Touchpoint
Related Servers
Alternatives to Touchpoint
AlicenseBqualityAmaintenanceA Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.4244,633,135 npm37,028Apache 2.0
Related Servers
- AlicenseNot gradedqualityAmaintenanceLets AI agents see and control desktop applications through the accessibility layer, enabling clicking, typing, scrolling, dragging, and window/app management across macOS, Windows, and Linux entirely on the local machine.3MIT
- AlicenseAqualityAmaintenanceDrive, inspect, and assert on real Electron desktop apps from an AI agent — agent-native, Playwright-style automation with accessibility refs, stable error codes, and retrying assertions555MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to see and control your desktop with tools for screenshots, clicks, typing, and more, all locally on macOS and Windows.80 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to control other application windows by providing primitives for clicking, typing, capturing screenshots, and window management. Supports macOS, Windows, and Linux.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI hosts to drive cross-platform desktop GUI automation and browser control, providing tools to read, click, type, send shortcuts, screenshot, and verify GUI elements and web pages.311 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to autonomously control Windows 11 and 10 desktops via sub-10ms screen capture, native UI Automation element inspection, and zero-lag keyboard and mouse input. Combines a visual plane with a semantic plane and stall detection so agents can operate real applications reliably without vision-only guessing.1MIT
TDQS
Scored across 27 tools
Each tool targets a distinct resource and action: discovery (apps, windows, find, snapshot, screenshot), element inspection (get_element), input (click, set_value, set_numeric_value, focus, select_text, type_text, press_key), and window management (activate, minimize, close, move, resize, fullscreen). Overlaps like find vs wait_for are differentiated by polling behavior, and mouse_move/scroll have distinct roles.
All tools follow a consistent lower_snake_case verb_noun pattern (mouse_move, minimize_window, activate_window, set_value, wait_for_window, etc.). Exceptionally uniform, with no mixed conventions or vague verbs. Even atypical names like 'find', 'snapshot', and 'action' function as clear verbs.
At 27 tools, the count exceeds the typical 3-15 range, but the domain (cross-platform UI automation) justifies the breadth. Each tool covers a distinct operation—discovery, inspection, input, window manipulation, and waiting—with no redundancy. The count feels justified by the complexity required to handle various platforms and web content.
The surface is remarkably complete for UI automation: it covers discovery (apps/windows/elements), inspection (snapshot, get_element, read_text), interaction (click, type, set_value, scroll, drag via coordinate/action), and synchronization (wait_for, wait_for_app, wait_for_window). The generic `action` tool covers any raw accessibility action, providing a fallback for unforeseen operations. No critical dead-ends.