desktop-touch
Harusame64/desktop-touch-mcp
Windows desktop automation with entity-based actions instead of coordinate clicks, using UIA, CDP, screenshots, keyboard, mouse, clipboard and terminal control.
- Local integrations
Installation, supported tools and required credentials are maintained by the project.
Project details
- GitHub stars
- 22
- Language
- TypeScript
- License
- MIT
- Forks
- 5
- Latest release
- v2.3.19d ago
- Activity
- updated 1d ago
- Platforms listed
- Windows
- claude
- desktop-automation
- llm
- mcp
- ui-automation
- windows
- agent
- anthropic
First MCP server?Start with the basics
Local macOS servers for Mail, Calendar, Reminders, Messages, Contacts, Notes, Shortcuts, Files, Maps and system tools, unified or standalone.
Inspect, debug and drive running WPF apps without source changes: visual tree, dependency properties, bindings, DataContext, screenshots, clicks and text input.
Drive native GUI apps under development: launch, screenshot, read the accessibility tree, inject input, tail logs and diff frames on desktop, Android and iOS.
Mac window manager and menu bar utilities: arrange windows across displays, snap to custom zones, save workspaces, window screenshots and on-device OCR.
Accessibility-first computer use on macOS, Windows and Linux: element IDs instead of pixels, background input, a pointer overlay and its own Chrome tab group.
GNOME desktop automation via D-Bus: screenshots, window management, mouse and keyboard input, clipboard, workspaces and notifications on GNOME 45 to 49.
Read-only desktop context through OpenWand: current selection, clipboard, active window, browser page and screen.
Physical USB HID keyboard and mouse control via a Raspberry Pi Pico 2: move, click, drag, type, key combos and scroll, with a mock mode for testing.