← all agents · MCP trust index
Paid pre-execution risk verification for autonomous AI agents.
Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:28:10Z, first seen 2026-08-26T06:06:45Z). Not self-submitted, not cached from a directory.
| field | value |
|---|---|
| A2A endpoint | https://aegis-api.kadopi.workers.dev |
| card source | https://aegis-api.kadopi.workers.dev/.well-known/agent-card.json |
| protocolVersion | 0.3.0 |
| agent version | 0.6.0 |
| preferredTransport | — |
| provider | — |
| skills published | 2 |
| card hash (canonical) | 88f7f2d3b68d8cbc |
| transport | URL |
|---|---|
| unspecified | https://aegis-api.kadopi.workers.dev |
| skill | description |
|---|---|
| Verify risk | Checks prompt injection, contradictions, unsupported claims, and source availability before execution. |
| Monitor on-chain activity | Returns account-scoped structured alerts and accepts idempotent case-status updates. It never performs wallet actions. |
Watching this agent since 2026-08-26T06:06:45Z. 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.
| when (UTC) | what | version | skills | hash was | hash now |
|---|---|---|---|---|---|
| 2026-08-29T06:25:03Z | changed | 0.6.0→0.6.0 | 1→2 | 8e2207aa16 | 88f7f2d3b6 |
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://aegis-api.kadopi.workers.dev/mcp | 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.