mcp-search-server

haran2001/mcp-search-server

3.3

If you are the rightful owner of mcp-search-server and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

The MCP Search Server is an intelligent Model Context Protocol server designed to help users discover and research MCP servers using the Exa AI search engine.

The MCP Search Server is a sophisticated tool that leverages the power of the Exa AI search engine to facilitate the discovery and research of Model Context Protocol (MCP) servers. Built with FastMCP, it seamlessly integrates with AI assistants like Claude and Cursor, providing users with a robust platform for exploring MCP servers. The server is designed to intelligently analyze search results, rank them based on relevance, and provide detailed information about specific MCP servers. It supports multiple search modes, including broad and GitHub-focused searches, and offers direct Q&A capabilities for users to ask specific questions about MCP servers. With its ability to organize MCPs by functional categories and find similar MCPs, the MCP Search Server is an invaluable tool for developers, AI assistants, and teams looking to standardize and document their use of MCPs.

Features

  • Smart MCP Discovery: Enables users to search for MCP servers based on specific requirements.
  • Intelligent Analysis: Automatically analyzes and ranks search results for MCP relevance.
  • Detailed Information: Provides comprehensive details about specific MCP servers.
  • Similar MCPs: Finds MCP servers similar to ones users already know.
  • Category Organization: Organizes MCPs by functional categories.

Usages

usage with claude desktop

{
  "mcpServers": {
    "mcp-search": {
      "command": "python",
      "args": ["/absolute/path/to/mcp_search_server.py"],
      "env": {
        "EXA_API_KEY": "your_exa_api_key_here"
      }
    }
  }
}

usage with cursor

{
  "command": "python",
  "args": ["/path/to/mcp_search_server.py"],
  "env": {
    "EXA_API_KEY": "your_api_key"
  }
}

usage with command line testing

bash
# Interactive testing with FastMCP CLI
fastmcp dev mcp_search_server.py

# Web-based inspector
fastmcp inspect mcp_search_server.py

usage with programmatic access

python
from fastmcp import Client

async def main():
    async with Client("mcp_search_server.py") as client:
        result = await client.call_tool("search_mcps", {
            "requirement": "file management",
            "max_results": 5
        })
        print(result.text)

Tools

  1. search_mcps

    Search for MCPs based on requirements.

  2. get_mcp_details

    Get detailed info about a specific MCP.

  3. find_similar_mcps

    Find MCPs similar to a reference.

  4. ask_mcp_question

    Ask specific questions about MCPs.

  5. categorize_mcps

    Get MCPs organized by categories.