MCP server for fal.ai image generation
npm install mcp-fal-ai-image   
Effortlessly generate images from text prompts using fal.ai and the Model Context Protocol (MCP). Integrates directly with AI IDEs like Cursor and Windsurf.
This tool is designed for:
- Developers and designers who want to generate images from text prompts without leaving their IDE.
- Rapid prototyping of UI concepts, marketing assets, or creative ideas.
- Content creators needing unique visuals for blogs, presentations, or social media.
- AI researchers and tinkerers experimenting with the latest fal.ai models.
- Automating workflows that require programmatic image generation via MCP.
Key features:
- Supports any valid fal.ai model and all major image parameters.
- Works out of the box with Node.js and a fal.ai API key.
- Saves images locally with accessible file paths.
- Simple configuration and robust error handling.
1. Requirements: Node.js 18+, fal.ai API key
2. Configure MCP:
``json`
{
"mcpServers": {
"fal-ai-image": {
"command": "npx",
"args": ["-y", "mcp-fal-ai-image"],
"env": { "FAL_KEY": "YOUR-FAL-AI-API-KEY" }
}
}
}
generate-image
3. Run: Use the tool from your IDE.
> π‘ Typical Workflow:
> Describe the image you want (e.g., βgenerate a landscape with flying cars using model fal-ai/kolors, 2 images, landscape_16_9β) and get instant results in your IDE.
- generate an image of a red applegenerate an image of a red apple using model fal-ai/kolors
- generate 3 images of a glowing red apple in a futuristic city using model fal-ai/recraft-v3, square_hd, 40 inference steps, guidance scale 4.0, safety checker on
-
Supported parameters: prompt, model ID (any fal.ai model), number of images, image size, inference steps, guidance scale, safety checker.
Images are saved locally; file paths are shown in the response. For model IDs, see fal.ai/models.
- FAL_KEY environment variable is not set: Set your fal.ai API key as above.npx
- not found: Install Node.js 18+ and npm.
Advanced: Example MCP Request/Response
`json
{
"tool": "generate-image",
"args": {
"prompt": "A futuristic cityscape at sunset",
"model": "fal-ai/kolors"
}
}
// Example response
{
"images": [
{ "url": "file:///path/to/generated_image1.png" },
{ "url": "file:///path/to/generated_image2.png" }
]
}
`
Generated images are saved to your local system:
- By default: ~/Downloads/fal_ai (on Linux/macOS; uses XDG standard if available)FAL_IMAGES_OUTPUT_DIR
- Custom location: Set the environment variable to your desired folder. Images will be saved in
The full file path for each image is included in the tool's response.
- If you specify a model ID that is not supported by fal.ai, you will receive an error from the backend. Double-check for typos or visit fal.ai/models to confirm the model ID.
- For the latest list of models and their capabilities, refer to the fal.ai model catalog or API docs.
- For other errors, consult your MCP client logs or open an issue on GitHub.
Contributions and suggestions are welcome! Please open issues or pull requests on GitHub.
- Your API key is only used locally to authenticate with fal.ai.
- No user data is stored or transmitted except as required by fal.ai API.
MIT License Β© 2025 Madhusudan Kulkarni