← all agents · MCP trust index

AFMR Discovery Agent

Read-only discovery for AFMR 1.0, the AFMR Reputation Attestation working draft, and configuration-scoped Lift Evidence.

Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:49:50Z, first seen 2026-08-26T02:43:13Z). Not self-submitted, not cached from a directory.

Measured card surface

fieldvalue
A2A endpoint
card sourcehttps://afmr.ai/.well-known/agent-card.json
protocolVersion
agent version1.0.0
preferredTransport
providerAgent Failure Mode Registry
skills published4
card hash (canonical)c4edf521c212d7f4

Skills (from card)

skilldescription
Discover AFMR resourcesReturns canonical AFMR authority, schemas, registries, evidence surfaces, current lifecycle status, and explicit decision boundaries.
Look up an AFMR failure modeReturns an exact record from the canonical AFMR 1.0 registry when a permanent AFMR-F### identifier is supplied.
Discover the Reputation Attestation contractReturns the Working Draft 0.1 specification, schema, verifier requirements, endpoint-registry location, lifecycle vocabulary, and explicit interpretation boundaries.
Discover the Lift Evidence contractReturns the empty configuration-only index and canonical public-card schema without asserting measured lift, individual reputation, or safety.

Card-drift history

Watching this agent since 2026-08-26T02:43:13Z. Hash = SHA-256 (16 hex) of the card's canonical JSON (sort_keys, no whitespace), so whitespace-only edits don't count as drift. Feed: api/a2a-drift.json.

No drift recorded yet for this agent — its card hash has been stable across every round since we started watching.

Same host, MCP side

Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.

MCP endpointgradeMCP OKauth
https://afmr.ai/mcpAopen
https://afmr.ai/api/rpcAopen

Golemreach Trust Layer · A2A index · method & opt-out · card re-fetched every sweep round; opt-out per /trust/bot removes the whole host within 48h.