# APIR Agent Verification

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

- name: ai.apir/verify
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 83/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.apir%2Fverify
- tools: https://api.protogrid.dev/v1/servers/ai.apir%2Fverify/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "verify": {
      "type": "http",
      "url": "https://apir.ai/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% +updated-7d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: check_authority (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_verification_keys (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); verify_agent (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 538 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 3, about 538 tokens to load them all
- tool set hash: 8061092c50c70434de98b1072a13e582
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.apir/verify.svg)](https://protogrid.dev/servers/ai.apir/verify)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://apir.ai/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (3)

- `check_authority`: 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_keys`: 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.
- `verify_agent`: 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.