Skip to content

APIR Agent Verification

by apir.ai · remote · no sign-in to list tools · v1.0.0 · published by ai.apir

Check an AI agent you did not build: is it who it claims, inside its mandate, and what's its record

Changes · 1
CompareRegistry entry

3 tools: 1 change things and 2 only read.

Scanned Oct 21, 2026

5 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http verify https://apir.ai/api/mcp

Findings

Matches of fixed checks, with the text they matched.

5 info

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 1Claude Code: ask
  • verify_agentCheck whether an AI agent carries a real, cryptographically signed credential.2 findings

    Why it is in this group

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

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...arries a real, cryptographically signed credential. Accepts an agent name, a credential id..."

      What this check looks for
    • Info

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

      Matched text

      inputSchema.properties.query.description: "Agent name, credential id (TP-... or APIR-TP-...), agent UUID,..."

      What this check looks for
    Description, as the server wrote it
    Check whether an AI agent carries a real, cryptographically signed credential. Accepts an agent name, a credential id (TP-...), an agent UUID, a domain or a DID. Returns one of seven verdicts: VERIFIED, EXPIRED, REVOKED, SUPERSEDED, UNSIGNED, UNCHECKED or NO_RECORD. IMPORTANT for interpreting the answer: VERIFIED means the Ed25519 signature recomputes against the key published at apir.ai and the credential is unexpired and unrevoked. It confirms WHO issued the credential and that its contents are unaltered. It is NOT a guarantee that the agent behaves well. NO_RECORD is an honest, first-class answer: it means nothing is on file, which is not evidence of wrongdoing and not a warning. It means any claim the agent makes about itself is unverified. Free, unauthenticated, and no account is required.
Only reads 2Claude Code: allow
  • check_authorityResolve the human mandate behind an AI agent: which actions a named person actually permitted, any value cap, the expiry, and whether the grant itself is signed.2 findings

    Why it is in this group

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

    Findings

    • Info

      The description mentions "credential".

      Matched text

      description: "...else's behalf. An agent holding a valid credential may still be acting outside its mandate..."

      What this check looks for
    • Info

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

      Matched text

      inputSchema.properties.query.description: "Agent name, credential id, or agent UUID."

      What this check looks for
    Description, as the server wrote it
    Resolve the human mandate behind an AI agent: which actions a named person actually permitted, any value cap, the expiry, and whether the grant itself is signed. Where authority was delegated agent to agent, the full chain is walked back to the human at the root, and one law is enforced at every hop: authority may only ever narrow. No hop can hold an action, a target or a spending cap wider than the hop above it, and the root must be a human. Use this before letting an agent transact, sign, spend or commit on someone else's behalf. An agent holding a valid credential may still be acting outside its mandate, and those are different questions.
  • get_verification_keysReturn the Ed25519 public keys APIR publishes, so a signature can be recomputed offline without trusting any APIR response, including this one.1 finding

    Why it is in this group

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

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...i. Retired keys stay published so older credentials still verify."

      What this check looks for
    Description, as the server wrote it
    Return the Ed25519 public keys APIR publishes, so a signature can be recomputed offline without trusting any APIR response, including this one. Keys are published as a JWKS at apir.ai/.well-known/jwks.json and as did:web:apir.ai. Retired keys stay published so older credentials still verify.

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 untrusted-input or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write0
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 Oct 22, 2026, 14:19 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
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
none
RFC 9728 protected resource metadata
none
Authorization servers
none
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://apir.ai/api/mcp: tools/list returned 3 tools to an anonymous client, including verify_agent (write)

    What this check looks for

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http verify https://apir.ai/api/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__verify__check_authority",
      "mcp__verify__get_verification_keys"
    ],
    "ask": [
      "mcp__verify__verify_agent"
    ],
    "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 verify. Review it before you use it.