Nano-Banana
Wraps Google's Gemini 2.5 Flash Image API to bring AI image generation directly into your MCP-enabled editor. Exposes six operations: generate images from text prompts, edit existing images, continue editing your last creation, check configuration status, set up your API key, and retrieve info about recent generations. Works with Claude Desktop, Cursor, and other MCP clients through simple npx installation. Images auto-save to platform-specific directories with timestamp naming. Useful when you need to generate mockups, create assets, or iterate on visual concepts without leaving your coding environment.
- GitHub stars
- 191
- tools
- 6
- last updated
- Feb 14, 2026
Tools
6 toolsPublic tool metadata for what this MCP can expose to an agent.
generate_imageCreate a new image from a text prompt.
Create a new image from a text prompt.
No parameter schema in public metadata yet.
edit_imageEdit a specific image file.
Edit a specific image file.
No parameter schema in public metadata yet.
continue_editingContinue editing the last generated/edited image.
Continue editing the last generated/edited image.
No parameter schema in public metadata yet.
get_last_image_infoGet information about the last generated image.
Get information about the last generated image.
No parameter schema in public metadata yet.
configure_gemini_tokenConfigure your Gemini API key.
Configure your Gemini API key.
No parameter schema in public metadata yet.
get_configuration_statusCheck if the API key is configured.
Check if the API key is configured.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Nano-Banana MCP Server 🍌
🤖 This project was entirely generated by Claude Code - an AI coding assistant that can create complete, production-ready applications from scratch.
A Model Context Protocol (MCP) server that provides AI image generation and editing capabilities using Google's Gemini 2.5 Flash Image API. Generate stunning images, edit existing ones, and iterate on your creations with simple text prompts.
✨ Features
- 🎨 Generate Images: Create new images from text descriptions
- ✏️ Edit Images: Modify existing images with text prompts
- 🔄 Iterative Editing: Continue editing the last generated/edited image
- 🖼️ Multiple Reference Images: Use reference images for style transfer and guidance
- 🌍 Cross-Platform: Smart file paths for Windows, macOS, and Linux
- 🔧 Easy Setup: Simple configuration with API key
- 📁 Auto File Management: Automatic image saving with organized naming
🔑 Setup
Details
- Repository
- github.com/conechoai/nano-banana-mcp