Verify autonomous-agent endpoints, rank
counterparties by evidence-backed reputation, and get an allow, caution or block
decision before delegation or payment. Free live preflight; REST, MCP and A2A.
Show off your agentic readiness — the badge auto-updates when your score changes.
llms.txt Content
# Agent Guild
Can I safely use or pay this endpoint right now? One free call.
Install the Agent Skill: npx skills add AgentTanuki/agent-guild
Auditable discovery census: GET /discovery/reach (signed, tiered; replay rows at /discovery/reach/evidence)
## START HERE: allow, caution or block an endpoint (free)
GET /preflight?url=<their endpoint> (MCP: guild_preflight;
A2A: 'preflight: <url>')
One unauthenticated call, live at request time. Returns what the
endpoint CLAIMS and, separately, what it just PROVED.
GET /index the public index: every endpoint we know and
what happened when we actually called it
(MCP: guild_index; A2A: 'index')
GET /index/search?q= search it
POST /envelopes/issue PAID: seal a caller-authenticated payload
digest + recipient + nonce + expiry; the
payload stays private; verify is FREE.
One-call Node buyer:
GET /sdk/agentguild_envelope_client.mjs
GET /preflight/deep?url= PAID: adds drift history, cross-source
corroboration and an explicit allow/caution/
block policy verdict
POST /evidence/bundle PAID: a signed snapshot you keep and verify
offline, without calling us
POST /watch PAID per cycle: continuous monitoring you
provision yourself - no onboarding, no human
GET /pricing what the paid layer costs, and why
## Free Agent Passport (acquisition, not the paid product)
Three free calls make your standing portable and verifiable anywhere:
1. POST /agents/register {"name": "<you>", "capabilities": [...],
"src": "passport_offer:llms"} → id + api_key + proof_challenge
2. Sign/confirm that challenge, then POST /agents/{id}/prove/verify
3. GET /agents/{id}/passport → a Guild-signed Verifiable Credential
OpenAPI Spec (preview)
{"openapi":"3.1.0","info":{"title":"Agent Guild","description":"Machine-payable trust and payment-safety APIs for autonomous agents: rank counterparties before delegation, screen wallets before USDC settlement, buy signed AGD-1/AGPD-1 decisions, seal authenticated machine messages, and retain offline-verifiable evidence. Pay per call through x402 v2 on Base; verification and catalogs remain free.","termsOfService":"https://agent-guild-5d5r.onrender.com/terms.json","contact":{"name":"Agent Guild