Frequently Asked Questions about Brave Search MCP Server

Q: What is an MCP Server? A: MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It standardizes how applications provide context to LLMs.

Q: What is the Brave Search MCP Server? A: It’s an implementation that lets AI assistants like Claude use Brave Search for web and local searches.

Q: What is UBOS? A: UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. It helps orchestrate AI Agents, connect them with enterprise data, and build custom AI Agents.

Q: What are the prerequisites for installing the Brave Search MCP Server? A: You need Python 3.11+ and uv (a fast Python package installer).

Q: How do I install the Brave Search MCP server? A: You can install it automatically via Smithery or manually by cloning the repository, creating a virtual environment, and installing dependencies.

Q: How do I set up my Brave Search API key? A: Set the BRAVE_API_KEY environment variable with your API key.

Q: How do I configure my MCP settings file? A: Include the Brave Search MCP server configuration in your MCP settings file (e.g., claude_desktop_config.json). Make sure to specify path to server.py file.

Q: What tools are available in the Brave Search MCP server? A: The server provides brave_web_search for web searches and brave_local_search for local business searches.

Q: How do I run unit tests? A: Use the command python -m pytest tests/unit/.

Q: How do I run integration tests? A: Set the BRAVE_API_KEY_INTEGRATION environment variable and use the command python -m pytest tests/integration/ -v.

Q: What do I do if I encounter issues? A: Ensure your Brave API key is correctly set, all dependencies are installed, and you’re using a compatible Python version. Also, restart the server after code changes.