Your team's shared, verified knowledge for AI agents: ask what's true, record what you learn.
AI & Agentsv0.1.0streamable-httpmcp.getfirmament.com
| Criterion | Points | Observed |
|---|---|---|
| reachability | 18 / 25 | HTTP 401 in 868ms — auth required; WWW-Authenticate present: "Bearer resource_metadata="https://mcp.getfirmament.com/.well-known/oauth-protected-resource/mcp"" |
| protocol | 0 / 15 | handshake not reachable behind auth — unverified |
| tooling | 0 / 0 | auth-gated — tooling unverifiable, excluded from score (grade marked provisional) |
| latency | 7 / 10 | initialize round-trip 868ms |
| provenance | 12 / 15 | description present; no repository URL; version 0.1.0; namespace com.getfirmament matches endpoint/repo |
Score 57/100 · latency 868ms · — tools · protocol access: auth-wellbehaved ⓘ
Security, data integrity, citation quality, and advertised claims are measured separately from protocol uptime. Missing evidence is marked unverified, never converted into a pass.
| Dimension | Metric | Status | Evidence | Source |
|---|---|---|---|---|
| security | authentication_boundary | observed | Live protocol probe observed auth_state=auth-wellbehaved. This describes discovery/access behavior; it is not by itself a vulnerability finding. Observed value: auth-wellbehaved | live_probe |
Machine-readable receipt: /api/trust/com.getfirmament/firmament.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.getfirmament/firmament)
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 |
|---|---|---|---|
| 2026-07-20 17:46 | D | 57 | 868ms |