Nano Banana Pro MCP Server

An MCP (Model Context Protocol) server that brings Google Gemini 2.0 Flash native image generation capabilities directly into Claude Code and other MCP-compatible AI assistants.

Generate, edit, and compose images using natural language - all without leaving your coding environment.

Features

• Generate Images: Create high-quality images from text prompts (up to 4K resolution)

• Edit Images: Modify existing images with text instructions

• Continue Editing: Iteratively refine the last generated image

• Compose Images: Combine up to 14 reference images into new compositions

• Google Search Grounding: Generate images based on real-time information

• Multiple Aspect Ratios: Support for 1:1, 16:9, 9:16, 4:3, 3:4, and more

• High Resolution: Output at 1K, 2K, or 4K resolution

Prerequisites

• Docker Desktop installed and running

• Gemini API key from Google AI Studio

Quick Start

1. Build the Docker Image

2. Create Output Directory

3. Add to Claude Code

Add the MCP server to Claude Code using one of these methods:

Option A: Using claude mcp add (Recommended)

Option B: Manual Configuration

Add to your Claude Code MCP configuration file (~/.claude/claude_desktop_config.json or similar):

Available Tools

generate_image

Generate a new image from a text prompt.

Parameters:

• prompt (required): Text description of the image to create

• aspectRatio (optional): 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9

• resolution (optional): 1K, 2K, or 4K

• useGoogleSearch (optional): Enable real-time information grounding

Example:

edit_image

Edit an existing image with text instructions.

Parameters:

• imagePath (required): Path to the image file

• prompt (required): Description of the modifications

• referenceImages (optional): Array of reference image paths

• aspectRatio (optional): Output aspect ratio

• resolution (optional): Output resolution

Example:

continue_editing

Continue editing the last generated/edited image.

Parameters:

• prompt (required): Description of additional modifications

• referenceImages (optional): Reference images for style transfer, etc.

• aspectRatio (optional): Output aspect ratio

• resolution (optional): Output resolution

Example:

compose_images

Combine multiple images into a new composition.

Parameters:

• images (required): Array of image paths (up to 14)

• prompt (required): How to combine the images

• aspectRatio (optional): Output aspect ratio

• resolution (optional): Output resolution

Example:

get_last_image_info

Get information about the last generated image.

get_configuration_status

Check if the API key is configured.

Tips for Best Results

1. Be Descriptive: The more detail in your prompt, the better the result

2. Use Photography Terms: For realistic images, mention camera angles, lens types, lighting

3. Iterate: Use continue_editing to refine images step by step

4. Reference Images: Use up to 14 reference images for character consistency or style transfer

5. Google Search: Enable for real-time data like weather, news, or current events

Output Location

Generated images are saved to the /output directory (mounted from ./output on your host).

Troubleshooting

"GEMINI_API_KEY not set"

Make sure your API key is set in your environment:

Images not appearing

Check the ./output directory on your host machine. Ensure the volume mount is correct.

Docker permission issues

On Linux, you may need to run:

Development

To run locally without Docker:

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT

Acknowledgments

• Google Gemini for the image generation API

• Model Context Protocol by Anthropic

• Claude Code for the amazing AI coding assistant