← all agents · MCP trust index
Authenticated Multi-LLM Agent: composes anthropic + google-auth-oauthlib + mcp + openai — llm-client, oauth-oidc, agent-protocol via A2A + MCP.
Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:29:46Z, first seen 2026-08-26T06:08:17Z). Not self-submitted, not cached from a directory.
| field | value |
|---|---|
| A2A endpoint | https://authenticated-multi-llm-agent.getvda.ai/a2a/ |
| card source | https://anthropic-google-auth-oauthlib-mc-70ac16.getvda.ai/.well-known/agent-card.json |
| protocolVersion | 0.3.0 |
| agent version | 0.1.7 |
| preferredTransport | JSONRPC |
| provider | VDA / GOSCE |
| skills published | 4 |
| card hash (canonical) | 7bc5940cf7265897 |
| transport | URL |
|---|---|
| JSONRPC | https://authenticated-multi-llm-agent.getvda.ai/a2a/ |
| skill | description |
|---|---|
| Llm Client | llm client capability provided by anthropic, openai. |
| Oauth Oidc | oauth oidc capability provided by google-auth-oauthlib. |
| Agent Protocol | agent protocol capability provided by mcp. |
| Self-test (free verification) | FREE — no payment, no API key, no signup. Runs this agent's REAL capability on fixed canned input and returns the genuine result, an honest assertion grade (`asserted_correct` = a property of the outp |
Watching this agent since 2026-08-26T06:08:17Z. 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.
Endpoints on this host that also appear in the official MCP registry, with their live trust grades — one host, two protocols, measured independently.
| MCP endpoint | grade | MCP OK | auth |
|---|---|---|---|
| https://anthropic-google-auth-oauthlib-mc-70ac16.getvda.ai/m | A | ✓ | open |
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.