Overview
What is fal-api-mcp-server?
A Model Context Protocol (MCP) server that provides image generation capabilities using fal.ai's FLUX.1 Pro model. It enables AI assistants like Claude to generate images directly from text prompts.
How to use fal-api-mcp-server?
Set your fal.ai API key as the FAL_KEY environment variable. Configure the server in your Claude Desktop JSON config using uv (development) or uvx (published). Once running, Claude can invoke the generate_image tool with a prompt to create images.
Key features of fal-api-mcp-server
- Integrates with fal.ai FLUX.1 Pro for image generation
- One tool: generate_image with customizable parameters
- Supports multiple output sizes and formats
- Includes safety checker with adjustable tolerance
- Can generate multiple images per prompt
Use cases of fal-api-mcp-server
- Generate landscape images from text descriptions
- Create character portraits for storytelling or game design
- Visualize futuristic scenes for concept art
- Produce multiple image variations for design exploration
FAQ from fal-api-mcp-server
What tool does this server provide?
It provides one tool, generate_image, which creates images from text prompts using fal.ai's FLUX.1 Pro model.
What parameters are required to generate an image?
Only prompt is required. Optional parameters include image_size, num_images, enable_safety_checker, safety_tolerance, and output_format.
How do I get a fal.ai API key?
Sign up at fal.ai to obtain an API key, then set it as the FAL_KEY environment variable.
What image sizes are supported?
Supported options: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9. Default is landscape_4_3.
Does this server store generated images?
No. fal.ai is a stateless model execution service; the server does not provide any persistent resources.
