Windows-MCP

MCP Server that enables Claude to interact with Windows OS

Category: Developer Tools
Primary Subcategory: Desktop, OS & File Automation

Integration details

Description

Windows-MCP is an open-source project that enables seamless integration between AI agents and the Windows operating system. Acting as an MCP server, it bridges the gap between large language models (LLMs) and the Windows OS, allowing agents to perform tasks such as **file navigation, application control, UI interaction, QA testing, and more**. **KEY FEATURES** - **Seamless Windows Integration**: Interacts natively with Windows UI elements, opens applications, controls windows, simulates user input, and more. - **Use Any LLM (Vision Optional)**: Does not rely on traditional computer vision techniques or fine-tuned models. Works with any LLM, reducing complexity and setup time. - **Rich Toolset for UI Automation**: Includes tools for keyboard and mouse control, window management, and capturing window or UI state. - **Lightweight & Open-Source**: Minimal dependencies with full source code available under the MIT license. - **Customizable & Extendable**: Easily adapt or extend tools to suit custom automation workflows or AI integrations. - **Real-Time Interaction**: Typical latency between actions ranges from `0.2` to `0.9` seconds, depending on system load, active applications, and LLM inference speed. **MINIMUM REQUIREMENTS** - **Python 3.13+** - **UV Package Manager** — `curl -LsSf https://astral.sh/uv/install.sh | sh`

Integration type: Connector
Verification status: Verified connector
Platform: Claude
Category: Developer Tools
Primary Subcategory: Desktop, OS & File Automation
Secondary Subcategories: None listed
Brand: CursorTouch
Access: Unknown
First tracked: 2026-07-28
Tool count: 18
Geography: US

Claude Discoverability Score

Windows-MCP isn’t discoverable through Claude’s Connector picker

It runs as a local Claude Desktop Extension, so Claude cannot surface or score it there today.

No spam. Unsubscribe any time.

What the current score measures

Claude showing a list of relevant Connectors in a conversation

Remote Connectors Claude can surface from the Connector picker.

How this score is measured

Primary Subcategory

Desktop, OS & File Automation

View Category

api.agi.techPending VerificationGet notified

DeviceLinkPending VerificationGet notified

Remote Desktop CommanderPending VerificationGet notified

Rooster WakePending VerificationGet notified

—Windows-MCPLocal Extension · Not scored

Tools

18 tools agents can invoke

Manages Windows applications with three modes: 'launch' (opens the prescibed application), 'resize' (adjusts the size/position of a named window or the active window if name is omitted), 'switch' (brings specific window into focus).
Performs mouse clicks at specified coordinates [x, y] or passing a UI element's label/id. Supports button types: 'left' for selection/activation, 'right' for context menus, 'middle'. Supports clicks: 0=hover only (no click), 1=single click (select/focus), 2=double click (open/activate). Provide either loc or label.
Manages Windows clipboard operations. Use mode="get" to read current clipboard content, mode="set" to set clipboard text.
Manages file system operations with eight modes: 'read' (read text file contents), 'write' (create/overwrite/append to files), 'copy' (copy files or directories), 'move' (move or rename), 'delete' (delete files or directories), 'list' (list directory contents), 'search' (find files by glob pattern), 'info' (get metadata like size, dates, type). Relative paths are resolved from the user's Desktop folder. Use absolute paths to access other locations.
Moves mouse cursor to coordinates [x, y] or passing a UI element's label/id. Set drag=True to perform a drag-and-drop operation from the current mouse position to the target coordinates. Default (drag=False) is a simple cursor move (hover). Provide either loc or label.
Enters text into multiple input fields at specified coordinates locs=[[x,y,text], ...] or using labels=[[label,text], ...]. Provide either locs or labels.
Selects multiple items such as files, folders, or checkboxes if press_ctrl=True, or performs multiple clicks if False. Pass locs (list of coordinates) or labels (list of UI element labels/ids).
Sends a Windows toast notification with a title and message.
A comprehensive system tool for executing any PowerShell commands. Use it to navigate the file system, manage files and processes, and execute system-level operations. Capable of accessing web content, interacting with network resources, and performing complex administrative tasks.
Manages system processes. Use mode="list" to list running processes with filtering and sorting options. Use mode="kill" to terminate processes by PID or name.
Accesses the Windows Registry. Use mode="get" to read a value, mode="set" to create/update a value, mode="delete" to remove a value or key, mode="list" to list values and sub-keys under a path.
Fetch content from a URL or the active browser tab. By default, performs a lightweight HTTP request to the URL. If you need to extract text from the active tab's DOM within the viewport, ensure the page is open in a browser and use Snapshot with use_dom=True first, then the agent will handle extraction. Use Screenshot for the default fast visual inspection path.
Captures a fast screenshot-first desktop snapshot with cursor position, active/open windows, and an image. Skips UI tree extraction for speed and should be the default first call when you mainly need visual context. Supports display=[0] or display=[0,1] using zero-based active Windows display indices. Note: the returned image may be downscaled for efficiency; when it is, multiply image coordinates by the ratio of original size to displayed size to get the actual screen coordinates for mouse actions (Click, Move, etc.).
Scrolls at coordinates [x, y], a UI element's label/id, or current mouse position if loc=None. Type: vertical (default) or horizontal. Direction: up/down for vertical, left/right for horizontal. wheel_times controls amount (1 wheel ≈ 3-5 lines). Use for navigating long content, lists, and web pages.
Executes keyboard shortcuts using key combinations separated by +. Examples: "ctrl+c" (copy), "ctrl+v" (paste), "alt+tab" (switch apps), "win+r" (Run dialog), "win" (Start menu), "ctrl+shift+esc" (Task Manager). Use for quick actions and system commands.
Captures complete desktop state including: system language, focused/opened windows, interactive elements (buttons, text fields, links, menus with coordinates), and scrollable areas. Use this when you need interactive element ids, scrollable regions, or browser DOM extraction with use_dom=True. Set use_vision=True to include screenshot. Set display=[0] or display=[0,1] using zero-based active Windows display indices; omit it to keep the default full-desktop behavior.
Types text at specified coordinates [x, y] or passing a UI element's label/id. Set clear=True to clear existing text first, False to append. Set press_enter=True to submit after typing. Set caret_position to 'start' (beginning), 'end' (end), or 'idle' (default). Provide either loc or label.
Pauses execution for specified duration in seconds. Use when waiting for: applications to launch/load, UI animations to complete, page content to render, dialogs to appear, or between rapid actions. Helps ensure UI is ready before next interaction.

Windows-MCP FAQ

How do I improve a Verified connector's discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

What are Windows-MCP alternatives on Claude?

As of 2026-09-13, Windows-MCP competes with api.agi.tech, DeviceLink, Remote Desktop Commander, Rooster Wake in Claude Desktop, OS & File Automation, ranked by public Discoverability Score.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.