MCP Queen

Official4 toolsLive

by mcpqueen · TypeScript

The graded MCP registry: evidence-backed server grades from live probes. Search, verify, connect.

Topics

agent-toolsmcpmcp-registrymcp-servermodel-context-protocol

Captured live from the server via tools/list.

search_servers

Search the graded MCP registry for servers matching a task or keyword (e.g. 'postgres', 'send email', 'web scraping'). Returns the best-graded matches with their remote endpoint URLs so you can connect directly. Optionally filter by category.

Parameters3

query	string	required	Keyword or task to search name/title/description for
category	string	optional	Optional category filter: Dev & Code, Data & Databases, Web & Search, AI & Agents, Finance & Crypto, Communication, Productivity, Security, Commerce, Media & Design, Cloud & Infra, Science & Health, Other
limit	number	optional	Max results (default 10, max 25)

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Keyword or task to search name/title/description for"
    },
    "category": {
      "type": "string",
      "description": "Optional category filter: Dev & Code, Data & Databases, Web & Search, AI & Agents, Finance & Crypto, Communication, Productivity, Security, Commerce, Media & Design, Cloud & Infra, Science & Health, Other"
    },
    "limit": {
      "type": "number",
      "description": "Max results (default 10, max 25)"
    }
  },
  "required": [
    "query"
  ]
}

list_grades

List the top graded MCP servers from the mcpqueen registry (deterministic probe grades with evidence). Returns grade, score 0-100, latency, tool count and auth state per server.

Parameters1

limit

number

optional

Max servers to return (default 25, max 100)

Raw schema

{
  "type": "object",
  "properties": {
    "limit": {
      "type": "number",
      "description": "Max servers to return (default 25, max 100)"
    }
  }
}

get_server_grade

Get the full grade and verbatim probe evidence for one MCP server, by its official registry name (e.g. 'com.healthai/radar').

Parameters1

name

string

required

Registry server name

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Registry server name"
    }
  },
  "required": [
    "name"
  ]
}

submit_feedback

Submit a field report about an MCP server you have actually used (what worked, what failed, surprising behavior). Reports are quarantined for human review and never auto-published.

Parameters3

server_name	string	required	Official registry name of the server the report is about
report	string	required	The field report, 20-2000 chars, specific and factual
agent_name	string	optional	Optional: which agent/client is reporting

Raw schema

{
  "type": "object",
  "properties": {
    "server_name": {
      "type": "string",
      "description": "Official registry name of the server the report is about"
    },
    "report": {
      "type": "string",
      "description": "The field report, 20-2000 chars, specific and factual"
    },
    "agent_name": {
      "type": "string",
      "description": "Optional: which agent/client is reporting"
    }
  },
  "required": [
    "server_name",
    "report"
  ]
}

README.md3 KBView on GitHub

mcpqueen.com — the graded MCP registry

LIVE at https://mcpqueen.com (Cloudflare Worker, launched 2026-07-12). Crawls the official MCP registry, probes every remote server, grades it deterministically with verbatim evidence, and publishes the results. Evidence discipline from Constat/Clarity, personality on top.

Why this is different (for agents and humans alike)

Every other MCP directory lists; this one verifies. Each remote server is probed live over streamable HTTP and graded on five criteria — and every point carries the verbatim observation that earned it. Unverifiable dimensions (auth-gated tooling) are marked provisional, never guessed. No stars, no votes, no pay-to-rank — probes only, continuously re-run.

Agents: connect to https://mcpqueen.com/mcp (streamable HTTP, no auth) and use search_servers to find working, graded servers for a task before you commit to one. Machine surfaces: /api/grades.json · /api/changes.json · /llms.txt. Registry name: com.mcpqueen/registry.

Architecture (single Worker)

src/worker.ts — everything: registry crawler, prober/grader, HTML pages, JSON API, and mcpqueen's own MCP endpoint.
public/ — static landing (crown data-rain + Vex the fox) served via the assets binding; the Worker handles all non-asset routes.
D1 database mcpqueen (schema.sql): servers, probes, latest_grades, feedback (quarantined agent field reports), meta (sync cursor).
Cron */15 * * * *: sync 4 registry pages + probe the 30 stalest remotes (~2,900 probes/day; full re-probe cycle ≈ 2.7 days over ~7.7K remotes).

Routes

Route	What
`/`	landing (static)
`/registry`	leaderboard + methodology
`/s/<registry-name>`	per-server grade with evidence + probe history
`/api/grades.json`	grades as JSON (CORS open)
`/mcp`	mcpqueen's MCP server: `list_grades`, `get_server_grade`, `submit_feedback`
`/mcp-info`	for-agents page
`/admin/*`	operator endpoints (key-gated)

Grading rubric (deterministic, every point carries its observation)

reachability 25 · protocol 15 · tooling 35 (tools/list, described %, typed %, description depth) · latency 10 · provenance 15 (metadata + namespace↔domain match). Auth-gated servers are scored on the verifiable subset and marked provisional. Agent feedback via submit_feedback is quarantined for human review — never auto-published, never affects grades directly.

Deploy

code

npm run deploy          # wrangler deploy (any Cloudflare API token with Workers + D1 write)
npm run db:schema       # apply schema.sql to remote D1

Custom domains mcpqueen.com + www are attached to the Worker (moved off the Pages project 2026-07-12; mcpqueen.pages.dev still exists as a static preview of public/ only — it has no /registry).

Install

Tools (4)

search_serverslist_gradesget_server_gradesubmit_feedback

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcpqueen.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "registry": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcpqueen.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.