📌Overview

Purpose: To provide a standardized interface for high-quality image generation using Together AI via a Model Context Protocol (MCP) server.

Overview: The Image Generation MCP Server facilitates the seamless creation of images by allowing users to specify parameters and prompts while integrating easily with existing MCP-compatible applications. It leverages the Flux.1 Schnell model to deliver superior image quality.

Key Features:

High-Quality Image Generation: Utilizes the advanced Flux.1 Schnell model to produce visually appealing images based on textual descriptions.
Customizable Dimensions: Users can define the width and height of the generated images for tailored results.
Clear Error Handling: Provides straightforward management of potential errors related to prompt validation and API communication.
Easy Integration: Designed for hassle-free compatibility with MCP-compatible clients, streamlining the implementation process.

Image Generation MCP Server

A Model Context Protocol (MCP) server for generating high-quality images via Together AI. This server provides a standardized interface for image generation parameters.

Features

High-quality image generation powered by the Flux.1 Schnell model
Customizable dimensions (width and height)
Clear error handling for prompt validation and API issues
Easy integration with MCP-compatible clients

Installation

Claude Desktop

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

Development/Unpublished Servers Configuration

{
  "mcpServers": {
    "image-gen": {
      "command": "uv",
      "args": ["--directory", "/ABSOLUTE/PATH/TO/image-gen/", "run", "image-gen"],
      "env": {
        "TOGETHER_AI_API_KEY": "<API KEY>"
      }
    }
  }
}

Available Tools

generate_image

Generates an image based on the given textual prompt and optional dimensions.

Input Schema:

{
  "prompt": {
    "type": "string",
    "description": "A descriptive prompt for generating the image (e.g., 'a futuristic cityscape at sunset')"
  },
  "width": {
    "type": "integer",
    "description": "Width of the generated image in pixels (optional)"
  },
  "height": {
    "type": "integer",
    "description": "Height of the generated image in pixels (optional)"
  },
  "model": {
    "type": "string",
    "description": "The model name as it appears in Together AI. Defaults to (black-forest-labs/FLUX.1-schnell) if incorrect."
  }
}

Prerequisites

Python 3.12 or higher
httpx
mcp

Contributing

Contributions are welcome! Please follow these steps to contribute:

Fork the repository
Create a new branch (feature/my-new-feature)
Commit your changes
Push the branch to your fork
Open a Pull Request

For significant changes, please open an issue first to discuss any proposed changes.

License

This project is licensed under the MIT License. See the LICENSE file for details.

mcp-image-gen