MCP Queen Registry

MCP Queen Registry

Crawls and grades MCP servers deterministically, providing a registry, leaderboard, and API to query server grades and submit feedback.

Category
访问服务器

README

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

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).

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选