fal.ai

A Python-based MCP server to list models, get schemas, generate content, manage queues, and upload files to fal.ai CDN.

typescript

0

GitHub Stars

typescript

Language

4 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "m1vision-fal.ai-mcp": {
      "command": "fastmcp",
      "args": [
        "dev",
        "main.py"
      ],
      "env": {
        "FAL_KEY": "YOUR_FAL_API_KEY_HERE"
      }
    }
  }
}

You can run and manage a fal.ai MCP Server to interact with fal.ai models, perform model discovery, generate content, manage queued tasks, and upload files to the fal.ai CDN. This guide shows practical steps to install, run, and use the server with an MCP client.

How to use

Start by running the server in development mode to expose an interactive MCP Inspector interface you can use to test tools and workflows.

fastmcp dev main.py

How to use with a desktop MCP client

You can also install and expose the server to a desktop MCP client. Run the install flow shown below to provide your API key to the server for authentication.

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

Run directly

If you prefer to start the server without the MCP runner, you can run the main script directly in any environment that has Python installed.

python main.py

Available tools

models

List available fal.ai models with optional pagination to explore all offerings.

search

Search for fal.ai models by keywords to quickly locate relevant capabilities.

schema

Retrieve the OpenAPI schema for a specific model to understand inputs, outputs, and available parameters.

generate

Generate content using a selected fal.ai model with given parameters. Supports both direct and queued execution.

result

Fetch the result of a previously queued request using its result URL.

status

Check the status of a queued request to monitor progress and completion.

cancel

Cancel an in-progress or queued request if needed.

upload

Upload a file to the fal.ai CDN for use with models and workflows.