Overview
What is Brave-Gemini Research MCP Server?
A Model Context Protocol server that provides AI assistants with web search capabilities via the Brave Search API and advanced research paper analysis using Google's Gemini model. It is designed for integration with AI assistants like Claude Desktop.
How to use Brave-Gemini Research MCP Server?
Install Node.js v18+, clone the repository, run npm install, create a .env file with BRAVE_API_KEY and GOOGLE_API_KEY, build with npm run build, and start the server with node dist/index.js. Optionally, configure Claude Desktop by adding the server to claude_desktop_config.json with correct paths and timeout settings.
Key features of Brave-Gemini Research MCP Server
- Web search via Brave Search API
- Local search for businesses and places
- Research paper analysis using Gemini AI
- Seamless integration with Claude Desktop
- Extensible design for adding new tools
Use cases of Brave-Gemini Research MCP Server
- Search the web for the latest AI research papers
- Find coffee shops in San Francisco
- Analyze a research paper on quantum computing with Gemini
FAQ from Brave-Gemini Research MCP Server
What API keys are required?
You need a Brave Search API key and a Google API key for Gemini integration. Both are set as environment variables BRAVE_API_KEY and GOOGLE_API_KEY.
How to fix timeout errors when using Claude Desktop?
Increase the timeoutMs in the Claude Desktop configuration (120000 ms recommended) and verify environment variables are correctly set.
What analysis types are available for research papers?
Summary, critique, literature review, key findings, and comprehensive (default). The analysisType parameter lets you choose.
How to debug the server?
Run with DEBUG=mcp:* NODE_ENV=development node dist/index.js for detailed debug output.
What are common Windows-specific issues?
Use PowerShell for environment variables, use double backslashes in JSON paths, and consider absolute paths if relative paths fail.
