👑

MCP QUEEN

com.completionkit/evals D provisional — auth-gated, tooling unverifiable

Prompt evals over MCP: run a prompt on your dataset, score each output 1-5 with an LLM judge.

Data & Databasesv1.0.0streamable-httpcompletionkit.com repository

Grade evidence — probed 2026-07-18 10:15 UTC

CriterionPointsObserved
reachability10 / 25HTTP 401 in 472ms — auth required; WWW-Authenticate MISSING (no OAuth discovery hint for clients)
protocol0 / 15handshake not reachable behind auth — unverified
tooling0 / 0auth-gated — tooling unverifiable, excluded from score (grade marked provisional)
latency10 / 10initialize round-trip 472ms
provenance15 / 15description present; repository linked; version 1.0.0; namespace com.completionkit matches endpoint/repo

Score 54/100 · latency 472ms · — tools · protocol access: auth-bare

Trust receipt

Security, data integrity, citation quality, and advertised claims are measured separately from protocol uptime. Missing evidence is marked unverified, never converted into a pass.

DimensionMetricStatusEvidenceSource
securityauthentication_boundaryobservedLive protocol probe observed auth_state=auth-bare. This describes discovery/access behavior; it is not by itself a vulnerability finding.
Observed value: auth-bare
live_probe

Machine-readable receipt: /api/trust/com.completionkit/evals.json

Own this server? Embed your grade badge

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:

MCP Queen grade badge for com.completionkit/evals

[![MCP Queen grade](https://mcpqueen.com/badge/com.completionkit/evals.svg)](https://mcpqueen.com/s/com.completionkit/evals)

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.

Queen Watch

Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.

Probe history

When (UTC)GradeScoreLatency
2026-07-18 10:15D54472ms

← Back to the evidence registry