Home / MCP / Brave Search MCP Server

Brave Search MCP Server

Provides an MCP server that exposes Brave Search web and local search capabilities for integration with AI assistants.

python

14stars

View on GitHub

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
    "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"
            }
        }
    }
}

You can run a Brave Search MCP Server that exposes Brave Search capabilities to MCP clients and AI assistants. This server enables web and local search tools to be used by your assistant, so you can perform web research and find local information through your AI workflows.

How to use

To use the Brave Search MCP Server with an MCP-compatible AI assistant, start the server according to your environment and point your assistant to the configured MCP server. Once running, your assistant can invoke the Brave Search tools to perform web searches or local searches, delivering results as part of your conversation. You don’t need to manage the low-level RPC details; simply ensure the server is running and your assistant is configured to connect to the Brave Search MCP endpoint.

How to install

Prerequisites you need before installation:

- Python 3.11+

- uvx (the Python package installer and resolver)

How to install

Installing via Smithery

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

How to install

Manual Installation

1. Clone the repository:

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

How to install

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

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

How to install

3. Set up your Brave Search API key:

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

How to use

Configure your MCP settings file to include the Brave Search MCP server. Use the following example to define the server that your assistant will connect to.

{
  "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"
      }
    }
  }
}

How to use

Replace YOUR_BRAVE_API_KEY_HERE with your actual Brave API key. Start your MCP-compatible AI assistant with this updated configuration to connect to the Brave Search MCP Server.

How to use

Start the Brave Search MCP server by running your MCP-compatible AI assistant with the updated configuration. The server will be ready to accept requests from MCP clients and provide Brave Search tools.

How to use

You can now use the Brave Search functionality in your MCP-compatible AI assistant by invoking the available tools.

Available tools

brave_web_search

Performs a web search using the Brave Search API and returns results suitable for presentation in your assistant.

brave_local_search

Searches for local businesses and places using Brave Search local data and returns relevant results for your conversations.