Nano-Banana
Enables image generation and editing using Google's Gemini models with support for model selection and custom aspect ratios. Users can generate high-quality images or modify existing ones through natural language prompts while controlling specific pa
What is Nano-Banana?
Nano-Banana is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables image generation and editing using google's gemini models with support for model selection and custom aspect ratios. users can generate high-quality images or modify existing ones through natu...
Enables image generation and editing using Google's Gemini models with support for model selection and custom aspect ratios. Users can generate high-quality images or modify existing ones through natural language prompts while controlling specific pa
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables image generation and editing using Google's Gemini m
Use Cases
Maintainer
Works with
Installation
NPM
npx -y nano-banana-mcpManual Installation
npx -y nano-banana-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Nano-Banana
Nano-Banana MCP brings Google Gemini's image generation and editing capabilities into any MCP-compatible AI assistant. It supports generating images from text descriptions, editing existing images with natural language prompts, continuing refinements on previously generated images, and switching between different Gemini model versions. Users working with Claude Code, Cursor, or other AI coding tools can generate design assets, mockups, or illustrations without leaving their workflow.
Prerequisites
- Node.js 18.0.0+ installed
- A Google Gemini API key — obtain one free from https://aistudio.google.com/app/apikey
- An MCP-compatible client such as Claude Desktop, Claude Code, or Cursor
Obtain a Google Gemini API key
Visit https://aistudio.google.com/app/apikey, sign in with a Google account, and create a new API key. Copy it — you will paste it into the MCP configuration.
Configure your MCP client
Add the Nano-Banana server to your MCP client config. The server is run via npx so no separate install is needed.
Verify the API key is recognized
After restarting your MCP client, ask it to check the configuration status. The server exposes a `get_configuration_status` tool for this purpose.
Generate your first image
Use the `generate_image` tool through your AI client with a text description. Generated images are saved locally and their path is returned.
Nano-Banana Examples
Client configuration
MCP configuration for Claude Desktop or Claude Code with the Gemini API key set as an environment variable.
{
"mcpServers": {
"nano-banana": {
"command": "npx",
"args": ["-y", "nano-banana-mcp"],
"env": {
"GEMINI_API_KEY": "YOUR_GEMINI_API_KEY_HERE"
}
}
}
}Prompts to try
Example prompts for image generation and editing with Nano-Banana MCP.
- "Generate an image of a futuristic cityscape at sunset with flying cars"
- "Edit the last image to add a crescent moon and stars to the sky"
- "Continue editing the image but make it look like a watercolor painting"
- "Generate a 16:9 product mockup of a minimalist phone app on a white background"
- "What is the status of my Gemini API configuration?"Troubleshooting Nano-Banana
Image generation fails with 'API key not valid' or authentication error
Double-check that GEMINI_API_KEY is set correctly in your MCP config env block. Make sure there are no extra spaces or quotes around the key. You can also use the `configure_gemini_token` tool to set the key at runtime.
The `edit_image` tool returns an error about missing image data
You must first generate or load an image before editing. Use `generate_image` first, then call `edit_image` with your modifications. Use `get_last_image_info` to confirm an image is loaded.
npx command hangs on first run
The first run downloads the package from npm. If it hangs, check your internet connection and npm registry access. Try running `npx -y nano-banana-mcp --version` in your terminal to force the download separately.
Frequently Asked Questions about Nano-Banana
What is Nano-Banana?
Nano-Banana is a Model Context Protocol (MCP) server that enables image generation and editing using google's gemini models with support for model selection and custom aspect ratios. users can generate high-quality images or modify existing ones through natural language prompts while controlling specific pa It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Nano-Banana?
Install via npm with the command: npx -y nano-banana-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Nano-Banana?
Nano-Banana works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Nano-Banana free to use?
Yes, Nano-Banana is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Nano-Banana Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Nano-Banana? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Nano-Banana in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Nano-Banana?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.