Connects LLMs to Draw Things, the local Stable Diffusion app for Mac, so you can generate images without cloud APIs. Exposes text-to-image generation, image-to-image transformation, and configuration queries over Draw Things' local HTTP server on port 7860. Works entirely on-device using Apple Silicon. You'd reach for this when you want Claude or Cursor to create images during a conversation without leaving your machine or burning API credits. Saves generated images to your Pictures folder by default. Requires Draw Things installed with its API server enabled, which takes about thirty seconds to set up in the app settings.
An MCP (Model Context Protocol) server for Draw Things - enabling LLMs to generate images locally on Mac using Stable Diffusion and other AI models.
Verify the server is running:
curl http://localhost:7860
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"drawthings": {
"command": "npx",
"args": ["-y", "mcp-drawthings"]
}
}
}
Add to .cursor/mcp.json in your project or global config:
{
"mcpServers": {
"drawthings": {
"command": "npx",
"args": ["-y", "mcp-drawthings"]
}
}
}
Restart Claude Desktop or Cursor to load the new MCP server.
check_statusCheck if the Draw Things API server is running and accessible.
get_configGet the current Draw Things configuration including the loaded model and settings.
generate_imageGenerate an image from a text prompt.
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Yes | Text description of the image to generate |
negative_prompt | string | No | Elements to exclude from the generated image |
width | number | No | Image width in pixels (default: 512) |
height | number | No | Image height in pixels (default: 512) |
steps | number | No | Number of inference steps (default: 20) |
cfg_scale | number | No | Guidance scale (default: 7.5) |
seed | number | No | Random seed for reproducibility (-1 for random) |
output_path | string | No | Custom file path to save the image |
Example:
Generate an image of a futuristic city at sunset with flying cars
transform_imageTransform an existing image using a text prompt (img2img).
Parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Yes | Text description of the desired transformation |
image_path | string | No* | Path to the source image file |
image_base64 | string | No* | Base64-encoded source image |
negative_prompt | string | No | Elements to exclude |
denoising_strength | number | No | Transformation strength 0.0-1.0 (default: 0.75) |
steps | number | No | Number of inference steps (default: 20) |
cfg_scale | number | No | Guidance scale (default: 7.5) |
seed | number | No | Random seed (-1 for random) |
output_path | string | No | Custom file path to save the result |
*Either image_path or image_base64 must be provided.
| Variable | Default | Description |
|---|---|---|
DRAWTHINGS_HOST | localhost | Draw Things API host |
DRAWTHINGS_PORT | 7860 | Draw Things API port |
DRAWTHINGS_OUTPUT_DIR | ~/Pictures/drawthings-mcp | Directory for generated images |
┌─────────────────┐ stdio ┌──────────────────┐ HTTP ┌─────────────┐
│ MCP Client │◄──────────────►│ mcp-drawthings │◄────────────►│ Draw Things │
│ (Claude/Cursor) │ JSON-RPC │ │ localhost │ App │
└─────────────────┘ └──────────────────┘ :7860 └─────────────┘
│
▼
┌──────────────┐
│ File System │
│ (images) │
└──────────────┘
# 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
curl http://localhost:7860Check that the output directory is writable. You can set a custom directory using the DRAWTHINGS_OUTPUT_DIR environment variable.
MIT