A
securityA
licenseA
qualityA MCP server that enables Claude and other MCP-compatible assistants to generate images from text prompts using Together AI's image generation models.
Last updated -
4
MIT License
🎨 Fal.ai MCP Server
A Model Context Protocol (MCP) server that enables Claude Desktop (and other MCP clients) to generate images, videos, music, and audio using Fal.ai models.
✨ Features
🚀 Performance
Native Async API - Uses fal_client.run_async() for optimal performance
Queue Support - Long-running tasks (video/music) use queue API with progress updates
Non-blocking - All operations are truly asynchronous
🌐 Transport Modes (New!)
STDIO - Traditional Model Context Protocol communication
HTTP/SSE - Web-based access via Server-Sent Events
Dual Mode - Run both transports simultaneously
🎨 Media Generation
🖼️ Image Generation - Create images using Flux, SDXL, and other models
🎬 Video Generation - Generate videos from images or text prompts
🎵 Music Generation - Create music from text descriptions
🗣️ Text-to-Speech - Convert text to natural speech
📝 Audio Transcription - Transcribe audio using Whisper
⬆️ Image Upscaling - Enhance image resolution
🔄 Image-to-Image - Transform existing images with prompts
🚀 Quick Start
Prerequisites
Python 3.10 or higher
Fal.ai API key (free tier available)
Claude Desktop (or any MCP-compatible client)
Installation
Option 1: Docker (Recommended for Production) 🐳
Official Docker image available on GitHub Container Registry:
# Pull the latest image
docker pull ghcr.io/raveenb/fal-mcp-server:latest
# Run with your API key
docker run -d \
--name fal-mcp \
-e FAL_KEY=your-api-key \
-p 8080:8080 \
ghcr.io/raveenb/fal-mcp-server:latest
Or use Docker Compose:
curl -O https://raw.githubusercontent.com/raveenb/fal-mcp-server/main/docker-compose.yml
echo "FAL_KEY=your-api-key" > .env
docker-compose up -d
Option 2: Install from PyPI
pip install fal-mcp-server
Or with uv:
uv pip install fal-mcp-server
Option 3: Install from source
git clone https://github.com/raveenb/fal-mcp-server.git
cd fal-mcp-server
pip install -e .
Configuration
Get your Fal.ai API key from fal.ai
Configure Claude Desktop by adding to:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
For Docker Installation:
{
"mcpServers": {
"fal-ai": {
"command": "curl",
"args": ["-N", "http://localhost:8080/sse"]
}
}
}
For PyPI Installation:
{
"mcpServers": {
"fal-ai": {
"command": "python",
"args": ["-m", "fal_mcp_server.server"],
"env": {
"FAL_KEY": "your-fal-api-key"
}
}
}
}
For Source Installation:
{
"mcpServers": {
"fal-ai": {
"command": "python",
"args": ["/path/to/fal-mcp-server/src/fal_mcp_server/server.py"],
"env": {
"FAL_KEY": "your-fal-api-key"
}
}
}
}
Restart Claude Desktop
💬 Usage
With Claude Desktop
Once configured, ask Claude to:
"Generate an image of a sunset"
"Create a video from this image"
"Generate 30 seconds of ambient music"
"Convert this text to speech"
"Transcribe this audio file"
HTTP/SSE Transport (New!)
Run the server with HTTP transport for web-based access:
# Using Docker (recommended)
docker run -d -e FAL_KEY=your-key -p 8080:8080 ghcr.io/raveenb/fal-mcp-server:latest
# Using pip installation
fal-mcp-http --host 0.0.0.0 --port 8000
# Or dual mode (STDIO + HTTP)
fal-mcp-dual --transport dual --port 8000
Connect from web clients via Server-Sent Events:
SSE endpoint:
http://localhost:8080/sse(Docker) orhttp://localhost:8000/sse(pip)Message endpoint:
POST http://localhost:8080/messages/
See Docker Documentation and HTTP Transport Documentation for details.
📦 Supported Models
Image Models
flux_schnell- Fast high-quality generationflux_dev- Development version with more controlsdxl- Stable Diffusion XL
Video Models
svd- Stable Video Diffusionanimatediff- Text-to-video animation
Audio Models
musicgen- Music generationbark- Text-to-speechwhisper- Audio transcription
🤝 Contributing
Contributions are welcome! Please see CONTRIBUTING.md for guidelines.
Local Development
We support local CI testing with act:
# Quick setup
make ci-local # Run CI locally before pushing
# See detailed guide
cat docs/LOCAL_TESTING.md
📝 License
MIT License - see LICENSE file for details.
🙏 Acknowledgments
Related MCP Servers
- -securityFlicense-qualityAn MCP server that connects Claude to FL Studio, allowing the AI to compose music, control instruments, and live record melodies, chords, and drums to the piano roll.Last updated -61
- -security-license-qualityProvides AI-powered visual analysis capabilities for Claude and other MCP-compatible AI assistants, allowing them to capture and analyze screenshots, perform file operations, and generate UI/UX reports.
- AsecurityAlicenseAqualityAn MCP server that allows Claude to use OpenAI's image generation capabilities (gpt-image-1) to create image assets for users, which is particularly useful for game and web development projects.Last updated -113MIT License