dsh-cua
Related Servers
Alternatives to dsh-cua
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceThe local MCP server that gives any AI agent safe desktop control. Provides 6 compact tools (computer, accessibility, window, system, browser, task) for cross-platform GUI automation with ground-truth verification.1,048 npm404MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that gives any AI assistant eyes and hands on your desktop — screenshots, clicking, typing, OCR, window management, accessibility-tree queries, workflow recording.5Apache 2.0
- FlicenseNot gradedqualityBmaintenanceMCP server that enables AI agents to control Windows by clicking, typing, and navigating with a visible cursor overlay, using a layered approach (native UIA, browser CDP, pixel fallback) for reliable interaction.1-
- FlicenseNot gradedqualityBmaintenanceMCP 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.-
- AlicenseNot gradedqualityBmaintenanceMCP server for driving any Windows app through five layers including OCR, UI Automation, and direct OS operations. Enables AI agents to control Windows desktop and OS cursor-free, even on background/locked windows.66 npm2MIT
- AlicenseNot gradedqualityBmaintenanceA local MCP server that lets multiple AI agents safely share a Windows desktop by coordinating exclusive access to the mouse, keyboard, screen, and windows, with human consent, takeover, and full activity logging.1 npmMIT
TDQS
Scored across 19 tools
Several tools overlap in purpose: element_action (by ref) vs element_action_at (by skyshot index) perform virtually the same UI Automation action through different handles, and click_at, type_text, and element_action(set_value) can all deliver input to a control. The very detailed descriptions do help tell them apart (ref vs index, soft vs physical input), so an agent can navigate it, but the boundaries are not clean.
Every name is prefixed with tool_ and uses snake_case, giving a predictable surface. Most follow verb_noun (type_text, capture_window, list_windows), though a cluster of element/clipboard tools is noun-first (element_action, element_at_point, clipboard_read), a minor deviation rather than a real inconsistency.
19 tools is on the heavy side but splits cleanly across a broad domain (windows, elements, input, displays, clipboard, app launch, coexistence). Each entry maps to a distinct capability, so the count is justified despite being near the upper comfortable range.
Coverage of the desktop-automation lifecycle is strong: window/element discovery, tree-based and coordinate-based acting, keyboard, text typing, screenshots, clipboard, displays, and app launching are all present. Gaps are minor (no drag-and-drop, explicit scroll-wheel, or window move/resize/close), which agents can largely work around.