MCP Fal

🚀 fal.ai MCP Server

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

🚀 Quick Start

The fal.ai MCP Server is a powerful tool designed to facilitate seamless interaction with fal.ai models and services. It provides a range of features to manage and utilize these models effectively.

✨ Features

• List all available fal.ai models.
• Search for specific models based on keywords.
• Retrieve the OpenAPI schema for a model.
• Generate content using any fal.ai model.
• Support both direct and queued model execution.
• Queue management (check status, get results, cancel requests).
• Upload files to the fal.ai CDN.

📦 Installation

Prerequisites

• Python 3.10 or higher.
• The fastmcp library.
• The httpx library.
• The aiofiles library.
• A fal.ai API key.

Steps

1. Clone this repository:

git clone https://github.com/am0y/mcp-fal.git
cd mcp-fal

2. Install the required packages:

pip install fastmcp httpx aiofiles

3. Set your fal.ai API key as an environment variable:

export FAL_KEY="YOUR_FAL_API_KEY_HERE"

💻 Usage Examples

Running the Server

You can run the server in development mode:

fastmcp dev main.py

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

Installation 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 in the Desktop application.

Direct Execution

You can also run the server directly:

python main.py

📚 Documentation

Tools

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

📄 License

MIT