🎨 Nano Banana MCP Server

A powerful Model Context Protocol (MCP) server for advanced image generation, editing, and analysis using Google's Gemini 2.5 Flash Image Preview (aka "nano-banana") and Gemini 3 Pro Image Preview (aka "nano-banana pro") models.

English | 日本語

✨ Features

Core Capabilities

• 🖼️ Image Generation - Create images from text prompts with advanced customization

• ✏️ Image Editing - Edit existing images using natural language (supports file paths or base64)

• 🔍 Image Analysis - Analyze and answer questions about images using Gemini

• 🎭 Multi-Image Processing - Combine, style transfer, or edit multiple images at once

• 📦 Batch Generation - Generate multiple images from an array of prompts

• 🎨 Style Templates - Use pre-defined templates for consistent styling

• 🔄 Variations - Generate variations of existing images with controlled randomness

• 🔬 Image Comparison - Compare and analyze differences between images

Advanced Features

• Dual Model Support - Choose between Gemini 2.5 Flash Image Preview or Gemini 3 Pro Image Preview

• High Resolution Output - Generate up to 4K images (4096x4096) with Gemini 3 Pro

• Generation Control - Fine-tune with temperature, topP, topK parameters

• Parallel Processing - Batch operations with optional parallel execution

• Smart Templates - 10+ professional style presets

• Flexible Input - Accept both file paths and base64 encoded images

• Auto-save - Automatically saves generated images with timestamps

Model Comparison

Supported Aspect Ratios: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9

Related MCP server: Nano Banana MCP Server

🚀 Quick Start

Prerequisites

• Node.js 18.0.0 or higher

• Valid Gemini API key

• MCP-compatible client (like Claude Code)

Installation

1. Clone the repository:

git clone https://github.com/Riti0208/nano-banana-mcp.git
cd nano-banana-mcp

2. Install dependencies:

npm install

3. Build the project:

npm run build

Configuration

Add to your Claude Code MCP settings (claude_code_config.json):

{
  "mcpServers": {
    "nano-banana": {
      "command": "node",
      "args": ["./dist/index.js"],
      "cwd": "/path/to/nano-banana-mcp",
      "env": {
        "GEMINI_API_KEY": "your-api-key-here"
      }
    }
  }
}

📖 Usage Examples

Generate an Image (Standard)

generate_image({
  prompt: "A serene mountain landscape at sunset",
  config: {
    temperature: 0.8,
    topP: 0.95
  }
})

Generate a High-Resolution Image (4K with Gemini 3 Pro)

generate_image({
  prompt: "Ultra detailed cyberpunk city at night with neon signs",
  model: "gemini-3-pro-image-preview",
  resolution: "4K",
  aspectRatio: "16:9",
  config: {
    temperature: 0.9
  }
})

Edit an Image

edit_image({
  prompt: "Add a rainbow in the sky",
  imagePath: "./landscape.jpg",
  model: "gemini-3-pro-image-preview",
  resolution: "2K",
  aspectRatio: "4:3",
  config: {
    temperature: 0.5
  }
})

Generate Multiple Variations

generate_variations({
  imagePath: "./original.png",
  count: 3,
  variationStrength: "moderate"
})

Batch Generation

batch_generate({
  prompts: [
    "A red apple",
    "A green apple",
    "A golden apple"
  ],
  parallel: true
})

Use Style Templates

generate_with_template({
  template: "photorealistic",
  customization: "A vintage coffee shop interior"
})

Compare Images

compare_images({
  image1Path: "./before.png",
  image2Path: "./after.png",
  compareType: "differences"
})

🛠️ Available Tools

🎨 Style Templates

• photorealistic - Ultra-realistic photography

• artistic - Artistic interpretation

• logo - Clean logo design

• portrait - Professional portraits

• landscape - Breathtaking landscapes

• product - Product photography

• architectural - Architectural photography

• fashion - Fashion photography

• food - Food photography

• abstract - Abstract art

⚙️ Configuration Parameters

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Google Gemini team for the amazing image generation API

• Model Context Protocol team for the MCP framework

• All contributors who help improve this project

🔗 Links

• Gemini API Documentation

• Model Context Protocol

• Report Issues