Fal Api MCP Server

🚀 fal-api-mcp-server

A server based on the Model Context Protocol (MCP) that uses the FLUX.1 Pro model from fal.ai to provide image generation capabilities.

✨ Features

Resources

This server does not provide any persistent resources since fal.ai is primarily a stateless model execution service.

Tools

The server implements one tool:

• generate_image: Generate an image based on a text prompt using fal.ai FLUX.1 Pro
  • Required parameters:
    • prompt: The text prompt for image generation
  • Optional parameters:
    • image_size: The desired image size (default: "landscape_4_3")
      • Options: "square_hd", "square", "portrait_4_3", "portrait_16_9", "landscape_4_3", "landscape_16_9"
    • num_images: The number of images to generate (default: 1)
    • enable_safety_checker: Enable the safety checker (default: true)
    • safety_tolerance: Safety tolerance level from 1 - 6, higher values are more lenient (default: "2")
    • output_format: The output image format, either "jpeg" or "png" (default: "jpeg")

📦 Installation

This server requires a fal.ai API key to function properly. You can register at fal.ai to obtain an API key.

The API key should be provided as an environment variable:

FAL_KEY=your_fal_ai_api_key

You can set this environment variable in your shell or create a .env file in the same directory as the server with the above content.

📚 Documentation

Demo

https://github.com/user-attachments/assets/564a0fc3-9204-4399-b1ea-ab6a5c9f2d84

🚀 Quick Start

Installation

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json%

"mcpServers": {
  "fal-api-mcp-server": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/fal-api-mcp-server",
      "run",
      "fal-api-mcp-server"
    ],
    "env": {
      "FAL_KEY": "your_fal_ai_api_key"
    }
  }
}

"mcpServers": {
  "fal-api-mcp-server": {
    "command": "uvx",
    "args": [
      "fal-api-mcp-server"
    ],
    "env": {
      "FAL_KEY": "your_fal_ai_api_key"
    }
  }
}

Usage

Once the server is configured and running, you can use Claude to generate images. For example:

• "Generate an image of a sunset over mountains"
• "Create a portrait of a cyberpunk character with neon lights"
• "Show a skyline of a future city with flying cars"

Claude will use the fal.ai FLUX.1 Pro model to generate the desired images.

🔧 Technical Details

Build and Publish

To prepare a distribution package:

1. Synchronize dependencies and update the lock file:

uv sync

2. Build the release:

uv build

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You need to set your PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run on stdio, debugging can be challenging. For the best debugging experience, we highly recommend using MCP Inspector.

You can start the MCP Inspector with the following command:

npx @modelcontextprotocol/inspector uv --directory /path/to/fal-api-mcp-server run fal-api-mcp-server

After starting, the Inspector will display a URL that you can access in your browser to begin debugging.