# ScreenHand

> Use this tool when you need to automate desktop interactions on macOS and Windows, leveraging Accessibility APIs, UI Automation, OCR, and Chrome DevTools Protocol to control UI elements, simulate keyboard and mouse input, and capture screenshots. ScreenHand provides a robust interface for AI assistants to interact with desktop environments, solving automation challenges in various use cases. It offers 82 tools for tasks such as browser automation, session management, and multi-agent coordination, making it an ideal solution for complex automation requirements.

Canonical page: https://skillsregistry.net/skills/gh-manushi4-screenhand  
JSON: https://api.skillsregistry.net/v1/skills/gh-manushi4-screenhand

## Description

Open-source MCP server providing desktop automation on macOS and Windows. Gives AI assistants fast control via Accessibility APIs, UI Automation, OCR, and Chrome DevTools Protocol. Features 82 tools for screenshots, UI element interaction, keyboard/mouse control, browser automation, and multi-agent coordination with session management.

## 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:** browser-automation
- **Updated:** 2026-05-21

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gh-manushi4-screenhand)
- **Repository:** <https://github.com/manushi4/screenhand>

## 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": "gh-manushi4-screenhand"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gh-manushi4-screenhand` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gh-manushi4-screenhand/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