Together AI Image Generation MCP server

This MCP server enables image generation through Together AI, providing a standardized interface to create high-quality images with customizable parameters. It implements the Model Context Protocol (MCP) to seamlessly integrate with compatible clients.

Installation

Prerequisites

• Python 3.12 or higher
• A Together AI API key

Setup

For Claude Desktop users, you need to modify the configuration file:

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

Add the following configuration to the file:

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

Make sure to:

• Replace /ABSOLUTE/PATH/TO/image-gen/ with the actual path to your installation
• Replace <API KEY> with your Together AI API key

Usage

Generate Image Tool

The server provides a single tool called generate_image that creates images based on text prompts.

Input Parameters

• prompt (required): A descriptive text prompt (e.g., "a futuristic cityscape at sunset")
• width (optional): Width of the image in pixels
• height (optional): Height of the image in pixels
• model (optional): The specific Together AI model to use (defaults to black-forest-labs/FLUX.1-schnell)

Example Usage

When using an MCP-compatible client like Claude Desktop, you can request image generation with:

Can you generate an image of a mountain landscape at sunset?

For more specific dimensions:

Generate an image of a cat playing with yarn, with dimensions 1024x768.

To specify a particular model:

Using the model black-forest-labs/FLUX.1-schnell, generate an image of space explorers on an alien planet.

Features

• High-quality images: Powered by the Flux.1 Schnell model from Together AI
• Customizable dimensions: Specify your preferred width and height
• Error handling: Clear feedback for invalid prompts or API issues
• Seamless integration: Works with any MCP-compatible client

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.