Nano Banana Pro

MCP server for Gemini 3 Nano Banana Pro image generation

typescript

13

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mrafaeldie12-nano-banana-pro-mcp": {
      "command": "npx",
      "args": [
        "@rafarafarafa/nano-banana-pro-mcp"
      ],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

You can run a self-contained MCP server that lets AI agents generate images using Google's Gemini image generation models, including Nano Banana Pro, by wiring it to Gemini through a simple CLI-based MCP. This server exposes image generation capabilities that you can invoke from your agents or automation workflows.

How to use

Use a client that supports MCP to connect to the Nano Banana Pro MCP Server. You will start a local process that runs the MCP and then direct your agent or automation to call the available tools. The main tool you’ll use is generate_image to create images from prompts, with optional reference images to guide the style or content.

How to install

Prerequisites you need on your machine before starting are Node.js and npm or npx available in your shell.

Install and run the MCP server using the standard local runtime shown in the configuration examples.

{
  "mcpServers": {
    "nano_banana_pro": {
      "command": "npx",
      "args": ["@rafarafarafa/nano-banana-pro-mcp"],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Additional notes

Set the Gemini API key in your environment as shown in the configuration snippet. Your key is required to access Gemini image generation models.

Configuration examples

{
  "mcpServers": {
    "nano_banana_pro": {
      "command": "npx",
      "args": ["@rafarafarafa/nano-banana-pro-mcp"],
      "env": {
        "GEMINI_API_KEY": "your_api_key_here"
      }
    }
  }
}

Security and keys

Keep your Gemini API key secret. Do not expose it in client code or publicly accessible configuration files. Use environment variables to load the key at runtime and restrict access to the MCP process.

Troubleshooting

If you cannot reach the Gemini API or generate images, verify that GEMINI_API_KEY is set correctly in the running MCP process environment and that your network allows outbound requests to Gemini endpoints.

Available tools

generate_image

Generate an image from a text prompt with optional reference images, model choice, aspect ratio, and output path. Supports prompts like creating a sunset over mountains or saving the result to a file.

edit_image

Edit existing images based on instructions, using a prompt and one or more input images. You can adjust models and output paths as needed.

describe_image

Analyze and describe one or more images in text form, optionally using a custom analysis prompt and choosing a Gemini model.