Give your agent its own email address with graduated human oversight, from approval to autonomy.
AI & Agentsv0.13.0streamable-httpmcp.multimail.dev repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 18 / 25 | HTTP 401 in 184ms — auth required; WWW-Authenticate present: "Bearer realm="OAuth", resource_metadata="https://mcp.multimail.dev/.well-known/oauth-protected-resource", error="invalid" |
| protocol | 0 / 15 | handshake not reachable behind auth — unverified |
| tooling | 0 / 0 | auth-gated — tooling unverifiable, excluded from score (grade marked provisional) |
| latency | 10 / 10 | initialize round-trip 184ms |
| provenance | 15 / 15 | description present; repository linked; version 0.13.0; namespace dev.multimail matches endpoint/repo |
Score 66/100 · latency 184ms · — tools · auth: auth-wellbehaved
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/dev.multimail/mcp-server)
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 |
|---|---|---|---|
| 2026-07-13 10:45 | C | 66 | 184ms |