Brave MCP Search

🚀 Brave Search MCP Server

This project implements a Model Context Protocol (MCP) server for Brave Search, supporting integration with AI assistants like Claude.

🚀 Quick Start

This project implements a Model Context Protocol (MCP) server for Brave Search, enabling seamless integration with AI assistants such as Claude.

✨ Features

• Integrate with AI assistants like Claude.
• Provide two main tools: brave_web_search and brave_local_search.

📦 Installation

Automatic Installation via Smithery

To quickly and automatically install the Brave Search MCP Server for use with the Claude desktop version using Smithery:

npx -y @smithery/cli install @arben-adm/brave-mcp-search --client claude

Manual Installation

1. Clone the repository:

   git clone https://github.com/your-username/brave-search-mcp.git
   cd brave-search-mcp
   

2. Create a virtual environment and install dependencies using uv:

   uv venv
   source .venv/bin/activate  # On Windows, use: .venv\Scripts\activate
   uv pip install -r requirements.txt
   

3. Set your Brave Search API key:

   export BRAVE_API_KEY=your_api_key_here
   

   On Windows, use: set BRAVE_API_KEY=your_api_key_here

💻 Usage Examples

Basic Usage

1. Configure the MCP settings file (e.g., claude_desktop_config.json) to include the Brave Search MCP server:

   {
     "mcpServers": {
       "brave-search": {
         "command": "uv",
         "args": [
           "--directory",
           "path-to\\mcp-python\\brave-mcp-search\\src",
           "run",
           "server.py"
         ],
         "env": {
           "BRAVE_API_KEY": "YOUR_BRAVE_API_KEY_HERE"
         }
       }
     }
   }
   

   Replace YOUR_BRAVE_API_KEY_HERE with your actual Brave API key.

2. Start the Brave Search MCP server by running your MCP-compatible AI assistant with the updated configuration.

3. The server is now up and ready to accept requests from MCP clients.

4. You can now use the Brave Search functionality in your MCP-compatible AI assistant (e.g., Claude) by invoking the available tools.

📚 Documentation

The server provides two main tools:

1. brave_web_search: Perform web searches using the Brave Search API.
2. brave_local_search: Search for local businesses and service locations.

For detailed information about the tools, refer to the tool docstrings in src/server.py.

🔧 Technical Details

Development

To make changes to the project:

1. Modify the code in the src directory as needed.
2. Update the requirements.txt file if you add or remove dependencies:

   uv pip freeze > requirements.txt
   

3. Restart the server to apply the changes.

Troubleshooting

If you encounter any issues:

1. Ensure that your Brave API key is set correctly.
2. Check that all dependencies are installed.
3. Verify that you are using a compatible Python version.
4. If you make changes to the code, make sure to restart the server.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.