BFL

MCP server for Black Forest Labs FLUX image generation and editing via the MCP protocol.

typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 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": {
    "elhombrejd-bfl_mcp": {
      "command": "npx",
      "args": [
        "bfl-mcp-server"
      ],
      "env": {
        "BFL_API_KEY": "your-api-key-here"
      }
    }
  }
}

You can run a self-contained MCP server that connects to Black Forest Labs FLUX image generation and editing services. This server exposes endpoints you can use from MCP clients to generate images from text prompts and edit existing images with natural-language instructions.

How to use

Connect your MCP client to the BFL MCP Server using the provided command-line interface. You will authenticate with your BFL API key and then issue tool calls to generate images or edit them. Use prompts in natural language to describe the image you want, and adjust options like aspect ratio, seed, safety settings, and output format to fit your needs. The server integrates with MCP clients such as Claude Desktop, Claude Code, and other MCP-enabled tools, so you can work within your preferred editor or chat environment.

How to install

Prerequisites: Ensure Node.js and npm are installed on your machine.

# Quick start: run the MCP server with your BFL API key
npx bfl-mcp-server YOUR_BFL_API_KEY

Configuration and usage notes

If you prefer to supply the API key via environment variables, set the key and run the server without additional arguments.

export BFL_API_KEY="your-api-key-here"
npx bfl-mcp-server

Available tools

generate_image

Create a new image by providing a descriptive text prompt. You can specify optional parameters such as aspect_ratio, seed, safety_tolerance, and output_format to control the result.

edit_image

Modify an existing image by supplying a text instruction and the input image data. Optional parameters include aspect_ratio, seed, safety_tolerance, and output_format to refine the result.