Togetherai Image MCP Server

🚀 Together AI Image Server

This is an MCP server designed to generate images using Together AI's image generation models. It offers a convenient way to leverage advanced AI capabilities for image creation.

🚀 Quick Start

📦 Installation

1. Install the dependencies:

npm install

2. Build the server:

npm run build

⚙️ Configuration

1. Together AI API Key

This server requires a Together AI API key. You can obtain it 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

{
  "mcpServers": {
    "togetherai-image": {
      "command": "node",
      "args": ["/path/to/togetherai-image-server/build/index.js"],
      "env": {
        "TOGETHER_API_KEY": "your-api-key-here"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

💻 Usage Examples

Basic Usage

The server provides a generate_image tool with the following parameters:

{
  prompt: string;           // Required: Text description of the image
  model?: string;          // Optional: Model to use (Default: 'black-forest-labs/FLUX.1.1-pro')
  width?: number;          // Optional: Image width in pixels (Default: 1024)
  height?: number;         // Optional: Image height in pixels (Default: 768)
  steps?: number;         // Optional: Number of inference steps (Default: 28)
  n?: number;             // Optional: Number of images to generate (Default: 1)
  outputDir?: string;     // Optional: Directory to save the images (Default: './output')
}

Example Usage

You can use the server in Cline like this:

Generate a picture of a cute cat sitting on a windowsill and save it to my desktop:

<use_mcp_tool>
<server_name>togeherai-image</server_name>
<tool_name>generate_image</tool_name>
<arguments>
{
  "prompt": "A cute cat sitting on a windowsill",
  "outputDir": "/Users/username/Desktop/generated-images"
}
</arguments>
</use_mcp_tool>

Output

The tool returns a JSON response containing:

• filepath: The full path where the image is saved
• filename: The filename of the saved image
• dimensions: The original and final image dimensions