
Windows Computer Use Mcp
Gives Claude direct control over your Windows desktop through MCP stdio. You get mouse operations (move, click, drag, scroll), keyboard input (type text, send key combos like ctrl+c), screenshots of full screen or regions, clipboard read/write, and app management (list running processes, get focused window, launch apps). All the low-level input goes through Win32 user32.dll calls wrapped in PowerShell scripts executed via Bun. Useful when you want Claude to automate GUI tasks, capture screen state for visual reasoning, or orchestrate workflows across desktop applications without building custom integrations for each one.
- tools
- 18
- transport
- STDIO
- last updated
- Apr 3, 2026
Tools
18 toolsPublic tool metadata for what this MCP can expose to an agent.
screenshotTake a screenshot of the current screen
Take a screenshot of the current screen
No parameter schema in public metadata yet.
zoomTake a screenshot of a specific region
Take a screenshot of a specific region
No parameter schema in public metadata yet.
mouse_moveMove the mouse cursor to coordinates
Move the mouse cursor to coordinates
No parameter schema in public metadata yet.
left_clickLeft-click at coordinates or current position
Left-click at coordinates or current position
No parameter schema in public metadata yet.
right_clickRight-click at coordinates
Right-click at coordinates
No parameter schema in public metadata yet.
double_clickDouble-click at coordinates
Double-click at coordinates
No parameter schema in public metadata yet.
left_click_dragClick and drag from one point to another
Click and drag from one point to another
No parameter schema in public metadata yet.
scrollScroll the mouse wheel
Scroll the mouse wheel
No parameter schema in public metadata yet.
typeType a string of text
Type a string of text
No parameter schema in public metadata yet.
keyPress a key combination (e.g. `ctrl+c`, `alt+f4`)
Press a key combination (e.g. `ctrl+c`, `alt+f4`)
No parameter schema in public metadata yet.
hold_keyHold a key for a duration
Hold a key for a duration
No parameter schema in public metadata yet.
cursor_positionGet current cursor position
Get current cursor position
No parameter schema in public metadata yet.
list_running_applicationsList all running apps with visible windows
List all running apps with visible windows
No parameter schema in public metadata yet.
get_frontmost_applicationGet the currently focused app
Get the currently focused app
No parameter schema in public metadata yet.
open_applicationOpen an app by name or path
Open an app by name or path
No parameter schema in public metadata yet.
list_displaysList connected displays
List connected displays
No parameter schema in public metadata yet.
read_clipboardRead clipboard text
Read clipboard text
No parameter schema in public metadata yet.
write_clipboardWrite text to clipboard
Write text to clipboard
No parameter schema in public metadata yet.
Sponsors
Readme
Windows Computer Use MCP Server
English | 中文
An MCP (Model Context Protocol) server that provides desktop automation tools for Windows. Control mouse, keyboard, take screenshots, manage clipboard, and interact with applications — all through the MCP protocol.
Note: This server only runs on Windows.
Features
- Screenshots — Capture full screen or specific regions as base64 PNG
- Mouse Control — Move, click, double-click, right-click, drag, scroll
- Keyboard Input — Type text, press key combinations, hold keys
- Cursor Position — Get current cursor coordinates
- Clipboard — Read and write clipboard text
- Application Management — List running apps, get frontmost app, open apps
- Display Info — List connected displays with dimensions
Tools
Details
- Repository
- github.com/hiphopanda/windows-computer-use-mcp
- Package
windows-computer-use-mcp- Transport
- STDIO
- Registry
- MCP registry, active