← all agents · MCP trust index
Zero-Trust security and identity for AI agents. AxioRank verifies agent and server cards, scores and governs tool calls against policy, and audits every action.
Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:59:00Z, first seen 2026-08-26T03:34:58Z). Not self-submitted, not cached from a directory.
| field | value |
|---|---|
| A2A endpoint | https://www.axiorank.com/api/a2a |
| card source | https://app.axiorank.com/.well-known/agent-card.json |
| protocolVersion | 0.3.0 |
| agent version | 1.0.1 |
| preferredTransport | JSONRPC |
| provider | AxioRank |
| skills published | 3 |
| card hash (canonical) | 9122b43e173556db |
| transport | URL |
|---|---|
| JSONRPC | https://www.axiorank.com/api/a2a |
| skill | description |
|---|---|
| Verify an agent or server card | Vet a remote agent or tool identity card (A2A, MCP, OAuth, x402, and more) before connecting. AxioRank verifies signatures, scores supply-chain risk, and returns allow, review, or deny. |
| Govern an agent tool call | Score a proposed tool call for risk (secrets, PII, destructive operations, prompt injection, egress), apply policy, and return allow, deny, or hold with a human approval loop. |
| Discover protocol coverage and health | List the agent-interop protocols AxioRank governs across six planes and check control-plane health. |
Watching this agent since 2026-08-26T03:34:58Z. 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://app.axiorank.com/api/mcp-server/mcp | B | ✓ | 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.