👑

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)

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

#ServerGradeScoreLatencyToolsProtocol accessProbed
1 com.googleapis.compute/mcp
AI & Agents
D 59
715ms open 08-26 13:30
2 com.dotprompts/dotprompts
.prompts
AI & Agents
D prov. 58
303ms auth-wellbehaved 08-26 11:00
3 ai.axonagentic/neuroautomata
Axon NeuroAutomata
AI & Agents
D prov. 57
910ms auth-wellbehaved 08-25 15:00
4 ai.krtr/krtr
AI & Agents
D prov. 57
662ms auth-wellbehaved 08-25 16:45
5 ai.superfact/superfact
AI & Agents
D prov. 57
804ms auth-wellbehaved 08-26 00:30
6 ai.tinyfish.agent/web-agent
TinyFish AI Web Agent
AI & Agents
D prov. 57
712ms auth-wellbehaved 08-26 00:45
7 ai.zentrik/mcp
Zentrik
AI & Agents
D prov. 57
1150ms auth-wellbehaved 08-26 01:45
8 app.novumos/novumos
NovumOS
AI & Agents
D prov. 57
655ms auth-wellbehaved 08-26 02:30
9 com.acprompt/acprompt
AI & Agents
D prov. 57
669ms auth-wellbehaved 08-26 06:30
10 com.ontoramp/graph-query
OntoRamp Graph Query
AI & Agents
D prov. 55
222ms auth-wellbehaved 08-26 18:15
11 ai.paperlantern/code
Paper Lantern
AI & Agents
D prov. 54
281ms auth-bare 08-25 20:00
12 ai.pyrimid/pyrimid
Pyrimid Protocol
AI & Agents
D prov. 54
186ms auth-bare 08-25 20:15
13 ai.taskforcehq/taskforce
Taskforce
AI & Agents
D prov. 54
269ms auth-bare 08-26 00:30
14 ai.waystation/mcp
AI & Agents
D prov. 54
21ms auth-bare 08-26 01:30
15 com.6ducklearn/mcp
6DuckLearn MCP
AI & Agents
D prov. 54
66ms auth-bare 08-26 06:15
16 com.guruwalk/affiliates-mcp
GuruWalk Affiliates
AI & Agents
D prov. 54
193ms auth-bare 08-26 14:01
17 com.hekkova/mcp
AI & Agents
D prov. 54
323ms auth-bare 08-26 14:01
18 com.inboxpolicy/send-decision
AI & Agents
D prov. 54
118ms auth-bare 08-26 14:15
19 com.jumpcloud/jumpcloud-genai
AI & Agents
D prov. 54
586ms auth-wellbehaved 08-26 14:45
20 com.pingfyr/pingfyr
Pingfyr
AI & Agents
D prov. 54
207ms auth-bare 08-26 19:00
21 ai.multinex/memq
Multinex MemQ
AI & Agents
D prov. 52
1515ms auth-wellbehaved 08-25 17:15
22 co.ultraprompt/ultra-prompt
Ultra Prompt
AI & Agents
D prov. 51
46ms auth-wellbehaved 08-26 06:00
23 ai.filtrix.mcp/filtrix-ai
Filtrix AI MCP
AI & Agents
D prov. 49
207ms auth-bare 08-25 16:15
24 com.datadoe/amazon-seller-mcp
DataDoe MCP
AI & Agents
D prov. 49
661ms auth-bare 08-26 10:30
25 com.daxoom/daxoom
AI & Agents
D prov. 49
625ms auth-bare 08-26 10:45
26 com.lassare/ask
Lassare
AI & Agents
D prov. 49
629ms auth-bare 08-26 15:15
27 com.mycloudclaw/cloudclaw
CloudClaw
AI & Agents
D prov. 49
975ms auth-bare 08-26 17:01
28 com.outliyr/agent-tools
AI & Agents
D prov. 49
157ms auth-bare 08-26 18:30
29 ai.bunzee/bunzee
Bunzee
AI & Agents
D prov. 45
778ms auth-bare 08-25 15:15
30 com.automatedclientacquisition.www/aca
ACA - Automated Client Acquisition
AI & Agents
D prov. 45
1006ms auth-bare 08-26 07:30

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.