Give AI eyes and hands on your desktop. ScreenHand is an open-source MCP server that lets Claude and other AI agents see your screen, click buttons
Screenhand MCP server exists for a simple reason — assistants are far more useful when they can act on Screenhand directly instead of describing what you should do. Give AI eyes and hands on your desktop. ScreenHand is an open-source MCP server that lets Claude and other AI agents see your screen, click buttons, type text, and control any app on macOS and Windows.
An open-source MCP server for macOS and Windows. Works with Claude, Cursor, Codex CLI, and any MCP-compatible client.
The server ships on npm as screenhand, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
| | macOS | Windows | |---|---|---| | OS | macOS 12+ | Windows 10 (1809+) | | Runtime | Node.js 18+ | Node.js 18+ | | Native | Swift (included) | .NET 8 SDK | | Permissions | Accessibility access for terminal | None (UI Automation works without admin) | | Browser | Chrome with --remote-debugging-port=9222 | Same |
This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. It is maintained by manushi4; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Screenhand's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
{
"mcpServers": {
"screenhand": {
"command": "npx",
"args": ["-y", "screenhand"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| | macOS | Windows | |---|---|---| | OS | macOS 12+ | Windows 10 (1809+) | | Runtime | Node.js 18+ | Node.js 18+ | | Native | Swift (included) | .NET 8 SDK | | Permissions | Accessibility access for terminal | None (UI Automation works without admin) | | Browser | Chrome with --remote-debugging-port=9222 | Same |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.