πŸ‘‘

MCP QUEEN

The Graded Registry

Every remote server in the official MCP registry, probed live and graded with receipts β€” the only MCP index where every grade shows its evidence.

16246servers indexed
7735remote endpoints
742graded (rolling)
206grade A
68%reachable
384msmedian latency
SortBestWorstJust probedMost toolsFastest
GradeAllA (206)B (3)C (194)D (105)F (234)Provisional
CategoryAll categoriesOther (202)Web & Search (136)AI & Agents (127)Cloud & Infra (65)Productivity (42)Dev & Code (34)Data & Databases (28)Finance & Crypto (26)Communication (21)Media & Design (19)Commerce (17)Science & Health (13)Security (12)

20 matches. Categories are keyword-derived from registry metadata β€” imperfect by design, deterministic by principle.

#ServerGradeScoreLatencyToolsAuthProbed
1 ai.cobbles/cobbles
AI & Agents
D prov. 57
1699ms β€” auth-wellbehaved 07-12 14:19
2 ai.cueframe/cueframe
AI & Agents
D prov. 57
805ms β€” auth-wellbehaved 07-12 14:19
3 ai.enyal/enyal
ENYAL by Greenland AI
AI & Agents
D prov. 57
569ms β€” auth-wellbehaved 07-12 14:20
4 ai.hirey/hi
AI & Agents
D prov. 57
876ms β€” auth-wellbehaved 07-12 14:31
5 ai.korey/mcp
Korey
AI & Agents
D prov. 57
1000ms β€” auth-wellbehaved 07-12 14:46
6 ai.krtr/krtr
AI & Agents
D prov. 57
549ms β€” auth-wellbehaved 07-12 14:46
7 ai.parceled/mcp
AI & Agents
D prov. 57
775ms β€” auth-wellbehaved 07-12 15:16
8 ai.relaystation/relaystation
Relaystation
AI & Agents
D prov. 57
881ms β€” auth-wellbehaved 07-12 15:31
9 ai.calendarmcp/server
CalendarMCP
AI & Agents
D prov. 54
82ms β€” auth-bare 07-12 14:19
10 ai.responsibleailabs/rail-score
AI & Agents
D prov. 54
313ms β€” auth-bare 07-12 15:31
11 ai.taskforcehq/taskforce
Taskforce
AI & Agents
D prov. 54
385ms β€” auth-bare 07-12 17:47
12 ai.hivewiki/hivewiki
hiveWiki
AI & Agents
D prov. 52
2702ms β€” auth-wellbehaved 07-12 14:31
13 ai.multinex/memq
Multinex MemQ
AI & Agents
D prov. 52
2043ms β€” auth-wellbehaved 07-12 15:01
14 ai.superfact/superfact
AI & Agents
D prov. 52
2044ms β€” auth-wellbehaved 07-12 17:47
15 app.joinways/joinways
Joinways
AI & Agents
D prov. 52
2997ms β€” auth-wellbehaved 07-12 19:03
16 ai.bunzee/bunzee
Bunzee
AI & Agents
D prov. 49
363ms β€” auth-bare 07-12 14:19
17 ai.filtrix.mcp/filtrix-ai
Filtrix AI MCP
AI & Agents
D prov. 49
289ms β€” auth-bare 07-12 14:20
18 ai.multi-turn/enacta
AI & Agents
D prov. 49
390ms β€” auth-bare 07-12 15:01
19 ai.gossiper/shopify-admin-mcp
Gossiper Shopify Admin MCP Server
AI & Agents
D prov. 46
585ms β€” auth-wellbehaved 07-12 14:31
20 app.novumos/novumos
Novum OS
AI & Agents
D prov. 45
1063ms β€” auth-bare 07-12 19:03

Methodology

Each server is probed live over streamable HTTP: reachability (25) β€” does initialize succeed; auth-gated servers earn partial credit only if they advertise WWW-Authenticate so clients can discover OAuth. protocol (15) β€” valid JSON-RPC handshake; deprecated SSE transport is penalized. tooling (35) β€” tools/list works, share of tools with descriptions and fully-typed input schemas, median description depth. latency (10) β€” initialize round-trip. provenance (15) β€” 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 β€” probes only.