Happy slice of mcp pizzaMCP.pizza
Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

mcp-fal

MCP.Pizza Chef: am0y

mcp-fal is a Model Context Protocol (MCP) server designed to integrate fal.ai's AI models and services into MCP-enabled environments. It supports listing and searching fal.ai models, retrieving model schemas, generating content, and managing queued executions. The server also handles file uploads to fal.ai's CDN, providing a comprehensive interface for leveraging fal.ai's capabilities programmatically with Python 3.10+ and fastmcp.

Use This MCP server To

List all available fal.ai AI models for selection Search fal.ai models by keywords for targeted use Retrieve detailed schemas of fal.ai models Generate text or content using fal.ai models Manage queued model execution requests and results Upload files to fal.ai CDN for model input or storage

README

fal.ai MCP Server

A Model Context Protocol (MCP) server for interacting with fal.ai models and services.

Features

  • List all available fal.ai models
  • Search for specific models by keywords
  • Get model schemas
  • Generate content using any fal.ai model
  • Support for both direct and queued model execution
  • Queue management (status checking, getting results, cancelling requests)
  • File upload to fal.ai CDN

Requirements

  • Python 3.10+
  • fastmcp
  • httpx
  • aiofiles
  • A fal.ai API key

Installation

  1. Clone this repository:
git clone https://github.com/am0y/mcp-fal.git
cd mcp-fal
  1. Install the required packages:
pip install fastmcp httpx aiofiles
  1. Set your fal.ai API key as an environment variable:
export FAL_KEY="YOUR_FAL_API_KEY_HERE"

Usage

Running the Server

You can run the server in development mode with:

fastmcp dev main.py

This will launch the MCP Inspector web interface where you can test the tools interactively.

Installing in Claude Desktop

To use the server with Claude Desktop:

fastmcp install main.py -e FAL_KEY="YOUR_FAL_API_KEY_HERE"

This will make the server available to Claude in the Desktop app.

Running Directly

You can also run the server directly:

python main.py

API Reference

Tools

  • models(page=None, total=None) - List available models with optional pagination
  • search(keywords) - Search for models by keywords
  • schema(model_id) - Get OpenAPI schema for a specific model
  • generate(model, parameters, queue=False) - Generate content using a model
  • result(url) - Get result from a queued request
  • status(url) - Check status of a queued request
  • cancel(url) - Cancel a queued request
  • upload(path - Upload a file to fal.ai CDN

License

MIT

mcp-fal FAQ

How do I set up the mcp-fal server?
Clone the repository, install dependencies with pip, and set your fal.ai API key as an environment variable.
What Python version is required to run mcp-fal?
Python 3.10 or higher is required.
Can mcp-fal handle queued model execution?
Yes, it supports both direct and queued execution with queue management features.
How do I upload files to fal.ai using mcp-fal?
The server provides an endpoint to upload files directly to the fal.ai CDN.
Is there a web interface to test mcp-fal?
Yes, running the server in development mode launches the MCP Inspector web interface for testing.
What dependencies does mcp-fal require?
It requires fastmcp, httpx, and aiofiles Python packages.
How do I authenticate requests to fal.ai through mcp-fal?
You must set your fal.ai API key as an environment variable named FAL_KEY.
Can I search for specific fal.ai models using mcp-fal?
Yes, the server supports keyword-based model searches.