desktop-touch-mcp
Related Servers
Alternatives to desktop-touch-mcp
- AlicenseAqualityBmaintenanceAllow AI agents to see and control a real Windows PC you own: observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH — your machine, your key.16Apache 2.0
Related Servers
- FlicenseAqualityCmaintenanceWindows desktop automation MCP server enabling screenshot capture, precise visual locating of UI elements via vision models, and automated mouse clicking.41-
- FlicenseNot gradedqualityAmaintenanceMCP 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 gradedqualityBmaintenanceGUI automation MCP server that enables AI agents to see and control the Windows desktop using a local Vision LLM (Ollama), supporting screenshot analysis, mouse/keyboard actions, and autonomous task execution.4MIT
- AlicenseNot gradedqualityBmaintenanceMCP server providing AI-friendly computer-use primitives (capture, detect, click) to let LLM agents drive desktop GUI applications on Windows, macOS, and Linux.1MIT
- FlicenseAqualityAmaintenanceCross-platform desktop automation MCP server that lets AI agents capture screenshots, run OCR with UI-element classification, control mouse/keyboard, and launch programs on Linux, macOS, and Windows.201-
- AlicenseNot gradedqualityBmaintenanceA Windows computer use agent — FastMCP server that gives AI assistants hands on the real desktop: windows, UI elements, mouse, keyboard, screenshots, OCR, shortcuts, dialogs, and outcome verification.40MIT
TDQS
Scored across 30 tools
Each tool has a well-defined primary purpose with detailed 'Prefer' guidance, but there is some overlap between screenshot (text/som detail), desktop_state, and workspace_snapshot as observation tools, and the three click-related tools (browser_click, click_element, mouse_click) require careful reading of descriptions to distinguish. Overall, the boundaries are mostly clear.
The browser_* and screenshot_* prefixes are consistent, but the overall convention is mixed: bare nouns (keyboard, terminal, scroll, excel, clipboard) coexist with verb_noun (focus_window, click_element, wait_until) and noun_verb (mouse_click, mouse_drag) patterns. This inconsistency makes predicting tool names by analogy difficult.
30 tools is on the heavy side, but the server covers multiple subdomains (browser automation, native UI control, terminal interaction, clipboard, Excel macros, window management, screenshot caching), so each tool roughly earns its place. Still, the count exceeds the comfortable 3-15 range and approaches the limit where discoverability suffers.
The surface covers most core operations for desktop automation, but several tool descriptions reference helpers that are not present in this set (desktop_discover, desktop_act), which would cause dead ends when agents follow the documented 'Prefer' guidance. Basic browser workflows (navigation, click, fill, wait) are well-covered, and workarounds exist for missing operations like refresh (browser_eval).