# Windows Desktop Automation

> Use this tool when you need to automate interactions with the Windows operating system, launch applications, or perform UI automation tasks. It solves problems related to desktop automation, QA testing, and system interaction by providing programmatic control of applications and UI elements. The tool accepts inputs such as PowerShell commands and mouse/keyboard actions, and outputs desktop state and UI element interactions, making it ideal for AI agents requiring direct Windows system control.

Canonical page: https://skillsregistry.net/skills/cursortouch-windows-desktop-automation  
JSON: https://api.skillsregistry.net/v1/skills/cursortouch-windows-desktop-automation

## Description

Windows MCP server by Jeomon George that enables AI assistants to directly interact with the Windows operating system through native UI automation and system control. Built using Python with uiautomation, pyautogui, and fastmcp, the implementation provides tools for launching applications, capturing desktop state with interactive UI elements, performing mouse and keyboard actions, window management, clipboard operations, and PowerShell command execution. The server uses UI automation to identify clickable elements, text fields, and scrollable areas without relying on computer vision, making it work with any LLM while maintaining 1.5-2.3 second latency between actions. Designed for AI agents performing desktop automation tasks, QA testing workflows, and general Windows system interaction where programmatic control of applications and UI elements is needed.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/cursortouch-windows-desktop-automation)

## 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": "cursortouch-windows-desktop-automation"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/cursortouch-windows-desktop-automation` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/cursortouch-windows-desktop-automation/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