Nano-Banana (Gemini 2.5 Flash Image)

Integrates with Google's Gemini 2.5 Flash to generate and edit images from text prompts, supporting iterative workflows with reference images and automatic cross-platform file management.

This MCP server provides access to Google's Gemini 2.5 Flash Image generation and editing capabilities through a TypeScript implementation that supports both creating new images from text prompts and editing existing images with optional reference images. Built with cross-platform support, it handles configuration through environment variables or local config files, automatically manages image saving to platform-appropriate directories (Documents on Windows, current directory on macOS/Linux), and includes session-based image tracking for iterative editing workflows. The implementation offers six core tools including token configuration, image generation, image editing with multi-image support, continuation editing for the last generated image, and status checking, making it suitable for AI assistants that need to create and iteratively refine visual content using Google's latest image generation technology.