The FLUX Image Generator MCP Server generates images using Black Forest Lab's FLUX model based on text prompts. You can:
Generate single images with customizable dimensions, prompt upsampling, seeds, and safety settings
Quickly generate images with default settings
Batch generate up to 10 images from multiple prompts
Save generated images locally with optional custom paths
Integrate with MCP clients like Claude for image generation workflows
Create reproducible results through seed values and enhance detail through prompt upsampling
Uses .ENV files for configuration, allowing users to securely store their Black Forest Lab API key.
Provides tools for generating images using Black Forest Lab's FLUX model with features including text-to-image generation, customizable dimensions, prompt upsampling, and batch image generation.
Runs as a Node.js application, requiring v18.0.0 or higher for operation as a prerequisite for the server.
Available as an npm package for easy installation using the package manager.
FLUX Image Generator MCP Server
An MCP (Model Context Protocol) server for generating images using Black Forest Lab's FLUX model. Uses the latest MCP SDK (v1.7.0).
Features
Generate images based on text prompts
Customize image dimensions, prompt upsampling, and safety settings
Save generated images locally
Batch image generation from multiple prompts
Related MCP server: Image Generator MCP Server
Prerequisites
Node.js (v18.0.0 or higher)
Black Forest Lab API key (get one at https://api.bfl.ml)
Installation
From Source
Clone this repository
Install dependencies:
Create a
.envfile based on.env.exampleand add your Black Forest Lab API key:
Build the project:
Using npm
Usage
Starting the MCP Server
Start the server with:
For development with auto-recompilation:
Integrating with MCP Clients
To use this server with MCP clients (like Claude), add the following to your client's configuration:
Available Tools
generateImage
Generates an image based on a text prompt with customizable settings.
Parameters:
prompt(string, required): Text description of the image to generatewidth(number, optional, default: 1024): Width of the image in pixelsheight(number, optional, default: 1024): Height of the image in pixelspromptUpsampling(boolean, optional, default: false): Enhance detail by upsampling the promptseed(number, optional): Random seed for reproducible resultssafetyTolerance(number, optional, default: 3): Content moderation tolerance (1-5)
Example:
quickImage
A simplified tool for quickly generating images with default settings.
Parameters:
prompt(string, required): Text description of the image to generate
Example:
batchGenerateImages
Generates multiple images from a list of prompts.
Parameters:
prompts(array of strings, required): List of text prompts (maximum 10)width(number, optional, default: 1024): Width of the imagesheight(number, optional, default: 1024): Height of the images
Example:
Output Format
All tools return responses in this format:
For errors:
The batch tool returns:
License
MIT