Brave Search

Implements a Brave Search MCP Server with web and local search tools for MCP-enabled assistants.

python

1

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You can extend your AI assistant with Brave Search capabilities by running a Brave Search MCP Server that exposes web search and local search tools through the Model Context Protocol (MCP). This enables seamless querying of Brave Search results and local data within your AI workflows.

How to use

To use Brave Search with an MCP client, first ensure your Brave API key is available as an environment variable. Then start the Brave Search MCP Server via your MCP client using the stdio configuration shown in the setup snippet. Once the server is running, your MCP client can invoke the Brave Search tools to perform web searches and local searches as part of your assistant’s capabilities.

How to install

Prerequisites: Python 3.11 or newer and uv, a fast Python package installer and resolver.

Installing via Smithery can set up Brave Search MCP server for Claude Desktop automatically.

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

Manual installation steps are below. Follow these in sequence to run the server locally.

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

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

Set up your Brave Search API key in your environment.

export BRAVE_API_KEY=your_api_key_here  # On Windows, use: set BRAVE_API_KEY=your_api_key_here

Configuration snippet to include in your MCP client

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

Available tools

brave_web_search

Performs a web search using the Brave Search API and returns results suitable for display or further processing by the AI assistant.

brave_local_search

Searches local businesses and places using Brave Local search data and presents results to the assistant.