Connect Claude to Google Gemini AI for multi-turn chat, research, and grounded responses. Developers can route queries through Gemini's models while maintaining Claude's context and reasoning.
io.github.houtini-ai/gemini
Local install
STDIO
1 required env var
How models use it and what it is built for.
Connect Claude to Google Gemini AI for multi-turn chat, research, and grounded responses. Developers can route queries through Gemini's models while maintaining Claude's context and reasoning.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Google AI Studio API key (get from https://aistudio.google.com/apikey)
Where to find authoritative docs and source for Houtini AI Gemini.
Paste any of these into Agent Studio after connecting Houtini AI Gemini.
Common questions about connecting and running Houtini AI Gemini.
What is the Gemini MCP server and why would I use it?
It's a Model Context Protocol bridge that lets you call Google Gemini AI models from Claude, enabling multi-turn conversations, research capabilities, and grounded responses. Use it when you want Gemini's strengths (like real-time grounding) available within Claude's reasoning context.
How do I set up authentication?
Get a free Google AI Studio API key from https://aistudio.google.com/apikey, then set the GEMINI_API_KEY environment variable before running the MCP server. The key is required to authenticate all requests to Gemini.
Is there a cost to use this server?
Google Gemini API has a free tier with rate limits. Check https://ai.google.dev/pricing for current pricing and quota details. Costs depend on your usage volume and which Gemini model you call.
Can I use this without a Google account?
No, you need a Google account to generate an API key from Google AI Studio. The key is tied to your Google Cloud project and billing account.
What happens if my GEMINI_API_KEY is invalid or expired?
The MCP server will fail to authenticate requests to Gemini and return an error. Verify your key is correct, hasn't been revoked, and that your Google Cloud project is active and has billing enabled.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams