MCP Server Finder

🔍 GitHub MCP服务器搜索API

FastAPI微服务，让您在GitHub上搜索 MCP服务器存储库 使用自然语言提示。

使用它来查找实现MCP服务器的开源存储库，用于不同的任务，如网络搜索、LLM集成、检索等。

______________________________________________________________________

🚀 如何使用

▶️ 步骤1：启动API服务器

python main.py

你会在终端上看到这样的东西：

Uvicorn running on http://127.0.0.1:8000

▶️ 步骤2：测试服务器

✅ 选项A：使用浏览器（Swagger UI）

打开浏览器并转到：

http://127.0.0.1:8000/docs

您将看到一个交互式API页面（Swagger UI）

展开/搜索端点

输入提示（例如，网络搜索），然后单击执行

查看下面的JSON响应

🌀 选项B：使用终端（curl）

curl "http://127.0.0.1:8000/search?prompt=web%20search"

在Powershell中以更好的格式获取响应(🪟)

(Invoke-RestMethod "http://127.0.0.1:8000/search?prompt=web%20search") | ConvertTo-Json -Depth 5

输出示例：

{
  "results": [
    {
      "name": "tavily/tavily-search",
      "url": "https://github.com/tavily/tavily-search",
      "description": "A search API for LLMs"
    }
  ]
}

示例测试

alt text

alt text

收到的回复：

{
  "results": [
    {
      "name": "exa-labs/exa-mcp-server",
      "url": "https://github.com/exa-labs/exa-mcp-server",
      "description": "Claude can perform Web Search | Exa with MCP (Model Context Protocol)"
    },
    {
      "name": "mshojaei77/ReActMCP",
      "url": "https://github.com/mshojaei77/ReActMCP",
      "description": "ReActMCP is a reactive MCP server that empowers AI assistants to instantly respond with real-time, Markdown-formatted web search insights powered by the Exa API."
    },
    {
      "name": "jsonallen/perplexity-mcp",
      "url": "https://github.com/jsonallen/perplexity-mcp",
      "description": "A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API."
    },
    {
      "name": "nickclyde/duckduckgo-mcp-server",
      "url": "https://github.com/nickclyde/duckduckgo-mcp-server",
      "description": "A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing."
    },
    {
      "name": "RamXX/mcp-tavily",
      "url": "https://github.com/RamXX/mcp-tavily",
      "description": "An MCP server for Tavily's search API"
    },
    {
      "name": "nkapila6/mcp-local-rag",
      "url": "https://github.com/nkapila6/mcp-local-rag",
      "description": "\"primitive\" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨"
    },
    {
      "name": "yokingma/one-search-mcp",
      "url": "https://github.com/yokingma/one-search-mcp",
      "description": "🚀 OneSearch MCP Server: Web Search & Scraper & Extract,  Support Firecrawl, SearXNG, Tavily, DuckDuckGo, Bing, etc."
    },
    {
      "name": "LinkupPlatform/python-mcp-server",
      "url": "https://github.com/LinkupPlatform/python-mcp-server",
      "description": "Linkup is a third-party extension that gives Claude access to real-time web search and premium content sources. It seamlessly integrates with Claude Desktop, enabling up-to-date information retrieval during conversations through a simple 60-second setup process."
    },
    {
      "name": "Sunwood-ai-labs/duckduckgo-web-search",
      "url": "https://github.com/Sunwood-ai-labs/duckduckgo-web-search",
      "description": "DuckDuckGo Web Search MCP Server - A simple web search implementation for Claude Desktop using DuckDuckGo API"
    },
    {
      "name": "DappierAI/dappier-mcp",
      "url": "https://github.com/DappierAI/dappier-mcp",
      "description": "Dappier MCP server connects any AI to proprietary, real-time data — including web search, news, sports, stock market data, and premium publisher content."
    }
  ]
}