KOF Nano Banana

Generates Gemini-based images from prompts and processes prompt queues with validation and YAML frontmatter support.

javascript

0

GitHub Stars

javascript

Language

4 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": {
    "keeponfirst-kof-nanobanana-mcp": {
      "command": "node",
      "args": [
        "/path/to/kof-nanobanana-mcp/dist/index.js"
      ],
      "env": {
        "GEMINI_API_KEY": "your-api-key-here"
      }
    }
  }
}

You can run the KOF Nano Banana MCP Server to generate Gemini-powered images from prompts, manage a prompt queue with validation and dry-run support, and configure per-prompt settings via YAML frontmatter. This server is designed to work with any MCP-enabled client and is useful when you want automated image generation as part of your workflow.

How to use

To use this MCP server, you run it as an MCP endpoint and connect a client that supports MCP. You can start by either running the server via npx for a quick setup or running it locally from source for development. The server exposes image generation capabilities using Gemini models and supports processing a queue of prompt files with validation and dry-run options.

How to install

Prerequisites: you need Node.js installed on your machine. Ensure you have npm or npx available in your shell.

Option 1: Use via npx (Recommended) If you want a quick start without building locally, configure your MCP config to use npx and the nanobanana MCP package.

{
  "mcpServers": {
    "nanobanana": {
      "command": "npx",
      "args": ["-y", "@keeponfirst/kof-nanobanana-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key-here"
      }
    }
  }
}

Option 2: Local Development If you prefer to build and run from source, follow these steps to set up the project locally and run the MCP server.

cd kof-nanobanana-mcp
npm install
npm run build

Additional configuration and usage details

The server requires a Gemini API key with billing enabled to access the Gemini image generation models. You should obtain this key from your Google Cloud project and provide it to the MCP server in the environment.

You configure the MCP to point at the local runtime by specifying the node command and the path to the built index. This enables the MCP client to start the server locally and pass prompts for image generation.

Available tools

nanobanana_generate_image

Generate a single image using a specified prompt, output path, and model. Supports optional aspect ratio and overwrite controls.

nanobanana_list_queue

List and validate prompt files in the queue with optional validation and conflict checks.

nanobanana_process_queue

Batch process all prompt files in the queue with options to validate, dry-run, and control overwriting behavior.