Provides access to Fal.ai's image generation platform with 600+ AI models including Flux and Stable Diffusion, enabling image generation, workflow execution, and real-time progress tracking for AI-powered visual content creation.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Fal.ai MCP Servergenerate a cyberpunk cityscape with neon lights using flux"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Fal.ai MCP Server
An MCP (Model Context Protocol) server that provides seamless integration with Fal.ai's image generation models and workflows.
Features
π¨ Image Generation - Access 600+ Fal.ai models including Flux, Stable Diffusion, and more
π Workflow Support - Run pre-built pipelines like sdxl-sticker
π Streaming - Real-time progress updates for long-running operations
π¦ Simple API - Unified interface for all models and workflows
β‘ Queue Management - Built-in status tracking for async operations
Installation
Quick Install (npm)
npm install -g fal-mcp-serverFrom Source
git clone https://github.com/yourusername/fal-mcp-server.git
cd fal-mcp-server
npm install
npm run build
npm linkSetup
1. Get your Fal.ai API Key
Sign up at fal.ai and get your API key from the dashboard.
2. Add to Claude Code
claude mcp add fal --env "FAL_KEY=your-api-key-here" -- npx -y fal-mcp-server3. Verify Connection
claude mcp listYou should see:
fal: npx -y fal-mcp-server - β ConnectedAvailable Tools
generate_image
Generate images using any Fal.ai model.
Parameters:
prompt(required): Text description of the imagemodel: Model ID (default: "fal-ai/flux/schnell")image_size: "square", "landscape_4_3", or "portrait_3_4"num_images: 1-4 imagesseed: For reproducible generation
Example:
{
"prompt": "a cyberpunk cat in neon city",
"model": "fal-ai/flux/dev",
"image_size": "landscape_4_3",
"num_images": 2
}run_model
Run any Fal.ai model with custom parameters.
Parameters:
model_id(required): The model endpoint IDinput(required): Model-specific input parametersstream: Enable streaming for real-time updates
Example:
{
"model_id": "fal-ai/stable-diffusion-v3-medium",
"input": {
"prompt": "professional portrait photo",
"negative_prompt": "low quality, blurry"
}
}run_workflow
Execute Fal.ai workflows (multi-step pipelines).
Parameters:
workflow_id(required): The workflow IDinput(required): Workflow input parametersstream: Stream workflow events
Example:
{
"workflow_id": "workflows/fal-ai/sdxl-sticker",
"input": {
"prompt": "cute puppy mascot"
}
}list_popular_models
Get a list of popular Fal.ai models.
check_status
Check the status of an async request.
Parameters:
request_id(required): The request ID to check
Popular Models
fal-ai/flux/schnell - Fastest Flux model (4 steps)
fal-ai/flux/dev - High quality Flux model
fal-ai/flux-pro - Professional Flux model
fal-ai/fast-sdxl - Fast Stable Diffusion XL
fal-ai/stable-diffusion-v3-medium - Latest SD3
fal-ai/recraft-v3 - Artistic style generation
Workflows
workflows/fal-ai/sdxl-sticker - Generate β Remove BG β Sticker
Usage in Claude Code
Once installed, you can use natural language to interact with Fal.ai:
"Generate a cyberpunk cityscape using Flux"
"Create a sticker of a cute robot"
"Run the sdxl-sticker workflow with a puppy prompt"
"List available image models"
Environment Variables
FAL_KEY(required): Your Fal.ai API key
Development
# Install dependencies
npm install
# Build TypeScript
npm run build
# Watch mode for development
npm run watch
# Run locally
FAL_KEY=your-key node dist/index.jsLicense
MIT
Contributing
Contributions welcome! Please submit PRs to improve the server.