# Windows Desktop Control

> Use this tool when you need to automate Windows desktop interactions, such as launching applications or executing commands, and require a lightweight interface for AI agents to control the operating system. It solves problems related to workflow automation, application testing, and enabling AI assistants to interact with Windows environments. The tool accepts commands and inputs, and outputs desktop state information, making it ideal for use cases that require direct desktop control and automation.

Canonical page: https://skillsregistry.net/skills/computer-agent-windows-desktop-control  
JSON: https://api.skillsregistry.net/v1/skills/computer-agent-windows-desktop-control

## Description

Windows MCP Server provides a lightweight interface for AI agents to interact with the Windows operating system through a set of specialized tools. Developed by Jeomon George, it leverages UIAutomation, PyAutoGUI, and other libraries to enable desktop automation capabilities including launching applications, executing PowerShell commands, retrieving desktop state information, and performing mouse/keyboard actions. The implementation features a tree-based approach to identify interactive UI elements across applications, making it particularly valuable for automating workflows, testing applications, or enabling AI assistants to directly control Windows desktop environments like a human user would.

## 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:** 2026-05-27

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/computer-agent-windows-desktop-control)
- **Repository:** <https://github.com/cursortouch/windows-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": "computer-agent-windows-desktop-control"
    }
  }
}
```

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