# Draw Things

> Use this tool when you need to generate images locally on Apple Silicon Macs using text or image prompts, and want control over parameters like dimensions and guidance scale. It solves problems like remote server dependencies and limited control over image generation, enabling use cases like art creation and design prototyping. The tool takes text or image inputs and produces generated images as output, with configurable settings for refinement and customization.

Canonical page: https://skillsregistry.net/skills/james-see-draw-things  
JSON: https://api.skillsregistry.net/v1/skills/james-see-draw-things

## Description

Integrates with the Draw Things application to provide local AI image generation capabilities on Apple Silicon Macs. Supports text-to-image generation and image-to-image transformations using locally loaded Stable Diffusion models. Provides tools for checking API status, retrieving configuration, and generating images with configurable parameters including dimensions, steps, guidance scale, and seed control.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/james-see-draw-things)
- **Repository:** <https://github.com/james-see/mcp-drawthings>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "james-see-draw-things"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/james-see-draw-things` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/james-see-draw-things/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt