Back to Directory/Media & Images

io.github.fjacquet/nano-banana-mcp

AI image generation and editing with Google Gemini: Nano Banana 2.1, Pro and Lite models

Media & ImagesTypeScriptv3.2.1

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:

Brand nameModel IDNotes
Nano Banana 2.1gemini-nano-banana-2.1Default — pro quality at Flash speed
Nano Banana Progemini-3-pro-imageHighest quality, advanced reasoning
Nano Banana 2gemini-3.1-flash-imagePrevious default
Nano Banana 2 Litegemini-3.1-flash-lite-imageFastest and cheapest — 1K output only
Nano Bananagemini-2.5-flash-imageLegacy — shut down by Google on 2027-03-15

Quick Start

  1. Get a Gemini API key from Google AI Studio

  2. Add to your MCP client config (Claude Code example):

{
  "mcpServers": {
    "nano-banana": {
      "command": "npx",
      "args": ["-y", "github:fjacquet/Nano-Banana-MCP"],
      "env": {
        "GEMINI_API_KEY": "your-key-here"
      }
    }
  }
}

See docs/configuration.md for Cursor and other MCP clients.

  1. Use the tools:
Generate an image of a sunset over mountains
Edit this image to add some birds in the sky
Continue editing to make it more dramatic

Tools

ToolDescription
generate_imageCreate new images from text prompts
edit_imageModify existing images with optional reference images
continue_editingIteratively edit the last image
get_last_image_infoGet info about the last image
configure_gemini_tokenSet API key
get_configuration_statusCheck configuration

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

npm install
npm run dev          # Run with tsx
npm run build        # Compile TypeScript
npm test             # Run tests
npm run lint         # Lint
npm run typecheck    # Type-check

Requires Node.js >= 18.0.0.

License

MIT — see LICENSE.

Fork of ConechoAI/Nano-Banana-MCP.

Installation

Source-derived launch command. Check the maintainer’s required arguments and credentials before running:

bash
npx -y @fjacquet/nano-banana-mcp

Set up in your AI client

Merge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.

json
{
  "mcpServers": {
    "io-github-fjacquet-nano-banana-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@fjacquet/nano-banana-mcp"
      ]
    }
  }
}

Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.

Claude Desktop setup reference

Package

@fjacquet/nano-banana-mcpnpm

Compatible MCP Clients

io.github.fjacquet/nano-banana-mcp works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.

  • Claude Desktop~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.
  • Cursor~/.cursor/mcp.jsonRestart Cursor for changes to take effect.
  • VS Code.vscode/mcp.jsonReload VS Code window for changes to take effect.
  • Windsurf~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect.
  • Claude Code.mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.

Learn More