fal.ai

by am0y

57 316 downloads Not rated yet MIT

GitHub

About

Bridges AI systems with fal.ai's machine learning models and services, enabling image generation, media processing, and specialized AI capabilities through direct or queued execution modes with authentication and file management support.

Details

Repository: am0y/mcp-fal
License: MIT

Explore

- 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

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below
Plugin Name fal.ai

Command (node, npx, python, etc.) /absolute/path/to/mcp-fal/venv/bin/python
Arguments
- Argument 1 /absolute/path/to/mcp-fal/main.py
Environment
- FAL_KEY your_fal_api_key_here
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "d:/Projects/python/mcp-fal/main.py"
            ],
            "command": "d:/Projects/python/mcp-fal/venv/Scripts/python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "d:/Projects/python/mcp-fal/main.py"
            ],
            "command": "d:/Projects/python/mcp-fal/venv/Scripts/python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "d:/Projects/python/mcp-fal/main.py"
            ],
            "command": "d:/Projects/python/mcp-fal/venv/Scripts/python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "d:/Projects/python/mcp-fal/main.py"
            ],
            "command": "d:/Projects/python/mcp-fal/venv/Scripts/python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "d:/Projects/python/mcp-fal/main.py"
            ],
            "command": "d:/Projects/python/mcp-fal/venv/Scripts/python.exe"
        }
    }
}

JSON

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

From the repository

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

1. Clone this repository:

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

cd mcp-fal

2. Create a virtual environment and install dependencies:

python -m venv venv venv/Scripts/pip install -r requirements.txt # Windows

1. Clone this repository:

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



2. Copy the environment template and add your API key:

bash
cp .env.example .env

Prerequisites: Python 3.10+ installed

python -m venv venv

bash

After setting up the virtual environment above, configure your MCP client:

> [!WARNING]
> This Docker setup is experimental and does NOT work for MCP integration.
>
> MCP servers use stdio transport and must be spawned by MCP clients. Docker containers will exit immediately because there's no stdin connection. This is kept for educational purposes and potential future experimentation.

docker-compose up -d

The container will start and exit immediately because MCP servers require an active stdin connection.

`models`

List available models with optional pagination. Parameters: page (optional int), total (optional int)

`search`

Search for models by keywords. Parameters: keywords (string)

`schema`

Get OpenAPI schema for a specific model. Parameters: model_id (string)

`generate`

Generate content using a model. Parameters: model (string), parameters (object), queue (optional boolean)

`result`

Get result from a queued request. Parameters: url (string)

`status`

Check status of a queued request. Parameters: url (string)

`cancel`

Cancel a queued request. Parameters: url (string)

`upload`

Upload a file to fal.ai CDN. Parameters: path (string)

- 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

---

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "fal.ai": {
            "env": {
                "FAL_KEY": "your_fal_api_key_here"
            },
            "args": [
                "/absolute/path/to/mcp-fal/main.py"
            ],
            "command": "/absolute/path/to/mcp-fal/venv/bin/python"
        }
    }
}

Linux

{
    "env": {
        "FAL_KEY": "your_fal_api_key_here"
    },
    "args": [
        "/absolute/path/to/mcp-fal/main.py"
    ],
    "command": "/absolute/path/to/mcp-fal/venv/bin/python"
}

Macos

{
    "env": {
        "FAL_KEY": "your_fal_api_key_here"
    },
    "args": [
        "/absolute/path/to/mcp-fal/main.py"
    ],
    "command": "/absolute/path/to/mcp-fal/venv/bin/python"
}

Windows

{
    "env": {
        "FAL_KEY": "your_fal_api_key_here"
    },
    "args": [
        "d:/Projects/python/mcp-fal/main.py"
    ],
    "command": "d:/Projects/python/mcp-fal/venv/Scripts/python.exe"
}

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

Features

Requirements

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

Installation

Manual Installation (Recommended)

1. Clone this repository:

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

cd mcp-fal

2. Create a virtual environment and install dependencies:
```bash
python -m venv venv
venv/Scripts/pip install -r requirements.txt # Windows

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Explore

Setting up with Highlight

From the repository

models

search

schema

generate

result

status

cancel

upload

Claude Desktop / Cursor

Linux

Macos

Windows

Features

Requirements

Installation

Manual Installation (Recommended)

Videos about fal.ai

How to build a PRO AI Filmmaking Pipeline | Claude Code and fal MCP

Steal My Ultimate AI Video Workflow (n8n, OpenAI & Fal.ai)

Build a Multi-Model Image Generator with FAL.AI + KIE.AI (Claudemas Day 4)

More like this

Sentry

Github

Git

GitLab

`models`

`search`

`schema`

`generate`

`result`

`status`

`cancel`

`upload`