Image Generation MCP Server

MCP server enabling high-quality image generation via Together AI's Flux.1 Schnell model.

Catalog onlyCatalog onlySTDIO

Overview

Together MCP Server is a Model Context Protocol (MCP) server that enables seamless generation of high-quality images using Together AI's Flux.1 Schnell model.

To use the Together MCP Server, install it via npm and configure it with your Together AI API key. You can then use the generate_image tool to create images by providing a text prompt.

High-quality image generation powered by the Flux.1 Schnell model - Support for customizable dimensions (width and height) - Clear error handling for prompt validation and API issues - Easy integration with MCP-compatible clients - Optional image saving to disk in PNG format

Generating artistic images based on textual descriptions.
Creating images for marketing materials or social media posts.
Developing applications that require dynamic image generation.

Add to your AI client

Use these steps to connect Image Generation MCP 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-mcp-server-manascb1344": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-mcp-server-manascb1344"
      ]
    }
  }
}

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-mcp-server-manascb1344": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-mcp-server-manascb1344"
      ]
    }
  }
}

Claude Code

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

.mcp.json (project root)

{
  "mcpServers": {
    "together-mcp-server-manascb1344": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-mcp-server-manascb1344"
      ]
    }
  }
}

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-mcp-server-manascb1344": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-mcp-server-manascb1344"
      ]
    }
  }
}

Windsurf

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

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "together-mcp-server-manascb1344": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-mcp-server-manascb1344"
      ]
    }
  }
}

Cline

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

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "together-mcp-server-manascb1344": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-together-mcp-server-manascb1344"
      ]
    }
  }
}

FAQ

What is the required parameter for generating an image?

The only required parameter is the prompt, which describes the image to generate.

Can I customize the dimensions of the generated images?

Yes! You can specify the width and height of the images within the allowed range.

Is there a way to save the generated images?

Yes! You can specify a path to save the generated image in PNG format.

Research and data

Image Generation MCP Server — MCP Registry