← all agents · MCP trust index
Decomposes any request into a grounded, reusable route and returns a scored decision frame for a choice or a synthesized, checkable answer for a question — served over MCP. Every solved ask makes the next one cheaper.
Everything on this page was fetched from the agent's own well-known card by GolemreachTrustBot (outside-in probe, last checked 2026-08-29T17:52:50Z, first seen 2026-08-26T02:45:45Z). Not self-submitted, not cached from a directory.
| field | value |
|---|---|
| A2A endpoint | https://liminality.physea.ai |
| card source | https://liminality.physea.ai/.well-known/agent-card.json |
| protocolVersion | — |
| agent version | 0.1.0 |
| preferredTransport | — |
| provider | Physea |
| skills published | 3 |
| card hash (canonical) | dcb944bae0b2928f |
| transport | URL |
|---|---|
| unspecified | https://liminality.physea.ai |
| skill | description |
|---|---|
| Solve | Work out a hard question, decision, or multi-step task end to end and return a grounded, reusable result. |
| Decide | Score options against the criteria that matter and recommend one, with what would flip it. |
| Answer | Give a direct, source-grounded answer with an honest confidence instead of a guess. |
Watching this agent since 2026-08-26T02:45:45Z. 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.
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://liminality.physea.ai/mcp | D | ✗ | required |
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.