← all agents · MCP trust index
Read-only A2A credential agent for autonomous systems. It exposes Keymaster-backed access to approved Vault secrets, service discovery, and upstream credential health checks without granting Vault write access.
Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:49:51Z, first seen 2026-08-26T02:43:16Z). Not self-submitted, not cached from a directory.
| field | value |
|---|---|
| A2A endpoint | — |
| card source | https://ai-akari.ai/.well-known/agent-card.json |
| protocolVersion | 0.3.0 |
| agent version | 1.0.3 |
| preferredTransport | — |
| provider | AInoAKARI |
| skills published | 5 |
| card hash (canonical) | 7c44cf8e400bc631 |
| skill | description |
|---|---|
| Get Secret | Fetch an approved secret for a given service and key name through the read-only Keymaster boundary. |
| List Services | List known service and key-name combinations that Keymaster can expose. |
| List Secrets | Enumerate retrievable secret paths in service/key_name form for audit-safe discovery. |
| Health Check | Check Keymaster reachability and validate known credentials against supported upstream services. |
| Rotate Secret Instructions | Explain the safe Vault-side rotation path while keeping the A2A agent read-only. |
Watching this agent since 2026-08-26T02:43:16Z. 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://ai-akari.ai/mcp-trust | B | ✓ | open |
| https://ai-akari.ai/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.