cannot be undone?

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

What tools does the Agent402.Tools: payments and trust for AI agents MCP server have?

16 tools: 2 destructive, 1 irreversible, 10 write, 3 read. catalog.call, memory.write, payment.info, web.search, web.answer, web.news, browser.render, audio.transcribe and 8 more.

Does the Agent402.Tools: payments and trust for AI agents MCP server need sign-in or OAuth?

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

Does the Agent402.Tools: payments and trust for AI agents MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): browser.render and audio.transcribe.

Has the Agent402.Tools: payments and trust for AI agents MCP server changed its tools?

Yes, 8 times since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.