smithery.json•7.76 kB
{
"name": "fal-mcp-server",
"title": "Fal MCP Server - AI Image, Video & Music Generation",
"description": "Generate stunning AI images, videos, and music using Fal.ai models (FLUX, Stable Diffusion, MusicGen) directly in Claude Desktop through the Model Context Protocol",
"version": "0.3.0",
"author": {
"name": "Raveen Beemsingh",
"email": "raveen.b@gmail.com",
"github": "raveenb"
},
"license": "MIT",
"urls": {
"repository": "https://github.com/raveenb/fal-mcp-server",
"homepage": "https://raveenb.github.io/fal-mcp-server/",
"documentation": "https://raveenb.github.io/fal-mcp-server/",
"issues": "https://github.com/raveenb/fal-mcp-server/issues",
"pypi": "https://pypi.org/project/fal-mcp-server/",
"docker": "ghcr.io/raveenb/fal-mcp-server"
},
"categories": [
"ai-ml",
"generation",
"creative-tools",
"media",
"claude-integration"
],
"keywords": [
"fal",
"ai",
"image-generation",
"video-generation",
"music-generation",
"flux",
"stable-diffusion",
"musicgen",
"claude",
"mcp",
"model-context-protocol"
],
"runtime": {
"language": "python",
"minVersion": "3.10",
"package": "fal-mcp-server"
},
"requirements": {
"apiKey": {
"name": "FAL_KEY",
"description": "Fal.ai API key",
"required": true,
"url": "https://fal.ai/dashboard/keys"
}
},
"installation": [
{
"type": "pip",
"command": "pip install fal-mcp-server"
},
{
"type": "docker",
"command": "docker pull ghcr.io/raveenb/fal-mcp-server:latest"
},
{
"type": "uv",
"command": "uv pip install fal-mcp-server"
}
],
"configuration": {
"claude": {
"mcpServers": {
"fal-mcp-server": {
"command": "fal-mcp",
"args": [],
"env": {
"FAL_KEY": "your-api-key-here"
}
}
}
}
},
"transports": [
{
"type": "stdio",
"default": true,
"description": "Standard I/O for Claude Desktop integration"
},
{
"type": "http",
"port": 8080,
"description": "HTTP/SSE for web-based access"
},
{
"type": "dual",
"description": "Both STDIO and HTTP simultaneously"
}
],
"tools": [
{
"name": "generate_image",
"description": "Generate images from text prompts using AI models",
"parameters": {
"prompt": {
"type": "string",
"required": true,
"description": "Text description of the image to generate"
},
"model": {
"type": "string",
"default": "flux_schnell",
"enum": ["flux_schnell", "flux_dev", "flux_pro", "sdxl", "sd3", "lcm"],
"description": "AI model to use for generation"
},
"image_size": {
"type": "string",
"default": "landscape_16_9",
"description": "Output image dimensions"
},
"num_images": {
"type": "integer",
"default": 1,
"min": 1,
"max": 4,
"description": "Number of images to generate"
}
}
},
{
"name": "generate_video",
"description": "Create videos from images using AI models",
"parameters": {
"image_url": {
"type": "string",
"required": true,
"description": "URL of the source image"
},
"model": {
"type": "string",
"default": "svd",
"enum": ["svd", "animatediff", "kling"],
"description": "Video generation model"
},
"duration": {
"type": "integer",
"default": 4,
"min": 2,
"max": 10,
"description": "Video duration in seconds"
}
}
},
{
"name": "generate_music",
"description": "Generate music and audio from text descriptions",
"parameters": {
"prompt": {
"type": "string",
"required": true,
"description": "Description of the music to generate"
},
"model": {
"type": "string",
"default": "musicgen_large",
"enum": ["musicgen_small", "musicgen_medium", "musicgen_large", "bark"],
"description": "Audio generation model"
},
"duration": {
"type": "integer",
"default": 30,
"min": 5,
"max": 120,
"description": "Audio duration in seconds"
}
}
}
],
"models": {
"image": [
{
"id": "flux_schnell",
"name": "FLUX Schnell",
"description": "Fast image generation (2-3 seconds)",
"provider": "Black Forest Labs"
},
{
"id": "flux_dev",
"name": "FLUX Dev",
"description": "High-quality development model",
"provider": "Black Forest Labs"
},
{
"id": "flux_pro",
"name": "FLUX Pro",
"description": "Professional quality model",
"provider": "Black Forest Labs"
},
{
"id": "sdxl",
"name": "Stable Diffusion XL",
"description": "Popular open-source model",
"provider": "Stability AI"
}
],
"video": [
{
"id": "svd",
"name": "Stable Video Diffusion",
"description": "Image-to-video generation",
"provider": "Stability AI"
},
{
"id": "animatediff",
"name": "AnimateDiff",
"description": "Animation from static images",
"provider": "Community"
}
],
"audio": [
{
"id": "musicgen_large",
"name": "MusicGen Large",
"description": "High-quality music generation",
"provider": "Meta"
},
{
"id": "bark",
"name": "Bark",
"description": "Text-to-speech synthesis",
"provider": "Suno"
}
]
},
"features": [
"Native async API for fast performance",
"Queue management for long-running tasks",
"Progress tracking for generation tasks",
"Multiple aspect ratios and resolutions",
"Batch generation support",
"Docker support with official image",
"Comprehensive error handling",
"Type-safe Python implementation"
],
"badges": [
{
"type": "pypi",
"url": "https://badge.fury.io/py/fal-mcp-server.svg"
},
{
"type": "docker",
"url": "https://img.shields.io/badge/Docker-ghcr.io-blue?logo=docker"
},
{
"type": "license",
"url": "https://img.shields.io/badge/License-MIT-yellow.svg"
},
{
"type": "github-stars",
"url": "https://img.shields.io/github/stars/raveenb/fal-mcp-server?style=social"
}
],
"examples": [
{
"title": "Generate an Image",
"description": "Create a cyberpunk city scene",
"prompt": "Generate an image of a cyberpunk city at sunset with neon lights",
"tool": "generate_image",
"model": "flux_dev"
},
{
"title": "Create a Video",
"description": "Animate a landscape image",
"prompt": "Create a video from this landscape image",
"tool": "generate_video",
"model": "svd"
},
{
"title": "Generate Music",
"description": "Create ambient background music",
"prompt": "Generate 60 seconds of calm ambient electronic music",
"tool": "generate_music",
"model": "musicgen_large"
}
],
"metrics": {
"stars": "https://img.shields.io/github/stars/raveenb/fal-mcp-server",
"downloads": "https://pepy.tech/badge/fal-mcp-server",
"version": "https://badge.fury.io/py/fal-mcp-server.svg",
"tests": "95%+ coverage",
"ci": "GitHub Actions"
}
}