PluginBench
MCP Server
Stale
MIT

io.github.james-see/mcp-drawthings MCP Server

io.github.james-see/mcp-drawthings

Generate images locally on Mac using Draw Things and Stable Diffusion via Claude or Cursor.

What is the io.github.james-see/mcp-drawthings MCP server?

The mcp-drawthings MCP server enables LLMs to generate and transform images locally on Mac using Draw Things, which runs Stable Diffusion and other AI models on Apple Silicon. It provides text-to-image and image-to-image capabilities without sending data to external services.

This server bridges Claude and Cursor with Draw Things, a local AI image generation app for Mac. You can generate images from text prompts, transform existing images, and query Draw Things configuration—all processing happens locally on your Mac's Apple Silicon chip.

How to install io.github.james-see/mcp-drawthings

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "mcp-drawthings": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-drawthings"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • check_status — Check if the Draw Things API server is running and accessible.
  • get_config — Get the current Draw Things configuration including the loaded model and settings.
  • generate_image — Generate an image from a text prompt with customizable parameters like dimensions, inference steps, guidance scale, and seed.
  • transform_image — Transform an existing image using a text prompt (image-to-image) with control over denoising strength and other generation parameters.

Use cases

  • Generate concept art and visual designs directly within Claude or Cursor without leaving your editor
  • Transform and iterate on existing images using natural language descriptions
  • Create illustrations and mockups locally while maintaining privacy and avoiding API costs
  • Batch generate variations of images by adjusting prompts, seeds, and parameters
  • Integrate AI image generation into creative workflows on Mac with full local processing

io.github.james-see/mcp-drawthings MCP server FAQ

What is mcp-drawthings?

It's an MCP server that connects Claude or Cursor to Draw Things, a local AI image generation app for Mac, enabling text-to-image and image-to-image generation using Stable Diffusion.

Is it free to use?

Yes, mcp-drawthings is open-source (MIT license). Draw Things is also free, though it requires macOS with Apple Silicon (M1/M2/M3/M4).

How do I install it in Claude Desktop?

Add the server to ~/Library/Application Support/Claude/claude_desktop_config.json with the command 'npx -y mcp-drawthings', then restart Claude Desktop.

How do I install it in Cursor?

Add the server to .cursor/mcp.json in your project or global config with the command 'npx -y mcp-drawthings', then restart Cursor.

Do I need an API key or authentication?

No API key required. You only need Draw Things installed and its API Server enabled in settings (runs on localhost:7860 by default).

What are the system requirements?

macOS with Apple Silicon (M1/M2/M3/M4), Draw Things app installed, and Node.js 18 or later.

README (reference)

Source of truth, from the repository.

mcp-drawthings

An MCP (Model Context Protocol) server for Draw Things - enabling LLMs to generate images locally on Mac using Stable Diffusion and other AI models.

Features

  • Text-to-Image Generation - Generate images from text prompts using the currently loaded model in Draw Things
  • Image-to-Image Transformation - Transform existing images using text prompts
  • Configuration Access - Query the current Draw Things settings and loaded model
  • Local Processing - All image generation runs locally on your Mac using Apple Silicon (M1/M2/M3/M4)

Prerequisites

  • macOS with Apple Silicon (M1/M2/M3/M4)
  • Draw Things app installed
  • Node.js 18 or later

Setup

1. Enable Draw Things API Server

  1. Open Draw Things
  2. Click the gear icon (⚙️) to open Settings
  3. Enable API Server / HTTP Server
  4. The server runs on port 7860 by default

Verify the server is running:

curl http://localhost:7860

2. Configure Your MCP Client

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "drawthings": {
      "command": "npx",
      "args": ["-y", "mcp-drawthings"]
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project or global config:

{
  "mcpServers": {
    "drawthings": {
      "command": "npx",
      "args": ["-y", "mcp-drawthings"]
    }
  }
}

3. Restart Your MCP Client

Restart Claude Desktop or Cursor to load the new MCP server.

Available Tools

check_status

Check if the Draw Things API server is running and accessible.

get_config

Get the current Draw Things configuration including the loaded model and settings.

generate_image

Generate an image from a text prompt.

Parameters:

ParameterTypeRequiredDescription
promptstringYesText description of the image to generate
negative_promptstringNoElements to exclude from the generated image
widthnumberNoImage width in pixels (default: 512)
heightnumberNoImage height in pixels (default: 512)
stepsnumberNoNumber of inference steps (default: 20)
cfg_scalenumberNoGuidance scale (default: 7.5)
seednumberNoRandom seed for reproducibility (-1 for random)
output_pathstringNoCustom file path to save the image

Example:

Generate an image of a futuristic city at sunset with flying cars

transform_image

Transform an existing image using a text prompt (img2img).

Parameters:

ParameterTypeRequiredDescription
promptstringYesText description of the desired transformation
image_pathstringNo*Path to the source image file
image_base64stringNo*Base64-encoded source image
negative_promptstringNoElements to exclude
denoising_strengthnumberNoTransformation strength 0.0-1.0 (default: 0.75)
stepsnumberNoNumber of inference steps (default: 20)
cfg_scalenumberNoGuidance scale (default: 7.5)
seednumberNoRandom seed (-1 for random)
output_pathstringNoCustom file path to save the result

*Either image_path or image_base64 must be provided.

Configuration

Environment Variables

VariableDefaultDescription
DRAWTHINGS_HOSTlocalhostDraw Things API host
DRAWTHINGS_PORT7860Draw Things API port
DRAWTHINGS_OUTPUT_DIR~/Pictures/drawthings-mcpDirectory for generated images

Architecture

┌─────────────────┐     stdio      ┌──────────────────┐     HTTP      ┌─────────────┐
│   MCP Client    │◄──────────────►│  mcp-drawthings  │◄────────────►│ Draw Things │
│ (Claude/Cursor) │   JSON-RPC     │                  │  localhost    │    App      │
└─────────────────┘                └──────────────────┘   :7860       └─────────────┘
                                           │
                                           ▼
                                   ┌──────────────┐
                                   │  File System │
                                   │   (images)   │
                                   └──────────────┘

Development

# Clone the repository
git clone https://github.com/james-see/mcp-drawthings
cd mcp-drawthings

# Install dependencies
npm install

# Build
npm run build

# Run in development mode
npm run dev

Troubleshooting

"Cannot connect to Draw Things API"

  1. Make sure Draw Things is running
  2. Check that the API Server is enabled in Draw Things settings
  3. Verify the server is accessible: curl http://localhost:7860
  4. Check if a different port is configured in Draw Things

Images not generating

  1. Make sure a model is loaded in Draw Things
  2. Check Draw Things for any error messages
  3. Try generating an image directly in Draw Things first

Permission errors saving images

Check that the output directory is writable. You can set a custom directory using the DRAWTHINGS_OUTPUT_DIR environment variable.

License

MIT

Related Projects

Related MCP servers

Incident forensic with log files analyzing

1
Python
View repository →

Free lockfile malware check plus paid behavioral scan of packages, agent skills and MCP tools.

0
JavaScript
MIT
View repository →

MCP server providing monkey data, journeys, and location services for various monkey species.

123
Jupyter Notebook
MIT
View repository →

Design beautiful terminal prompts visually without editing JSON—drag, drop, customize, and export Oh My Posh configurations.

130
TypeScript
View repository →
WIWiggle logo

Wiggle

Active

A coordination layer for autonomous agents: rooms, messaging, inbox, roles, and polls.

0
Python
MIT
View repository →

Make money with x402. See what's earning, find profitable gaps, and price your service right.

View repository →