This server allows you to generate high-quality images using Together AI models based on text prompts, with control over various parameters:
Generate images from text descriptions (
prompt)Select image generation models (default:
black-forest-labs/FLUX.1.1-pro)Customize image dimensions (width, height)
Set the number of inference steps (default: 28)
Generate multiple images in one request
Choose output format (PNG, JPG, SVG)
Save images to a specified absolute directory path
Automatically resize images while maintaining aspect ratio if below 256 pixels
Create output directories recursively as needed
Receive detailed metadata including filepath, filename, and dimensions
Supports Together AI's latest FLUX.1.1-pro model for image generation
Provides high-quality JPEG output (90% quality) for the generated images
Specifies configuration path for Linux users to set up the MCP server
Specifies configuration path for macOS users to set up the MCP server
Defines tool parameters using TypeScript type annotations
Together AI Image Server
An MCP server for generating images using Together AI's image generation models.
Setup
Install dependencies:
Build the server:
Related MCP server: OpenAI GPT Image MCP
Configuration
1. Together AI API Key
The server requires a Together AI API key. You can get one from Together AI's platform.
2. Cline Configuration
Add the server to your Cline MCP settings file:
For macOS/Linux: ~/Library/Application Support/Windsurf/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
Usage in Cline
The server provides a generate_image tool with the following parameters:
Example Usage
You can use the server in Cline like this:
Output
The tool returns a JSON response containing:
filepath: Full path to the saved imagefilename: Name of the saved image filedimensions: Original and final dimensions of the image
Features
Supports Together AI's latest FLUX.1.1-pro model
Automatically resizes images if dimensions are below 256 pixels
Maintains aspect ratio during resizing
High-quality JPEG output (90% quality)
Creates output directories recursively
Returns detailed metadata including image dimensions