
Gemini MCP
by houtini-ai
Integrate Google Gemini 3 models with Claude Code for image/video generation, deep research, and code execution.
What it does
This MCP server enables Claude Code to leverage the full power of Google's Gemini 3 models. It bridges the gap between Claude's reasoning and Gemini's multi-modal capabilities, allowing for high-resolution image generation, video creation, and advanced web research directly within the developer workflow.
Tools
gemini-query: Direct prompts to Gemini with adjustable reasoning depth (thinking levels).gemini-generate-image: Creates high-res images (up to 4K) with various aspect ratios.gemini-generate-video: Async video generation using Veo.gemini-search: Real-time web search with grounded citations.gemini-run-code: Executes Python code (numpy, pandas, matplotlib) via Gemini.gemini-deep-research: Autonomous multi-step research agent.gemini-youtube: Analyzes YouTube videos by URL with timestamp clipping.gemini-analyze-document: Processes PDFs and documents with table extraction.
Installation
Add the following to your Claude Desktop config or use the CLI command:
{
"mcpServers": {
"gemini": {
"command": "npx",
"args": ["-y", "@rlabs-inc/gemini-mcp"],
"env": {
"GEMINI_API_KEY": "YOUR_KEY"
}
}
}
}
Supported hosts
- Claude Desktop
- Claude Code
Quick install
claude mcp add gemini -s user -- env GEMINI_API_KEY=YOUR_KEY npx -y @rlabs-inc/gemini-mcpInformation
- Pricing
- free
- Published






