Windows computer-use MCP server: accessibility-first element actions (UIA), UI read as diffed text trees instead of screenshots, guarded raw input, and a cross-session arbiter that yields to the human. 19 tools.
It enables MCP-compatible AI clients to run local device, filesystem, shell, PowerShell, Git, browser, HTTP, clipboard and application actions on a Windows PC and a paired Android phone, with session-based device routing. Sensitive operations are gated behind configurable one-use approvals and recorded in a local SQLite audit.
An unofficial experimental local MCP server that lets AI clients work with an already logged-in Windows Weixin desktop client, providing bounded conversation and message reads, group and message search, polling of up to 16 selected chats, guarded text and attachment submission, and image/file viewing handoffs. It also exposes hybrid Computer Use prompts for native mention handoffs, while remeasuring the window, DPI, and target controls on each action and failing closed when evidence is insufficient.
An MCP server that gives any AI assistant eyes and hands on your desktop — screenshots, clicking, typing, OCR, window management, accessibility-tree queries, workflow recording.
A 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.
A stdio MCP server that gives AI agents eyes and hands on Windows: they can capture full-screen, window, or region screenshots and read or write clipboard text and images themselves. This enables a self-correcting see-it, fix-it loop directly from an AI terminal session, with no daemon, tray app, or temporary files.
