Windows Computer Use MCP
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Windows Computer Use MCP
A native Windows MCP server for desktop automation. It lets an MCP client
inspect and control ordinary Windows applications through UI Automation,
SendInput, and GDI screen capture — no macOS app bundle, Node runtime, or
vendor-specific agent required.
Features
Accessibility-first: every
get_app_statereturns a compact UI Automation tree with element indices, roles, names, values, bounds, and supported actions.Ten tools for window discovery, snapshots, clicking, typing, key presses, scrolling, dragging, text selection, value setting, and accessibility actions.
State-safe element actions: element indices are tied to the
state_idof the snapshot that produced them. Bounds, enabled state, and offscreen state are re-read when an action runs, so a moved or vanished control fails instead of clicking a stale location.DPI and multi-monitor aware: windows, screenshots, and input use absolute physical screen pixels across the virtual desktop.
Safety checks: UIPI integrity preflight, top-level window hit testing, cursor-movement verification, out-of-desktop coordinate rejection, and a read-only mode that hides all input tools.
Small dependency footprint: the only runtime dependency is
comtypes; PNG encoding is implemented with the standard library.
Related MCP server: Deskhand-mcp
Requirements
Windows 10 or Windows 11, 64-bit.
Python 3.10 or newer.
comtypesfor UI Automation. Without it,list_apps, screenshots, and coordinate input still work; the accessibility tree is unavailable.
The server does not require administrator rights. It checks process token integrity before sending input and refuses targets at a higher integrity level (Windows UIPI). It cannot operate on the secure desktop (UAC prompt or lock screen).
Install
git clone https://github.com/cooolie/windows-computer-use-mcp.git
cd windows-computer-use-mcp
python -m pip install -e .Verify the test suite:
python -m unittest discover -s tests -vConfigure an MCP client
Add a stdio server entry to your MCP client's configuration. For Claude Code,
the user-scope configuration lives in the top-level mcpServers object of
~/.claude.json:
{
"mcpServers": {
"computer-use-windows": {
"type": "stdio",
"command": "C:\\path\\to\\python.exe",
"args": ["-m", "computer_use_windows"],
"env": {
"PYTHONUNBUFFERED": "1",
"PYTHONIOENCODING": "utf-8",
"PYTHONUTF8": "1"
},
"timeout": 120000
}
}
}Use the absolute path to the Python interpreter where the package is installed
(for example, a virtual environment's python.exe). Claude Code inherits only a
small allowlist of environment variables on Windows, so a bare python may not
resolve to the intended interpreter.
To run directly from a checkout without installing the package, install the dependency and point the client at the launcher instead:
python -m pip install -r requirements.txt{
"command": "C:\\path\\to\\python.exe",
"args": ["C:\\path\\to\\windows-computer-use-mcp\\bin\\computer-use-mcp-server.py"]
}The server also includes .claude-plugin/plugin.json if you package it in a
Claude Code plugin marketplace.
Optional Claude Code skill
The repository ships a skill that teaches Claude Code when and how to use the tools. Copy it into your personal skills directory:
Copy-Item skills\computer-use\SKILL.md `
"$HOME\.claude\skills\computer-use-windows\SKILL.md"Restart Claude Code. The tools appear as mcp__computer-use-windows__*.
Tools
Tool | Purpose |
| List visible top-level windows with process, title, class, hwnd, and bounds. |
| Activate a window, return its accessibility tree, and capture a screenshot. |
| Click an element center or absolute screen coordinates with optional modifiers. |
| Set a value through ValuePattern, falling back to focus + select-all + typing. |
| Type Unicode text into the focused control. |
| Press a key or combination such as |
| Rotate the mouse wheel at an element or coordinate. |
| Drag between two absolute screen coordinates. |
| Select matching text inside a TextPattern element. |
| Invoke an action the element explicitly advertises. |
Typical loop
list_appsto find the target window.get_app_statewith the app name, title, process, or hwnd. Record the returnedstate_id.Act on an
element_indexfrom that state, passing the samestate_id.Call
get_app_stateagain before deciding the next action.
All element indices and state_id values expire on the next snapshot.
Coordinates and screenshots
Element rectangles and input coordinates are absolute physical screen pixels on the virtual desktop. Multi-monitor coordinates may be negative.
Screenshots may be scaled down. The result reports
originandscale, wherescaleis image pixels divided by screen pixels:screen = origin + image_pixel / scale.A screenshot captures the visible screen rectangle, not an offscreen window surface. If the target cannot be brought to the foreground, the screenshot is omitted rather than capturing an unrelated window.
UI Automation trees from Chromium/Electron applications are often sparse; use the screenshot and coordinates for those apps.
Safety and limits
The server targets existing windows; it does not launch applications. Start the app with the normal shell or CLI first.
Set
COMPUTER_USE_WINDOWS_READ_ONLY=1to expose onlylist_appsandget_app_state. In read-only modeget_app_statedoes not activate the window and captures no screenshot unless the target is already foreground.Screenshots can contain sensitive data. Do not send them to external services or include them in reports without the user's approval.
Input is refused when the server or target integrity level cannot be read, or when the target is elevated above the server.
Cloaked windows are excluded from
list_apps; minimized windows are listed withminimized=yesandget_app_staterestores them.The server is single-threaded and handles one tool call at a time.
See SECURITY.md for the security policy and private reporting instructions.
Project layout
bin/computer-use-mcp-server.py dependency-free checkout launcher
computer_use_windows/
server.py MCP stdio loop and protocol handling
schemas.py tool definitions and JSON schemas
tools.py dispatch and tool implementations
uia.py UI Automation snapshots and actions
win32.py ctypes bindings
apps.py window enumeration and activation
input.py SendInput keyboard and mouse injection
capture.py GDI screen capture
keys.py key-combination parser
png.py dependency-free PNG encoder
geometry.py rectangle helpers
skills/computer-use/SKILL.md optional Claude Code skill
tests/ unit and stdio integration testsDevelopment
python -m pip install -e .
python -m unittest discover -s tests -vThe tests run on Windows and do not inject mouse or keyboard input. The stdio
integration test starts the server, performs the MCP handshake, lists tools, and
calls list_apps. GitHub Actions runs the suite on Python 3.10 and 3.12.
License
MIT. See LICENSE.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.
Unofficial Browserless MCP — wraps the Browserless headless-Chromium REST API (browserless.io)
Control your authorized Windows computers via OAuth: files, shell, apps, and task status.
Remote MCP access to authorized Mac and Windows computers, with consent and STOP controls.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables MCP clients to observe and control Windows desktop applications by reading UIA element trees and capturing screenshots, then acting through UIA patterns or synthesized mouse and keyboard input. It runs standalone on an interactive Windows session, without requiring the original host application.1-
- AlicenseNot gradedqualityCmaintenanceEnables an MCP host to observe and control Windows desktop applications deterministically: reading UIA control trees, OCR text and pixel diffs, clicking, typing, scrolling and window management, plus verbatim text reading/appending via ValuePattern/TextPattern. Visual judgment is delegated back to the host model's own multimodal context through annotated screenshots, numbered element cards, grid maps and crosshair zoom-ins, so no separate vision model is needed.1AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients on Windows 10/11 to control an interactive desktop through screenshots, mouse and keyboard actions, window management, UI Automation, clipboard access, and multi-display switching. Supports batched actions, application access controls, and visual or text-based desktop interaction.50 npm1MIT
- AlicenseCqualityBmaintenanceEnables MCP clients to inspect desktop windows through accessibility trees and screenshots, perform actions on resolved UI elements, and verify expected conditions after those actions.731Apache 2.0