
Nano Banana Mcp
io.github.fjacquetv3.2.1Updated Oct 11, 2026
AI image generation and editing with Google Gemini: Nano Banana 2.1, Pro and Lite models
Overview
Lets an assistant generate and iteratively edit images through Google Gemini image models using a Gemini API key.
- What it does
- This local MCP server exposes tools for AI image work: generate_image creates new images from text prompts, edit_image modifies existing images with optional reference images, and continue_editing iteratively refines the last image. It also offers get_last_image_info, configure_gemini_token to set the API key, and get_configuration_status to check configuration. Generation and editing tools accept an optional model parameter to pick among several Gemini image models.
- When to use it
- Use it when you want an assistant to create or revise images from natural-language prompts inside an MCP client such as Claude Code or Cursor, including multi-step edits of the same image. It suits desktop workflows where image generation is part of the task rather than a separate app.
- Requirements
- Runs as a local process over stdio, so it needs Node.js 18 or newer and npx. A Gemini API key from Google AI Studio is required, supplied through the GEMINI_API_KEY environment variable or set later with the configure_gemini_token tool. Network access to Google's Gemini API is needed.
Installation
In SourceWeft
- Open Nano Banana Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
Nano-Banana MCP Server
[npm version] [CI] [License: MIT] [Node.js >= 18] [Release] [License]
An MCP server for AI image generation and editing using Google Gemini. Works with Claude Code, Cursor, and other MCP clients.
Models supported:
Quick Start
-
Get a Gemini API key from Google AI Studio
-
Add to your MCP client config (Claude Code example):
See docs/configuration.md for Cursor and other MCP clients.
- Use the tools:
Tools
All generation/editing tools accept an optional model parameter to choose between the two models.
See docs/tools.md for full API reference, docs/configuration.md for setup details, and docs/workflows.md for usage patterns.
Development
Requires Node.js >= 18.0.0.
License
MIT — see LICENSE.
Fork of ConechoAI/Nano-Banana-MCP.
Source: README.md at commit dd44598
Tools
0Version history
1- v3.2.1LatestOct 11, 2026


