Gemini

소개

This tool functions as an MCP (Model Context Protocol) server, providing seamless access to Google's Gemini API. It acts as a drop-in alternative to other MCP servers, offering a consistent interface for leveraging advanced Google AI capabilities. Users can initiate and manage multi-turn AI conversations, generate high-quality images using Nano Banana (with auto-detection for advanced models), and create videos with Veo 3.1, complete with asynchronous status checking and custom first-frame options.

주요 기능

• Start and continue multi-turn Gemini conversations with configurable context
• Generate images using Google's Nano Banana models with automatic Pro model detection
• Initiate and monitor asynchronous video generation via Veo 3.1
• Configure API key and model overrides via environment variables
• Integrates as a standard MCP server for use with tools like Claude Code
• 3 GitHub stars

사용 사례

• Facilitating complex, multi-turn AI conversations within an MCP-enabled environment.
• Programmatically generating diverse content, including text, images, and videos, for applications and services.
• Integrating Google Gemini's advanced AI capabilities into automated development workflows and tools.