Enables text-to-image generation, image editing, and multi-image composition using Google's Gemini AI image generation models (Nano Banana Pro and Nano Banana), with support for various aspect ratios, resolutions up to 4K, text rendering, and real-time Google Search grounding for current events and weather information.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Nano Banana MCP Servercreate a photorealistic sunset over mountains in 16:9 aspect ratio"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Nano Banana MCP Server
An MCP (Model Context Protocol) server for Google's Nano Banana Pro (Gemini 3 Pro Image) and Nano Banana (Gemini 2.5 Flash Image) AI image generation models.
Features
๐จ Text-to-Image Generation - Create images from natural language descriptions
โ๏ธ Image Editing - Modify existing images with text prompts
๐ผ๏ธ Multi-Image Composition - Combine up to 14 reference images
๐ Flexible Aspect Ratios - 10 aspect ratio options (1:1, 16:9, 9:16, etc.)
๐ High Resolution - Up to 4K output with Nano Banana Pro
๐ค Text Rendering - Generate images with accurate, legible text
๐ Google Search Grounding - Real-time information for current events/weather
Prerequisites
Node.js 18 or higher
Google AI API key from Google AI Studio
Installation
From Source
# Clone or download this directory
cd nanobanana-mcp-server
# Install dependencies
npm install
# Build the TypeScript
npm run buildConfiguration
Set your API key as an environment variable:
# Linux/macOS
export GEMINI_API_KEY="your-api-key-here"
# Windows (PowerShell)
$env:GEMINI_API_KEY="your-api-key-here"
# Windows (CMD)
set GEMINI_API_KEY=your-api-key-hereUsage
As stdio Server (for Claude Desktop, etc.)
npm startOr directly:
node dist/index.jsAs HTTP Server
TRANSPORT=http PORT=3000 npm startThe server will listen at http://localhost:3000/mcp.
Claude Desktop Configuration
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"nanobanana": {
"command": "node",
"args": ["/path/to/nanobanana-mcp-server/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your-api-key-here"
}
}
}
}Available Tools
nanobanana_generate_image
Generate images from text descriptions.
Parameters:
Name | Type | Required | Description |
| string | Yes | Text description of the image |
| string | No | Model ID (default: |
| string | No | Aspect ratio (e.g., |
| string | No | Resolution: |
| boolean | No | Enable real-time info grounding (Pro only) |
Example:
{
"prompt": "A photorealistic portrait of an astronaut on Mars at sunset, dramatic lighting, 85mm lens",
"model": "gemini-3-pro-image-preview",
"aspect_ratio": "16:9",
"resolution": "4K"
}nanobanana_edit_image
Edit an existing image using text prompts.
Parameters:
Name | Type | Required | Description |
| string | Yes | Description of the edit |
| string | Yes | Base64-encoded image data |
| string | Yes | MIME type (e.g., |
| string | No | Model ID |
| string | No | Output aspect ratio |
| string | No | Output resolution (Pro only) |
Example:
{
"prompt": "Add a wizard hat to the cat",
"image_base64": "<base64-image-data>",
"image_mime_type": "image/png"
}nanobanana_compose_images
Compose images using multiple reference images (Nano Banana Pro only).
Parameters:
Name | Type | Required | Description |
| string | Yes | Description of composition |
| array | Yes | Array of |
| string | No | Output aspect ratio |
| string | No | Output resolution |
Example:
{
"prompt": "Create a group photo of these 5 people at a beach party",
"images": [
{"base64": "<image1>", "mime_type": "image/jpeg"},
{"base64": "<image2>", "mime_type": "image/jpeg"}
],
"aspect_ratio": "16:9",
"resolution": "2K"
}nanobanana_list_models
List available models and their capabilities.
Parameters:
Name | Type | Required | Description |
| string | No |
|
Models
Nano Banana Pro (gemini-3-pro-image-preview)
Google's most advanced image generation model. Best for:
Professional asset production
Images with accurate text rendering
Complex compositions
High-resolution output (up to 4K)
Real-time information grounding
Nano Banana (gemini-2.5-flash-image)
Fast, low-latency image generation. Best for:
Quick experimentation
Batch processing
Iterative design
Cost-effective generation
Aspect Ratios
Ratio | Use Case |
| Square, social media posts |
| Landscape, presentations, YouTube thumbnails |
| Portrait, mobile screens, Stories |
| Classic photo format |
| DSLR photo format |
| Ultra-wide, cinematic |
Tips for Best Results
Prompting
Be Descriptive: Include details about style, lighting, composition, colors, and mood
Use Photography Terms: For photorealistic images, mention camera angles, lens types, lighting setups
Specify Style: "Oil painting", "3D render", "watercolor", "photorealistic", etc.
Include Context: Describe the environment, atmosphere, and mood
Example Prompts
Photorealistic:
A photorealistic close-up portrait of an elderly Japanese ceramicist with
deep wrinkles and a warm smile, inspecting a glazed tea bowl. Soft golden
hour light from a window. Shot with 85mm portrait lens, bokeh background.Stylized:
A kawaii-style sticker of a happy red panda wearing a bamboo hat, munching
on a leaf. Bold outlines, cel-shading, vibrant colors. White background.Logo:
Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'.
Clean, bold sans-serif font. Black and white. Circular design with a clever
coffee bean element.Error Handling
Common errors and solutions:
Error | Solution |
"GEMINI_API_KEY is required" | Set the environment variable |
Rate limit exceeded | Wait and retry, or reduce request frequency |
Content policy violation | Modify prompt to comply with Google's policies |
Invalid image format | Use supported formats: PNG, JPEG, GIF, WebP |
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Watch mode for development
npm run devLicense
MIT
Links
Google AI Studio - Get your API key
Gemini API Docs - Official documentation
MCP Protocol - Learn about MCP