Nano Banana MCP
Provides tools for image generation and editing using Google's Gemini models via Google AI Studio, supporting various model selections and customizable aspect ratios.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Nano Banana MCP (Local Fork)
Fork of nano-banana-mcp with model selection and aspect ratio support.
Changes from upstream
Model selection: Choose between
flash(fast/cheap) andpro(slower/better) via env var or per-request parameterAspect ratio: Pass
aspectRatiotogenerate_image(1:1, 16:9, 9:16, 3:2, 4:3, 21:9, etc.)Accurate model labeling: Status output shows actual model name instead of incorrect "Gemini 2.5 Flash"
Models
Quality | Model ID | Speed | Cost |
|
| Fast | ~$0.04-0.05/image |
|
| Slower | ~$0.13-0.24/image |
Configuration
{
"nano-banana": {
"type": "stdio",
"command": "node",
"args": ["/path/to/nano-banana-mcp-local/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your-key-here",
"NANO_BANANA_MODEL": "flash"
}
}
}Environment Variables
Variable | Values | Default | Description |
| API key string | required | Your Google AI Studio API key |
|
|
| Default model for all requests |
Usage
generate_image
generate_image({
prompt: "A dramatic photo of...",
quality: "pro", // optional, overrides env default
aspectRatio: "16:9" // optional, default 1:1
})edit_image / continue_editing
Same as upstream, plus optional quality parameter.
License
MIT (same as upstream)
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Generate and edit images (PNG, transparent, GIF, SVG) with GPT Image and Nano Banana models.
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Image generation, image editing and text/image-to-video with credit quotes and connection budgets.
Create images and videos from prompts, with options for image mixing, reference images, and start/…