dsh-cua - Windows Computer Use MCP server

dsh-cua

<!-- mcp-name: io.github.Hutusion/dsh-cua -->

English · 中文

<!-- Links in this file are absolute on purpose: PyPI renders this same README at https://pypi.org/project/dsh-cua/, where a relative target (README.zh-CN.md, examples/, skill/...) resolves against pypi.org and 404s. GitHub needs no help with either form. Do not "simplify" these back to relative paths. -->

An MCP server + agent skill for computer use on Windows: accessibility element actions come first and screenshots are only the fallback. It ships a cross-session arbiter — when several agents share one machine it serializes them, and it yields while you are actually using the computer yourself.

This repository contains only the MCP server and the skill. It stays neutral toward any stdio MCP client (dsh / Claude Code / Codex / Cursor / Cline / ZCode …) — nothing here requires dsh.

Platform semantics (0.3.1 and later): the tools only work on Windows — they drive user32/kernel32 and UI Automation. But the package also imports elsewhere and the server starts there, answering tools/list as usual, so any client or directory crawler can enumerate all 19 tools with their full schemas; actually calling a tool returns a clear "requires Windows" error rather than the process failing to start at all. In 0.3.0 the import itself raised, which made such crawlers unable to see the server at all (tests/linux-handshake.py is the regression test for this property, and CI runs it on ubuntu-latest).

What it is

A stdio MCP server exposing 19 tools:

diffable text tree — three orders of magnitude smaller than a screenshot), elementatpoint, readelement, findelements, capturewindow (DPI-aware, cropped to the client area), listwindows / findwindow / getwindowrect, listdisplays, cursorposition, clipboardread, coexistence_status

• Observe (read-only, callable at any time): skyshot (reads a window as a compact,

elementaction / elementactionat — press / setvalue / select / toggle / expand / collapse / scrollintoview / focus, delivered straight to the UIA element, so they never steal focus and never care about z-order

• Element actions (soft gate: serialized across agents, no physical input injected):

(element path first, raw event as fallback), sendkeys, typetext (targeted PostMessage), clipboardwrite, openapplication

• Physical input (hard gate: serialized across agents + yields to the human): click_at

Every action returns a receipt rather than a self-reported success: actionsent / effectverified / foreground_changed / user-active / arbiter-busy. "The call was accepted" and "the effect happened" are two different things, and the tool separates them for the agent.

How it differs

There are already several mature open-source Windows implementations. dsh-cua's differences are concentrated on one thing: sharing a machine with a human.

Shortened. The full README is on GitHub.