Gemini

概要

This Model Context Protocol (MCP) server provides a robust interface for interacting with Google's state-of-the-art AI models, including Gemini 2.5 Flash Image Preview, Imagen 4.0, and Veo 3.0. It empowers users and client applications to perform a wide range of multimodal AI tasks, from generating high-quality images and creating cinematic videos from text or images to advanced image editing and multi-image composition, all through a standardized protocol. Developers can seamlessly integrate cutting-edge Google AI functionalities into their projects.

主な機能

• Advanced image editing and multi-image composition capabilities
• Cinematic video generation from text or images using Google's Veo 3.0 models
• 1 GitHub stars
• Comprehensive support for various Gemini, Imagen, and Veo AI models
• Robust MCP protocol features including Stdio transport, detailed tool descriptions, and file output management
• High-quality image generation with Gemini 2.5 Flash Image Preview and Imagen 4.0 models

ユースケース

• Generating and editing images for creative projects or content creation workflows
• Creating videos from text prompts or animating static images for dynamic content
• Integrating Google's multimodal AI capabilities into MCP-compatible applications