Brave Search
A server for Brave Search, enabling integration with AI assistants like Claude.
Brave Search MCP Server
This project implements a Model Context Protocol (MCP) server for Brave Search, allowing integration with AI assistants like Claude.
Prerequisites
- Python 3.11+
- uv - A fast Python package installer and resolver
Installation
Installing via Smithery
To install Brave Search MCP server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @arben-adm/brave-mcp-search --client claude
Manual Installation
-
Clone the repository:
git clone https://github.com/your-username/brave-search-mcp.git cd brave-search-mcp -
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:
export BRAVE_API_KEY=your_api_key_hereOn Windows, use:
set BRAVE_API_KEY=your_api_key_here
Usage
-
Configure your 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_HEREwith your actual Brave API key. -
Start the Brave Search MCP server by running your MCP-compatible AI assistant with the updated configuration.
-
The server will now be running and ready to accept requests from MCP clients.
-
You can now use the Brave Search functionality in your MCP-compatible AI assistant (like Claude) by invoking the available tools.
Available Tools
The server provides two main tools:
brave_web_search: Performs a web search using the Brave Search API.brave_local_search: Searches for local businesses and places.
Refer to the tool docstrings in src/server.py for detailed usage information.
Development
To make changes to the project:
- Modify the code in the
srcdirectory as needed. - Update the
requirements.txtfile if you add or remove dependencies:uv pip freeze > requirements.txt - Restart the server to apply changes.
Troubleshooting
If you encounter any issues:
- Ensure your Brave API key is correctly set.
- Check that all dependencies are installed.
- Verify that you're using a compatible Python version.
- 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.
เซิร์ฟเวอร์ที่เกี่ยวข้อง
Google Search
An MCP (Model Context Protocol) server that gives AI assistants real-time news fetching, search, NLP analysis, and personalized news preferences — all accessible through natural language.
Obsidian Omnisearch
Search your Obsidian vault using the Omnisearch plugin via a REST API.
Unified Docs Hub
Creates a massive, searchable knowledge base from numerous curated and auto-discovered GitHub projects.
TranscriptAPI YouTube Skills
Get YouTube transcripts, search videos, browse channels, and extract playlists from any AI agent — powered by TranscriptAPI.com with no API key required.
Tavily
Search engine for AI agents (search + extract) powered by Tavily
News Fact-Checker
Automated fact-checking of news headlines using web search and Google Gemini AI.
MCP-WebSearch-SearXNG
Lets your model (or autonomous agent) browse the web, run searches across many engines at once, and surface images directly in your front end.
Readeck MCP
An MCP server for advanced research assistance, configurable via environment variables.
MCP-MCP
A meta-server for discovering and provisioning other MCP servers from a large database.
AgentBridge
A specialized gateway for AI agents to fetch and parse Chinese web content into clean Markdown. Pay-per-fetch via x402.