The Together AI Image Server allows you to generate images from text prompts using Together AI's API. With this server, you can:
- Generate Images: Create images based on text descriptions
- Control Output: Specify the number of images (1-4) and diffusion steps (1-4)
- Receive Results: Get URLs and local paths to the generated images
- Integration: Works as an MCP server, compatible with MCP-compatible assistants like Claude Desktop
Together AI Image Server
English | 简体中文
A TypeScript-based MCP (Model Context Protocol) server for generating images using Together AI API.
Overview
This server provides a simple interface to generate images using Together AI's image generation models through the MCP protocol. It allows Claude and other MCP-compatible assistants to generate images based on text prompts.
Features
Tools
generate_image
- Generate images from text prompts- Takes a text prompt as required parameter
- Optional parameters for controlling generation steps and number of images
- Returns URLs and local paths to generated images
Prerequisites
- Node.js (v14 or later recommended)
- Together AI API key
Installation
Configuration
Set your Together AI API key as an environment variable:
Alternatively, you can create a .env
file in the project root:
Development
Build the server:
For development with auto-rebuild:
Usage with Claude Desktop
To use with Claude Desktop, add the server config:
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
Replace /path/to/together-ai-image-server
with the actual path to your installation.
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
The Inspector will provide a URL to access debugging tools in your browser.
API Reference
generate_image
Generates images based on a text prompt using Together AI's image generation API.
Parameters:
prompt
(string, required): Text prompt for image generationsteps
(number, optional, default: 4): Number of diffusion steps (1-4)n
(number, optional, default: 1): Number of images to generate (1-4)
Returns:
JSON object containing:
image_urls
: Array of URLs to the generated imageslocal_paths
: Array of paths to locally cached images
License
MIT
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Tools
A MCP server that enables Claude and other MCP-compatible assistants to generate images from text prompts using Together AI's image generation models.
- Overview
- Features
- Prerequisites
- Installation
- Configuration
- Development
- Usage with Claude Desktop
- Debugging
- API Reference
- License
- Contributing
Related Resources
Related MCP Servers
- AsecurityAlicenseAqualityEnables the generation of images using Together AI's models through an MCP server, supporting customizable parameters such as model selection, image dimensions, and output directory.Last updated -17JavaScriptMIT License
- AsecurityFlicenseAqualityA TypeScript-based MCP server that generates images using OpenAI's dall-e-3 model based on text prompts and saves them to a specified directory.Last updated -110JavaScript
- AsecurityAlicenseAqualityAllows AI assistants to generate and transform high-quality images from text prompts using Google's Gemini model via the MCP protocol.Last updated -316PythonMIT License
- -securityFlicense-qualityAn MCP image generation server based on the Flux Schnell model that provides API access for generating images from text prompts with customizable dimensions and seeds.Last updated -1Python