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.
Похожие серверы
Jina AI MCP Tools
Integrates with Jina AI APIs for web reading, search, and fact-checking.
Google Maps MCP Server
Local business search and lead generation via Google Maps
Wikipedia Simple English MCP Server
Access Wikipedia content, prioritizing Simple English with a fallback to regular English.
DeepResearch
Lightning-Fast, High-Accuracy Deep Research Agent 👉 8–10x faster 👉 Greater depth & accuracy 👉 Unlimited parallel runs
Brave-Gemini Research MCP Server
Perform web searches with the Brave Search API and analyze research papers using Google's Gemini model.
Paper Search MCP
Search and download academic papers from sources like arXiv, PubMed, and Google Scholar.
AgentRank
Google for AI agents — live search across 25,000+ scored MCP servers, updated daily
Wolfram Alpha
Access the Wolfram Alpha API for computational knowledge and real-time data.
Tavily Search
A search API tailored for LLMs, providing web search, RAG context generation, and Q&A capabilities through the Tavily API.
Docs MCP Server
An MCP server that makes documentation and codebases searchable for AI assistants, supporting local directories and Git repositories.