👑

MCP QUEEN

The MCP Evidence Registry

Operational grades show whether a server connects and describes usable tools. Separate Trust Receipts show what has actually been observed about security and access boundaries, data integrity, citations, advertised claims, response quality, and real-world use.

Use MCP Queen in ChatGPT, Claude, or my agentWhy this registry is different
25517servers indexed
14061remote endpoints
14125graded (rolling)
20157trust observations
4response audits
650grade A
70%reachable
239msmedian latency
SortBestWorstJust probedMost toolsFastest
GradeAllA (650)B (12)C (523)D (202)F (613)Provisional
CategoryAll categoriesOther (516)AI & Agents (353)Cloud & Infra (259)Web & Search (252)Finance & Crypto (145)Productivity (78)Dev & Code (69)Data & Databases (65)Science & Health (58)Communication (55)Commerce (54)Media & Design (52)Security (44)

46 matches. Categories are keyword-derived from registry metadata — imperfect by design, deterministic by principle.

#ServerGradeScoreLatencyToolsProtocol accessProbed
1 com.googleapis.androidmanagement/mcp
Android Management API
Other
D 59
606ms open 08-26 13:30
2 com.googleapis.datastream/mcp
Other
D 59
629ms open 08-26 13:30
3 com.googleapis.memorystore/mcp
Other
D 59
571ms open 08-26 13:45
4 ai.diagramzu/mcp
DiagramZu
Other
D prov. 58
527ms auth-wellbehaved 08-25 16:00
5 ai.robomart/robomart
Other
D prov. 58
211ms auth-wellbehaved 08-25 20:30
6 ai.openhelm/dev-changes
Other
D prov. 57
845ms auth-wellbehaved 08-25 20:00
7 ai.openhelm/monitoring
Other
D prov. 57
726ms auth-wellbehaved 08-25 20:00
8 ai.smithery/plainyogurt21-clintrials-mcp
Other
D prov. 57
729ms auth-wellbehaved 08-25 23:45
9 ai.zine/mcp
Other
D prov. 57
853ms auth-wellbehaved 08-26 01:45
10 app.everpop/everpop
Other
D prov. 57
1436ms auth-wellbehaved 08-26 02:00
11 app.sharemypage/sharemypage
ShareMyPage
Other
D prov. 57
817ms auth-wellbehaved 08-26 02:45
12 com.archerionlabs/nasc
NASC — Networked AI Session Continuity
Other
D prov. 57
727ms auth-wellbehaved 08-26 07:30
13 com.biz-planner/mcp
Biz Planner
Other
D prov. 57
1021ms auth-wellbehaved 08-26 08:00
14 com.divineapi/horoscope
Divine API - Horoscope, Tarot & Numerology
Other
D prov. 57
530ms auth-wellbehaved 08-26 11:00
15 com.gencove.consumer/mcp
Other
D prov. 57
560ms auth-wellbehaved 08-26 12:45
16 com.guleki/geolocate-me
Geolocate Me
Other
D prov. 57
636ms auth-wellbehaved 08-26 14:01
17 com.knotrik/knotrik
Knotrik — AppSheet Intelligence
Other
D prov. 57
564ms auth-wellbehaved 08-26 15:00
18 com.mailopoly/mailopoly
Other
D prov. 57
927ms auth-wellbehaved 08-26 15:45
19 com.neurarelay/relay-mcp
Neura Relay MCP
Other
D prov. 57
862ms auth-wellbehaved 08-26 17:15
20 ai.marketcore/mcp
Marcora
Other
D prov. 55
161ms auth-wellbehaved 08-25 17:01
21 ai.mailjunky/mcp
MailJunky
Other
D prov. 54
107ms auth-bare 08-25 17:01
22 ai.waystation/airtable
Other
D prov. 54
44ms auth-bare 08-26 01:15
23 ai.waystation/miro
Other
D prov. 54
15ms auth-bare 08-26 01:30
24 ai.waystation/monday
Other
D prov. 54
8ms auth-bare 08-26 01:30
25 ai.waystation/office
Other
D prov. 54
8ms auth-bare 08-26 01:30
26 chat.mumo/mcp
Other
D prov. 54
180ms auth-bare 08-26 05:15
27 com.benriscore/api
Other
D prov. 54
38ms auth-bare 08-26 07:45
28 com.entidex/entidex
Entidex — Entity Intelligence & AI Knowledge Correction
Other
D prov. 54
80ms auth-bare 08-26 12:00
29 com.epublys/epublys
Epublys
Other
D prov. 54
448ms auth-bare 08-26 12:00
30 com.missingmcp/garmin
Garmin — MissingMCP
Other
D prov. 54
124ms auth-bare 08-26 16:45
31 ai.buron/buron
Buron
Other
D prov. 52
1578ms auth-wellbehaved 08-25 15:15
32 app.podstow/podstow
Podstow
Other
D prov. 52
1948ms auth-wellbehaved 08-26 02:45
33 bot.ttrpg/grimoire
Grimoire
Other
D prov. 52
3864ms auth-wellbehaved 08-26 04:45
34 com.heirmos/memory
Heirmos
Other
D prov. 52
1990ms auth-wellbehaved 08-26 14:01
35 com.cyclingcoachai/cycling-coach-ai
Cycling Coach AI
Other
D prov. 51
279ms auth-wellbehaved 08-26 10:15
36 ai.clawterminal/markets
ClawTerminal
Other
D prov. 49
148ms auth-bare 08-25 15:30
37 ai.rallyprop/gov-funding
RallyProp SBIR Opportunities
Other
D prov. 49
483ms auth-bare 08-25 20:15
38 cc.wealthos/mcp
Wealthos
Other
D prov. 49
302ms auth-bare 08-26 05:15
39 com.basenull/exec-brief
exec-brief
Other
D prov. 49
180ms auth-bare 08-26 07:45
40 com.basenull/polls
polls
Other
D prov. 49
180ms auth-bare 08-26 07:45
41 com.docpenny/pdf-generator
DocPenny PDF Generator
Other
D prov. 49
160ms auth-bare 08-26 11:00
42 com.jotform/mcp
Other
D prov. 49
145ms auth-bare 08-26 14:45
43 ai.butlerbrain/mcp
Other
D prov. 45
546ms auth-bare 08-25 15:15
44 ai.dimetrics/dimetrics
Other
D prov. 45
1004ms auth-bare 08-25 16:00
45 ai.edusignal/districts
Other
D prov. 45
864ms auth-bare 08-25 16:15
46 com.munispot/municipal-data
Other
D prov. 45
1081ms auth-bare 08-26 17:01

Own one of these servers?

Claim your live grade badge for your README, and get an email the moment your grade moves or your endpoint stops answering — find your server above and hit Watch. Free while in beta.

Running an agent?

Ask the queen before you connect to a stranger:
claude mcp add --transport http mcpqueen https://mcpqueen.com/mcp

Compare MCP servers by use case

Evidence-backed shortlists for high-intent decisions—not generated pages for every keyword.

Data & DatabasesWeb & SearchScience & HealthFinance & CryptoDev & Code Security & trust evidence

Methodology

Each server is probed live over streamable HTTP: reachability (25) — does initialize succeed; auth-gated servers earn partial credit only if they advertise WWW-Authenticate so clients can discover OAuth. protocol (15) — valid JSON-RPC handshake; deprecated SSE transport is penalized. tooling (35) — tools/list works, share of tools with descriptions and fully-typed input schemas, median description depth. latency (10) — initialize round-trip. provenance (15) — registry metadata completeness and whether the reverse-DNS namespace actually matches the serving domain. Scores scale to what is verifiable; unverifiable dimensions mark the grade provisional rather than guessing. Every point carries the verbatim observation that earned it. No stars, no votes, no pay-to-rank — probes only.

Trust Receipts are separate from the operational grade. Discovery records advertised security-sensitive capabilities, access caveats, citation promises, and corpus-size claims. Safe, read-only response audits sample eligible tools and test whether calls are usable, whether returned PMIDs/DOIs resolve against authoritative sources, and whether an apparently successful response actually contains an upstream error. Every observation includes its date, source type, sample size where applicable, and methodology version. No synthetic trust score is assigned, and absence of an observation means unaudited—not safe.

Queen Watch

Get an email when a server's grade changes or its endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.