MCP Server Gemini

A Model Context Protocol (MCP) server for integrating Google's Gemini 3 models with Claude Code, enabling powerful collaboration between both AI systems. Now with a beautiful CLI!

MCP Registry Support: Now discoverable in the official MCP ecosystem!

Features

| Feature | Description | |-------------------------------|-----------------------------------------------------------------| | Deep Research Agent | Autonomous multi-step research with web search and citations | | Token Counting | Count tokens and estimate costs before API calls | | Text-to-Speech | 30 unique voices, single speaker or two-speaker dialogues | | URL Analysis | Analyze, compare, and extract data from web pages | | Context Caching | Cache large documents for efficient repeated queries | | YouTube Analysis | Analyze videos by URL with timestamp clipping | | Document Analysis | PDFs, DOCX, spreadsheets with table extraction | | 4K Image Generation | Generate images up to 4K with 10 aspect ratios | | Multi-Turn Image Editing | Iteratively refine images through conversation | | Video Generation | Create videos with Veo 2.0 (async with polling) | | | Gemini writes and runs Python code (pandas, numpy, matplotlib) | | | Real-time web information with inline citations | | | JSON responses with schema validation | | | Extract entities, facts, sentiment from text | | | Control reasoning depth (minimal/low/medium/high) | | | Send prompts to Gemini 3 Pro/Flash models | | | Claude + Gemini collaborative problem-solving | | | Analyze code for quality, security, performance | | | Summarize content at different detail levels |