MCP Search Server is an intelligent server that helps you discover, analyze, and compare MCP servers using Exa's search capabilities. Built with FastMCP integration, it can perform searches for MCPs, retrieve detailed information about a specific MCP, find similar MCPs, answer questions about MCPs, and categorize MCPs by functional areas. Core tools include search_mcps for broad queries, get_mcp_details to inspect a repository in depth, find_similar_mcps to surface alternatives, ask_mcp_question for direct Q&A, and categorize_mcps to explore by category. Once running, you can interact with the server to quickly surface MCPs that fit your requirements, understand their installation notes, and compare options side-by-side.

Prerequisites:

• Python 3.10+ (recommended)
• Exa API Key (required)
• Internet connection for search functionality
• Optional: Git for cloning, FastMCP CLI for testing

Method 1: Direct Download and Setup

1. Create and navigate to the project directory mkdir mcp-search-server cd mcp-search-server

2. Install dependencies pip install -r requirements.txt

   Or install manually

   pip install fastmcp>=2.0.0 httpx>=0.25.0

3. Set up environment variable

   Linux/Mac

   export EXA_API_KEY=your_exa_api_key_here

   Windows Command Prompt

   set EXA_API_KEY=your_exa_api_key_here

   Windows PowerShell

   $env:EXA_API_KEY="your_exa_api_key_here"

4. Run the server python mcp_search_server.py

Method 2: Using Virtual Environment (Recommended)

1. Create virtual environment and activate python -m venv mcp-search-env

   Linux/Mac:

   source mcp-search-env/bin/activate

   Windows:

   mcp-search-env\Scripts\activate

2. Install dependencies pip install -r requirements.txt

3. Run the server python mcp_search_server.py

Exa API Key Setup

1. Get API Key from Exa Dashboard and copy it (starts with exa_)
2. Set environment variable as shown in the installation steps above

Verification and Testing

• Basic installation check: python --version and import checks
• API Key test: verify EXA_API_KEY is set
• Server test: run test_mcp_search.py or start the server directly

Tips and common issues:

• Ensure EXA_API_KEY is set in the environment before starting the server; the server will use this to access Exa services.
• If you encounter dependency issues, verify you are using Python 3.10+ and reinstall requirements.
• For local development, consider using a virtual environment to isolate dependencies.
• If the server cannot reach Exa APIs, check your network settings or proxy configuration.
• The mcp_search_server.py script assumes the repository structure from the project; if you fork or relocate files, update paths accordingly.
• When testing with the FastMCP CLI, ensure the CLI version is compatible with FastMCP endpoints used by this server.