Six-gate governance for AI agents: PROCEED/PAUSE/HALT decisions with hash-chained audit trails.
AI & Agentsv1.3.1streamable-httpmcp.aegis.undercurrentholdings.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 0 / 25 | HTTP 503 in 215ms — no valid initialize result |
| protocol | 0 / 15 | no handshake |
| tooling | 0 / 35 | unreachable — no tooling to assess |
| latency | 0 / 10 | not measurable |
| provenance | 15 / 15 | description present; repository linked; version 1.3.1; namespace com.undercurrentholdings matches endpoint/repo |
Score 15/100 · latency 215ms · — tools · protocol access: unreachable ⓘ
Security, data integrity, citation quality, and advertised claims are measured separately from protocol uptime. Missing evidence is marked unverified, never converted into a pass.
No deterministic trust observations published yet. This means unaudited—not safe, unsafe, accurate, or inaccurate.
Machine-readable receipt: /api/trust/com.undercurrentholdings/aegis.json
Live operational-grade badge, re-probed continuously — not a security or data-quality certification. Put it in your README and link to the complete receipt:
[](https://mcpqueen.com/s/com.undercurrentholdings/aegis)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-16 04:00 | F | 15 | 215ms |
| 2026-07-13 08:45 | F | 15 | 143ms |