# winauto-mcp

> winauto-mcp — pingpong2534-winauto-mcp. Use this tool when you need to automate interactions with Windows applications, as it enables attaching to a window, capturing screenshots, and sending inputs like clicks and keystrokes. It solves problems like automating tasks in legacy apps or integrating with existing Windows workflows. The tool accepts window handles and pixel coordinates as inputs and outputs UI Automation trees and screenshot data.

Canonical page: https://skillsregistry.net/skills/pingpong2534-winauto-mcp  
JSON: https://api.skillsregistry.net/v1/skills/pingpong2534-winauto-mcp

## Description

MCP server that lets an LLM see and drive any running Windows app: attach a window, screenshot it, read its UI Automation tree, and send clicks, typed text, and key presses with pixel coordinates.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/jg6yv45zai)
- **Repository:** <https://github.com/PingPong2534/winauto-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": "pingpong2534-winauto-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/pingpong2534-winauto-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/pingpong2534-winauto-mcp/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