Flux Image Generator

🚀 FLUX Image Generator MCP Server

An MCP (Model Context Protocol) server for generating images using the FLUX model from Black Forest Lab. It uses the latest MCP SDK (v1.7.0).

🚀 Quick Start

The FLUX Image Generator MCP Server is designed to generate images based on text prompts using the FLUX model. It offers a range of customizable settings and can be easily integrated with MCP clients.

✨ Features

• Generate images based on text prompts.
• Customize image dimensions, prompt upsampling, and safety settings.
• Save generated images locally.
• Generate multiple images from a batch of prompts.

📦 Installation

From Source

1. Clone this repository.
2. Install dependencies:

npm install

3. Create a .env file based on .env.example and add your Black Forest Lab API key:

BFL_API_KEY=your_api_key_here

4. Build the project:

npm run build

Using npm

npm install -g @modelcontextprotocol/server-flux-image-generator

💻 Usage Examples

Starting the MCP Server

Start the server using the following command:

npm start

For automatic recompilation during development:

npm run watch

Integrating with an MCP Client

To use this server with an MCP client (e.g., Claude), add the following to the client configuration:

{
  "mcpServers": {
    "flux-image-generator": {
      "command": "mcp-server-flux-image-generator",
      "env": {
        "BFL_API_KEY": "your_api_key_here"
      }
    }
  }
}

Available Tools

generateImage

Generate an image based on a text prompt with customizable settings. Parameters:

• prompt (string, required): Text describing the image.
• width (number, optional, default: 1024): Image width in pixels.
• height (number, optional, default: 1024): Image height in pixels.
• promptUpsampling (boolean, optional, default: false): Enhance details by upsampling the prompt.
• seed (number, optional): Random seed for reproducible results.
• safetyTolerance (number, optional, default: 3): Content moderation tolerance (1 - 5).

Example:

{
  "prompt": "A peaceful lake at sunset with mountains in the background",
  "width": 1024,
  "height": 768,
  "promptUpsampling": true,
  "seed": 12345,
  "safetyTolerance": 3
}

quickImage

A simplified tool to quickly generate an image with default settings. Parameters:

• prompt (string, required): Text describing the image.

Example:

{
  "prompt": "A future cityscape with flying cars"
}

batchGenerateImages

Generate multiple images in batch based on a list of prompts. Parameters:

• prompts (array of strings, required): List of prompts (maximum 10).
• width (number, default: 1024): Image width.
• height (number, default: 1024): Image height.

Example:

{
  "prompts": [
    "A peaceful lake at sunset with mountains in the background",
    "Flying cars in a future cityscape",
    "Prohibited content"
  ],
  "width": 1024,
  "height": 768
}

📚 Documentation

Output Format

Successful Response

{
  "images": [
    {
      "path": "/generated-images/1.png",
      "status": "success"
    },
    {
      "path": "/generated-images/2.png",
      //... other image objects
    }
  ]
}

🔧 Technical Details

Prerequisites

• Node.js (v18.0.0 or higher)
• Black Forest Lab API key (obtainable at https://api.bfl.ml)