# macOS Computer Use

> Use this tool when you need to automate interactions with macOS systems, control user interface elements, or capture visual data. It solves problems related to automated testing, workflow automation, and data extraction by providing native control over mouse and keyboard input, screenshot capture, and application management. With stdio transport and native Swift modules, it enables seamless integration with AI agents to drive real macOS interactions.

Canonical page: https://skillsregistry.net/skills/zooeyii-macos-computer-use  
JSON: https://api.skillsregistry.net/v1/skills/zooeyii-macos-computer-use

## Description

macOS Computer Use provides 24 tools for AI agents to interact with macOS natively — controlling mouse input, typing, key presses, capturing screenshots, querying the accessibility tree, and managing applications. It uses native Swift and input injection modules to drive real macOS interactions over stdio transport.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/zooeyii-macos-computer-use)
- **Repository:** <https://github.com/zooeyii/macos-computer-use-mcp>

## 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": "zooeyii-macos-computer-use"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zooeyii-macos-computer-use` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zooeyii-macos-computer-use/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
