drio
Open app

Together AI Image Server

Source

The server acts as a bridge between MCP-compatible assistants and Together AI's image generation capabilities.

Catalog onlyCatalog onlySTDIO

Overview

Together AI Image Server is a TypeScript-based server that acts as a bridge between MCP-compatible assistants and Together AI's image generation capabilities, allowing users to generate images from text prompts.

To use the server, clone the repository, install dependencies, set your Together AI API key, and configure it with compatible applications like Claude Desktop.

  • Generates images from text prompts using Together AI API. - Supports configuration for different environments. - Provides debugging tools through MCP Inspector.
  1. Generating custom images for creative projects.
  2. Assisting developers in integrating image generation into their applications.
  3. Enhancing user experiences in applications that require dynamic image content.

Add to your AI client

Use these steps to connect Together AI Image Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "together-ai-image-server-zym9863": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-ai-image-server-zym9863"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "together-ai-image-server-zym9863": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-ai-image-server-zym9863"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "together-ai-image-server-zym9863": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-ai-image-server-zym9863"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "together-ai-image-server-zym9863": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-ai-image-server-zym9863"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "together-ai-image-server-zym9863": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-ai-image-server-zym9863"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "together-ai-image-server-zym9863": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-ai-image-server-zym9863"
      ]
    }
  }
}

FAQ

What is the required environment to run the server?

Node.js (v14 or later) and a Together AI API key are required.

Can I use this server with other MCP-compatible assistants?

Yes, it is designed to work with any MCP-compatible assistant.

Is there a way to debug the server?

Yes, you can use the MCP Inspector for debugging.

Developer tools