Brave-Gemini Research MCP Server
@falahgs
About Brave-Gemini Research MCP Server
No overview available yet
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Brave-Gemini-Research-MCP-Server": {
"command": "npx",
"args": [
"tsc"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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.
More AI & Agents MCP servers
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
meGPT - upload an author's content into an LLM
adriancoCode to process many kinds of content by an author into an MCP server
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
Sequential Thinking Multi-Agent System (MAS)
FradSerAn advanced sequential thinking process using a Multi-Agent System (MAS) built with the Agno framework and served via MCP.
Comments