Enables AI agents to generate, edit, and describe images using Google's Gemini models through an MCP server.
Acerca de
This tool functions as an MCP server, allowing various AI agents such as Claude to seamlessly interact with Google's Gemini image generation and analysis models, including the advanced Nano Banana Pro (gemini-3-pro-image-preview). It streamlines the process of integrating powerful image capabilities into AI workflows, providing a unified interface for generating new images, modifying existing ones, or extracting detailed descriptions directly within agent environments.
Características Principales
Edit one or more images based on detailed instructions.
Describe and analyze images to extract textual descriptions or specific information.
Support for multiple Gemini models, including Nano Banana Pro for high quality and Nano Banana for speed.
Easy integration with Claude Code CLI, Claude Desktop, Codex CLI, and Gemini CLI.
Generate images from text prompts with customizable models, aspect ratios, and sizes.
3 GitHub stars
Casos de Uso
Automate image manipulation tasks like adding elements or background removal.
Programmatically analyze and describe visual content for accessibility or data processing.
Generate hero images or creative assets for marketing and web development.
