brave-mcp-search

brave-mcp-search

11
cloud_platformsai_chatbot

The Brave Search MCP Server project creates a server compatible with Model Context Protocol to integrate Brave Search functionality with AI assistants like Claude. It offers tools for web searches and local business searches.

Brave Search MCP Server

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

Prerequisites

  • Python 3.11+
  • uv - A fast Python package installer and resolver

Installation

Installing via Smithery

Install the Brave Search MCP server for Claude Desktop automatically via Smithery.

Manual Installation

  1. Clone the repository.
  2. Create a virtual environment and use uv to install dependencies.
  3. Set up your Brave Search API key.

Usage

  1. Configure your MCP settings file to include the Brave Search MCP server.
  2. Start the server by running your MCP-compatible AI assistant.
  3. The server will be ready to accept requests from MCP clients.
  4. Use the Brave Search functionality in your MCP-compatible AI assistant.

Available Tools

  • brave_web_search: Performs a web search using the Brave Search API.
  • brave_local_search: Searches for local businesses and places.

Development

  1. Modify the code in the src directory.
  2. Update the requirements.txt if you add or remove dependencies.
  3. Restart the server to apply changes.

Troubleshooting

  • Ensure the Brave API key is set correctly.
  • Check that all dependencies are installed.
  • Verify the Python version compatibility.
  • Restart the server after code changes.