Together Ai Image Server

🚀 Together AI Image Server

A TypeScript-based MCP (Model Context Protocol) server for generating images via the Together AI API.

🚀 Quick Start

This server offers a straightforward interface to generate images using Together AI's image generation models through the MCP protocol. It enables Claude and other MCP-compatible assistants to generate images based on text prompts.

✨ Features

Tools

• generate_image - Generate an image from a text prompt
  • Accepts a text prompt as a required parameter
  • Optional parameters to control the number of generation steps and the number of images
  • Returns the URL and local path of the generated image

📦 Installation

Prerequisites

• Node.js (v14 or higher recommended)
• Together AI API key

# Clone the repository
git clone https://github.com/zym9863/together-ai-image-server.git
cd together-ai-image-server

# Install dependencies
npm install

Configuration

Set your Together AI API key as an environment variable:

# On Linux/macOS
export TOGETHER_API_KEY="your-api-key-here"

# On Windows (Command Prompt)
set TOGETHER_API_KEY=your-api-key-here

# On Windows (PowerShell)
$env:TOGETHER_API_KEY="your-api-key-here"

Alternatively, you can create a .env file in the project root directory:

TOGETHER_API_KEY=your-api-key-here

Development

Build the server:

npm run build

Develop with automatic rebuild:

npm run watch

Usage with Claude Desktop

To use it with Claude Desktop, add the server configuration:

On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json%

{
  "mcpServers": {
    "Together AI Image Server": {
      "command": "/path/to/together-ai-image-server/build/index.js"
    }
  }
}

Replace /path/to/together-ai-image-server with the actual installation path.

Debugging

Debugging can be challenging since MCP servers communicate via stdio. We recommend using MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL in your browser to access the debugging tools.

📚 Documentation

API Reference

generate_image

Generate an image using Together AI's image generation API based on a text prompt.

Parameters:

• prompt (string, required): Text prompt for image generation
• steps (number, optional, default: 4): Number of diffusion steps (1 - 4)
• n (number, optional)