Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Fal Recraft V3 MCP Servercreate a digital illustration of a cyberpunk cat with neon blue and pink colors"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
fal-ai/recraft/v3 MCP Server
A Model Context Protocol (MCP) server that provides access to the fal-ai/recraft/v3 image generation model. This server allows you to generate high-quality images with superior design capabilities using advanced AI technology through the fal.ai platform.
Features
High-Quality Image Generation: Generate stunning images using the fal-ai/recraft/v3 model
Superior Design Capabilities: Advanced text-to-image generation with excellent design quality
Multiple Generation Methods: Support for synchronous and queue-based generation
Flexible Image Sizing: Support for predefined sizes and custom dimensions
Advanced Style Control: Comprehensive style system with realistic, digital, and vector illustration styles
Color Control: Specify custom RGB colors to guide generation
Local Image Download: Automatically downloads generated images to local storage
Queue Management: Submit long-running requests and check their status
Webhook Support: Optional webhook notifications for completed requests
Safety Checker: Built-in content safety filtering
Installation
Clone this repository:
Install dependencies:
Build the project:
Configuration
Environment Variables
Set your fal.ai API key as an environment variable:
You can get your API key from fal.ai.
MCP Client Configuration
Add this server to your MCP client configuration. For example, in Claude Desktop's config file:
If the package is published to npm, you can use:
Alternatively, if you've cloned the repository locally:
Available Tools
1. recraft_v3_generate
Generate images using the standard synchronous method.
Parameters:
prompt(required): Text description of the image to generateimage_size(optional): Predefined size or custom {width, height} object (default: "1024x1024")style(optional): Style to use for generation (default: "any")colors(optional): Array of RGB color objects to guide generation (max 5 colors)style_id(optional): Custom style ID for specific stylesenable_safety_checker(optional): Enable content safety filtering (default: true)num_images(optional): Number of images to generate (1-4, default: 1)seed(optional): Random seed for reproducible resultssync_mode(optional): Wait for completion (default: true)
Example:
2. recraft_v3_generate_queue
Submit a long-running image generation request to the queue.
Parameters: Same as recraft_v3_generate plus:
webhook_url(optional): URL for webhook notifications
Returns: A request ID for tracking the job
3. recraft_v3_queue_status
Check the status of a queued request.
Parameters:
request_id(required): The request ID from queue submissionlogs(optional): Include logs in response (default: true)
4. recraft_v3_queue_result
Get the result of a completed queued request.
Parameters:
request_id(required): The request ID from queue submission
Image Sizes
Predefined Sizes
1024x1024: Square format1365x1024: Wide landscape1024x1365: Tall portrait1536x1024: Ultra-wide landscape1024x1536: Ultra-tall portrait1820x1024: Panoramic landscape1024x1820: Panoramic portrait1024x2048: Extra tall portrait2048x1024: Extra wide landscape1434x1024: Wide landscape variant1024x1434: Tall portrait variant1024x1280: Standard portrait1280x1024: Standard landscape1024x1707: Long portrait
Custom Sizes
You can also specify custom dimensions (512-2048px):
Style Control
Recraft V3 offers comprehensive style control with three main categories:
Realistic Image Styles
realistic_image: General realistic stylerealistic_image/b_and_w: Black and white photographyrealistic_image/hard_flash: Hard flash photographyrealistic_image/hdr: HDR photographyrealistic_image/natural_light: Natural lightingrealistic_image/studio_portrait: Studio portrait stylerealistic_image/enterprise: Professional/corporate stylerealistic_image/motion_blur: Motion blur effects
Digital Illustration Styles
digital_illustration: General digital artdigital_illustration/pixel_art: Pixel art styledigital_illustration/hand_drawn: Hand-drawn appearancedigital_illustration/grain: Textured/grainy styledigital_illustration/infantile_sketch: Childlike sketch styledigital_illustration/2d_art_poster: 2D poster artdigital_illustration/handmade_3d: 3D handmade styledigital_illustration/hand_drawn_outline: Outlined hand-drawn styledigital_illustration/engraving_color: Colored engraving styledigital_illustration/2d_art_poster_2: Alternative 2D poster style
Vector Illustration Styles
vector_illustration: General vector artvector_illustration/engraving_bw: Black and white engravingvector_illustration/line_art: Clean line artvector_illustration/line_circuit: Circuit-like line patternsvector_illustration/linocut: Linocut print style
Any Style
any: Let the model choose the best style (default)
Example:
Color Control
Guide the generation with specific RGB colors:
Note: Maximum of 5 colors can be specified.
Safety Checker
Control content safety filtering:
When enabled (default), the safety checker filters out potentially harmful content.
Output
Generated images are automatically downloaded to a local images/ directory with descriptive filenames. The response includes:
Local file paths
Original URLs
Image dimensions (when available)
Content types
File sizes (when available)
Generation parameters used
Request IDs for tracking
Seed values for reproducibility
Error Handling
The server provides detailed error messages for:
Missing API keys
Invalid parameters
Network issues
API rate limits
Generation failures
Safety checker violations
Development
Running in Development Mode
Testing the Server
Getting the Installation Path
API Reference
This server implements the fal-ai/recraft/v3 API. For detailed API documentation, visit:
Examples
Basic Text-to-Image Generation
Advanced Generation with Style Control
Realistic Photography Style
Vector Art Generation
Queue-based Generation with Webhook
License
MIT License - see LICENSE file for details.
Contributing
Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
Support
For issues and questions:
Open an issue on GitHub
Check the fal.ai documentation
Changelog
v1.0.0
Initial release with fal-ai/recraft/v3 API support
Text-to-image generation with superior design capabilities
Comprehensive style system with realistic, digital, and vector illustration styles
RGB color control for guided generation
Queue management with webhook support
Local image download functionality
Built-in safety checker
Comprehensive error handling