# desktop-touch-mcp

> desktop-touch-mcp — harusame64-desktop-touch-mcp. Use this tool when you need to automate Windows desktop interactions, such as taking screenshots, simulating mouse and keyboard input, and automating UI elements. It solves problems like automating repetitive tasks, testing desktop applications, and integrating with large language models (LLMs) using token-efficient P-frame diffing. The tool accepts input commands and outputs automated desktop interactions, making it ideal for use cases requiring efficient and automated desktop control.

Canonical page: https://skillsregistry.net/skills/harusame64-desktop-touch-mcp  
JSON: https://api.skillsregistry.net/v1/skills/harusame64-desktop-touch-mcp

## Description

Windows computer-use MCP server: drive any desktop app via semantic discover-then-act targeting (entities + leases, not pixel coordinates), with per-action perception guards, a native Rust UIA engine, Chrome CDP, and Key Locker credential autofill for ssh/sudo password prompts. Works with Claude, Cursor, and any MCP client.

## Trust

- **Trust score (0–1):** 0.38
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Harusame64/desktop-touch-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": "harusame64-desktop-touch-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/harusame64-desktop-touch-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/harusame64-desktop-touch-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