Nano Banana (Gemini Image Generator) MCP server

MCP Nano Banana is a server that implements the Model Context Protocol, allowing compatible AI models to generate images using the Google Gemini API. It exposes a single tool named generate_image that accepts text prompts, generates images via Gemini, and returns the image data as a base64-encoded string.

Installation

Prerequisites

You'll need two API keys to use this server:

• Google Gemini API key
• ImgBB API key (get it from https://api.imgbb.com/)

Installing the Package

Install the MCP Nano Banana server using pip:

pip install mcp-nano-banana

Usage

Setting Up Environment Variables

There are two ways to provide the required API keys:

1. Using a .env file:

   Create a file named .env in your working directory with:

   GEMINI_API_KEY="YOUR_API_KEY_HERE"
   IMGBB_API_KEY="YOUR_API_KEY_HERE"
   

2. Setting environment variables directly when running the server.

Running the Server

You can run the server directly using the uvx command:

uvx mcp-nano-banana

Integrating with Claude Desktop or Other MCP Clients

To use MCP Nano Banana with Claude Desktop or other MCP-compatible applications, you need to add it to the client's MCP server configuration:

{
  "mcpServers": {
    "mcp-nano-banana": {
        "command": "uvx",
        "args": [
            "mcp-nano-banana"
        ],
        "env": {
            "GEMINI_API_KEY": "YOUR_API_KEY_HERE",
            "IMGBB_API_KEY": "YOUR_API_KEY_HERE"
        }
    }
  }
}

Alternative Installation Method

You can also install and run the server directly from GitHub:

uvx --from git+https://github.com/GuilhermeAumo/mcp-nano-banana mcp-nano-banana

How It Works

When a compatible AI model (like Claude) calls the generate_image tool with a text prompt:

1. The server sends the prompt to Google Gemini API
2. The generated image is saved to a public/ directory for auditing
3. The image is uploaded to ImgBB for hosting
4. The raw image data is returned as a base64-encoded string to the AI model

This allows the AI to generate and incorporate images into its responses based on user prompts.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "mcp-nano-banana" '{"command":"uvx","args":["mcp-nano-banana"],"env":{"GEMINI_API_KEY":"YOUR_API_KEY_HERE","IMGBB_API_KEY":"YOUR_API_KEY_HERE"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "mcp-nano-banana": {
            "command": "uvx",
            "args": [
                "mcp-nano-banana"
            ],
            "env": {
                "GEMINI_API_KEY": "YOUR_API_KEY_HERE",
                "IMGBB_API_KEY": "YOUR_API_KEY_HERE"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "mcp-nano-banana": {
            "command": "uvx",
            "args": [
                "mcp-nano-banana"
            ],
            "env": {
                "GEMINI_API_KEY": "YOUR_API_KEY_HERE",
                "IMGBB_API_KEY": "YOUR_API_KEY_HERE"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect