Draw Things MCP

Draw Things MCP

An integration that allows Cursor AI to generate images through the Draw Things API using natural language prompts.

jaokuohsuan

Image & Video Processing
Visit Server

Tools

generateImage

Generate an image based on a prompt

README

Draw Things MCP

Draw Things API integration for Cursor using Model Context Protocol (MCP).

Prerequisites

  • Node.js >= 14.0.0
  • Draw Things API running on http://127.0.0.1:7888

Installation

# Install globally
npm install -g draw-things-mcp-cursor

# Or run directly
npx draw-things-mcp-cursor

Cursor Integration

To set up this tool in Cursor, see the detailed guide in cursor-setup.md.

Quick setup:

  1. Create or edit ~/.cursor/claude_desktop_config.json:
{
  "mcpServers": {
    "draw-things": {
      "command": "draw-things-mcp-cursor",
      "args": []
    }
  }
}
  1. Restart Cursor
  2. Use in Cursor: generateImage({"prompt": "a cute cat"})

CLI Usage

Generate Image

echo '{"prompt": "your prompt here"}' | npx draw-things-mcp-cursor

Parameters

  • prompt: The text prompt for image generation (required)
  • negative_prompt: The negative prompt for image generation
  • width: Image width (default: 360)
  • height: Image height (default: 360)
  • steps: Number of steps for generation (default: 8)
  • model: Model to use for generation (default: "flux_1_schnell_q5p.ckpt")
  • sampler: Sampling method (default: "DPM++ 2M AYS")

Example:

echo '{
  "prompt": "a happy smiling dog, professional photography",
  "negative_prompt": "ugly, deformed, blurry",
  "width": 360,
  "height": 360,
  "steps": 4
}' | npx draw-things-mcp-cursor

MCP Tool Integration

When used as an MCP tool in Cursor, the tool will be registered as generateImage with the following parameters:

{
  prompt: string;       // Required - The prompt to generate the image from
  negative_prompt?: string;  // Optional - The negative prompt
  width?: number;       // Optional - Image width (default: 360)
  height?: number;      // Optional - Image height (default: 360)
  model?: string;       // Optional - Model name
  steps?: number;       // Optional - Number of steps (default: 8)
}

The generated images will be saved in the images directory with a filename format of: <sanitized_prompt>_<timestamp>.png

Response Format

Success:

{
  "type": "success",
  "content": [{
    "type": "image",
    "data": "base64 encoded image data",
    "mimeType": "image/png"
  }],
  "metadata": {
    "parameters": { ... }
  }
}

Error:

{
  "type": "error",
  "error": "error message",
  "code": 500
}

Troubleshooting

If you encounter issues:

  • Ensure Draw Things API is running at http://127.0.0.1:7888
  • Check log files in ~/.cursor/logs if using with Cursor
  • Make sure src/index.js has execution permissions: chmod +x src/index.js

License

MIT

Recommended Servers

Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
@kazuph/mcp-fetch

@kazuph/mcp-fetch

Model Context Protocol server for fetching web content and processing images. This allows Claude Desktop (or any MCP client) to fetch web content and handle images appropriately.

Featured
Local
JavaScript
mcp-pinterest

mcp-pinterest

A Pinterest Model Context Protocol (MCP) server for image search and information retrieval

Featured
TypeScript
mermaid-mcp-server

mermaid-mcp-server

A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.

Featured
JavaScript
ScreenshotOne MCP Server

ScreenshotOne MCP Server

An official MCP server implementation that allows AI assistants to capture website screenshots through the ScreenshotOne API, enabling visual context from web pages during conversations.

Official
TypeScript
Glif

Glif

Run AI workflows hosted on Glif.app via MCP, including ComfyUI-based image generators, meme generators, selfies, chained LLM calls, and more

Official
TypeScript
DeepSRT MCP Server

DeepSRT MCP Server

An MCP server that enables users to generate summaries of YouTube videos in multiple languages and formats through integration with DeepSRT's API.

Official
JavaScript
Frontend Review MCP

Frontend Review MCP

An MCP server that visually reviews UI edit requests by comparing screenshots before and after edits, ensuring changes satisfy user requests.

Local
JavaScript
MCP Media Processing Server

MCP Media Processing Server

A Node.js server that provides advanced video and image processing capabilities through the Model Context Protocol, enabling operations like conversion, compression, editing, and effects application.

Local
JavaScript
Youtube MCP Server

Youtube MCP Server

Bridges YouTube API and AI assistants, enabling video analysis by downloading and processing closed captions to create summaries of YouTube videos.

Local
Python