fal.ai MCP Server

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

Features

• Lists all available fal.ai models with pagination support.
• Enables searching for models using keywords.
• Retrieves model schemas in OpenAPI format.
• Generates content using any fal.ai model, supporting both direct and queued execution.
• Provides queue management functionalities, including status checking, result retrieval, and request cancellation.
• Facilitates file uploads to the fal.ai CDN.

Requirements

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

Installation

1. Clone the repository.
2. Install the required packages using pip install fastmcp httpx aiofiles.
3. Set the fal.ai API key as an environment variable: export FAL_KEY="YOUR_FAL_API_KEY_HERE".

Usage

The server can be run in development mode using fastmcp dev main.py, which launches the MCP Inspector. It can be installed for use with Claude Desktop via fastmcp install main.py -e FAL_KEY="YOUR_FAL_API_KEY_HERE". Alternatively, run it directly with python main.py.

API Reference

Provides tools like models, search, schema, generate, result, status, cancel, and upload for interacting with fal.ai models.

License

MIT