Together AI Image

Provides an MCP endpoint to generate images using Together AI models with configurable prompts and output options.

javascript

7

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "stefanskiasan-togetherai-image-mcp-server": {
      "command": "node",
      "args": [
        "/path/to/togetherai-image-server/build/index.js"
      ],
      "env": {
        "TOGETHER_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

This MCP server lets you generate images using Together AI models directly from an MCP client. You provide a text prompt and optional parameters, and the server returns image data along with metadata, making it easy to integrate image generation into your workflows.

How to use

To generate an image, call the generate_image tool from your MCP client. Provide a prompt describing the scene you want and any optional parameters you wish to tweak. The server uses Together AI's FLUX.1.1-pro model by default and will resize images if requested dimensions are too small, while preserving aspect ratio. You will receive a response that includes the path to the saved image, the file name, and both the original and final image dimensions.

How to install

Prerequisites you need before installing this MCP server:

Node.js and npm installed on your system
Network access to fetch dependencies and reach the Together AI API

Install dependencies and build the server using the following commands. Run these in the project root where the server sources reside.

npm install

npm run build

Configure the MCP server in your client settings

Configure the Together AI image MCP server in your client’s MCP settings to run locally. You must provide your Together AI API key to authorize image generation.

{
  "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 details for generate_image tool

The server exposes a generate_image tool with configurable options. You can set a model, image dimensions, sampling steps, number of images to generate, and the output directory where results will be saved. If you omit optional fields, sensible defaults are used.

Output

The tool returns a JSON payload that includes the following fields: filepath (full path to the saved image), filename (saved image file name), and dimensions (both the original and final image sizes).

Notes and features

Key features include support for the latest Together AI model (FLUX.1.1-pro), automatic resizing with aspect ratio preserved, high-quality JPEG output, recursive output directory creation, and rich metadata about image dimensions.

Available tools

generate_image

Generates an image based on a text prompt with optional model, dimensions, steps, and output options. Returns the saved image path, filename, and dimension metadata.