How do I install Windows?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Windows need an API key?

No required environment variable is listed on this record.

What transport does Windows use?

Windows runs locally over stdio.

When was Windows last checked?

Last checked 2026-11-09. An MCP Server for computer-use in Windows OS

Windows MCP server

Windows-MCP is a lightweight, open-source project that enables seamless integration between AI agents and the Windows operating system. Acting as an MCP server bridges the gap between LLMs and the Windows operating system, allowing agents to perform tasks such as file navigation, application control, UI interaction, QA testing, and more.

mcp-name: io.github.CursorTouch/Windows-MCP

Updates

Windows-MCP reached 2M+ Users in Claude Desktop Extensiosn.
Try out 🪟Windows-Use, an agent built using Windows-MCP.
Windows-MCP is now available on PyPI (thus supports uvx windows-mcp)
Windows-MCP is added to MCP Registry

Supported Operating Systems

Windows 10
Windows 11

The current package requires Python 3.14+, which supports Windows 10 and newer. Earlier Windows versions are not supported by the current installation.

🎥 Demos

https://github.com/user-attachments/assets/d0e7ed1d-6189-4de6-838a-5ef8e1cad54e

https://github.com/user-attachments/assets/d2b372dc-8d00-4d71-9677-4c64f5987485

✨ Key Features

Seamless Windows Integration
Interacts natively with Windows UI elements, opens apps, controls windows, simulates user input, and more.
Use Any LLM (Vision Optional) Unlike many automation tools, Windows-MCP doesn't rely on any traditional computer vision techniques or specific fine-tuned models; it works with any LLMs, reducing complexity and setup time.
Rich Toolset for UI Automation
Includes tools for basic keyboard, mouse operation and capturing window/UI state.
Lightweight & Open-Source
Minimal dependencies and easy setup with full source code available under MIT license.
Customizable & Extendable
Easily adapt or extend tools to suit your unique automation or AI integration needs.
Real-Time Interaction
Typical latency between actions (e.g., from one mouse click to the next) ranges from 0.2 to 0.5 secs, and may slightly vary based on the number of active applications and system load, also the inferencing speed of the llm.
DOM Mode for Browser Automation
Special use_dom=True mode for State-Tool that focuses exclusively on web page content, filtering out browser UI elements for cleaner, more efficient web automation. Supports Chrome, Edge, and Firefox (Firefox uses an IAccessible2 fallback since it doesn't expose RootWebArea via UIA).

🛠️Installation

Note: When you install this MCP server for the first time it may take a minute or two because of installing the dependencies in pyproject.toml. In the first run the server may timeout ignore it and restart it.

Prerequisites

Python 3.14+
UV (Package Manager) from Astra, install with pip install uv or curl -LsSf https://astral.sh/uv/install.sh | sh
The App tool resolves localized Start Menu display names as well as internal app names; an English Windows display language is not required.

Run at Login

Run the server directly when needed:

uvx windows-mcp serve
uvx windows-mcp serve --transport sse --host localhost --port 8000
uvx windows-mcp serve --transport streamable-http --host localhost --port 8000

Install it as a background task that starts now and at every login:

windows-mcp install

# Or choose the HTTP transport and bind address explicitly
windows-mcp install --transport sse --host 127.0.0.1 --port 8000

This creates a per-user Scheduled Task named windows-mcp-server and a wrapper script at ~/.windows-mcp/start-server.cmd. Use windows-mcp uninstall to remove it. Logs are written to ~/.windows-mcp/server.log and ~/.windows-mcp/server.error.log.

Install Claude Desktop.

npm install -g @anthropic-ai/mcpb

Configure the MCP server.

Option A: Install from PyPI (Recommended)

Use uvx to run the latest version directly from PyPI.

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "windows-mcp": {
      "command": "uvx",
      "args": [
        "windows-mcp",
        "serve"
      ]
    }
  }
}

Option B: Install from Source

Clone the repository:

git clone https://github.com/CursorTouch/Windows-MCP.git
cd Windows-MCP

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "windows-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "<path to the windows-mcp directory>",
        "run",
        "windows-mcp",
        "serve"
      ]
    }
  }
}

Fully restart Claude Desktop and verify the server appears in the MCP tools list.

Claude Desktop MSIX (Windows Store)

The MSIX-packaged Claude Desktop (Microsoft Store version) virtualizes %APPDATA%. This causes two main issues:

The config file is located at: %LOCALAPPDATA%\Packages\Claude_pzs8sxrjxfjjc\LocalCache\Roaming\Claude\claude_desktop_config.json (not %APPDATA%\Claude\).
Automatic installation from the "Claude Directory" will fail because the ${__dirname} variable resolves to the incorrect (non-virtualized) path.

To configure Windows-MCP on the Windows Store version of Claude:

You must manually edit the configuration file. Note that Electron apps in the MSIX sandbox do not inherit the system PATH, so you must use the full absolute path to uvx.exe (or uv.exe).

Option A: Using pre-installed executable

In a terminal, run uv tool install windows-mcp.
Use the generated executable in your config:

{
  "mcpServers": {
    "windows-mcp": {
      "command": "C:\\Users\\<user>\\.local\\bin\\windows-mcp.exe",
      "args": ["serve"]
    }
  }
}

Option B: Using uvx

{
  "mcpServers": {
    "windows-mcp": {
      "command": "C:\\Users\\<user>\\.local\\bin\\uvx.exe",
      "args": ["windows-mcp", "serve"]
    }
  }
}

Option C: Install from Source

{
  "mcpServers": {
    "windows-mcp": {
      "command": "C:\\Users\\<user>\\.local\\bin\\uv.exe",
      "args": [
        "--directory",
        "C:\\path\\to\\Windows-MCP",
        "run",
        "windows-mcp",
        "serve"
      ]
    }
  }
}

Replace <user> with your Windows username. To find the correct paths, run where uvx, where windows-mcp, or where uv. Fully quit Claude Desktop (Tray → Quit) and reopen after saving the config.

For additional Claude Desktop integration troubleshooting, see the MCP documentation.

Install Perplexity Desktop.
Open Perplexity Desktop and go to Settings -> Connectors -> Add Connector -> Advanced.
Enter the name as Windows-MCP, then paste one of the following configs.

Option A: Install from PyPI (Recommended)

{
  "command": "uvx",
  "args": [
    "windows-mcp",
    "serve"
  ]
}

Option B: Install from Source

{
  "command": "uv",
  "args": [
    "--directory",
    "<path to the windows-mcp directory>",
    "run",
    "windows-mcp",
    "serve"
  ]
}

Click Save, then restart Perplexity Desktop if needed.

For additional Claude Desktop integration troubleshooting, see the Perplexity MCP Support. The documentation includes helpful tips for checking logs and resolving common issues.

Install Gemini CLI.

npm install -g @google/gemini-cli

Open %USERPROFILE%/.gemini/settings.json.
Add the windows-mcp config and save it.

{
  "theme": "Default",
  ...
  "mcpServers": {
    "windows-mcp": {
      "command": "uvx",
      "args": [
        "windows-mcp",
        "serve"
      ]
    }
  }
}

Note: To run from source, replace the command with uv and args with ["--directory", "<path>", "run", "windows-mcp", "serve"].

Restart Gemini CLI.

npm install -g @qwen-code/qwen-code@latest

Open %USERPROFILE%/.qwen/settings.json.
Add the windows-mcp config and save it.

{
  "mcpServers": {
    "windows-mcp": {
      "command": "uvx",
      "args": [
        "windows-mcp",
        "serve"
      ]
    }
  }
}

Note: To run from source, replace the command with uv and args with ["--directory", "<path>", "run", "windows-mcp", "serve"].

Restart Qwen Code.

npm install -g @openai/codex

Open %USERPROFILE%/.codex/config.toml.
Add the windows-mcp config and save it.

[mcp_servers.windows-mcp]
command="uvx"
args=[
  "windows-mcp",
  "serve"
]

Note: To run from source, replace the command with uv and args with ["--directory", "<path>", "run", "windows-mcp", "serve"].

Restart Codex CLI.

Add the published stdio server from a Windows terminal:

autohand mcp add windows-mcp uvx windows-mcp serve

Add --scope project after add to keep the server configuration in the current project. See Autohand Code for current installation and CLI details.

Install Claude Code:

npm install -g @anthropic-ai/claude-code

Configure the server:

Option A: Install from PyPI (Recommended)

Use uvx to run the latest version directly from PyPI.

claude mcp add --transport stdio windows-mcp -- uvx windows-mcp serve

Option B: Install from Source

Clone the repository:

git clone https://github.com/CursorTouch/Windows-MCP.git
cd Windows-MCP

Run the following command in your terminal:

claude mcp add --transport stdio windows-mcp -- uv --directory "<path>" run windows-mcp serve

Note: To make the server available across all projects, add --scope user to the command.

Rerun Claude Code in terminal. Enjoy 🥳

Note: On Windows, if you encounter "Connection closed" errors, use the full path to uvx.exe:

claude mcp add --transport stdio windows-mcp -- C:\Users\<user>\.local\bin\uvx.exe windows-mcp serve

To verify the server is registered, run claude mcp list. Inside Claude Code, use /mcp to check server status.

WSL (Windows Subsystem for Linux)

If you run Claude Code from WSL, the MCP server must still execute on the Windows side (it needs Windows APIs for UI automation). Use powershell.exe as the command to bridge WSL and Windows:

Install uv on Windows (from a PowerShell terminal):

irm https://astral.sh/uv/install.ps1 | iex

From your WSL terminal, register the server:

claude mcp add windows-mcp --transport stdio -s user -- powershell.exe -Command "C:\Users\<user>\.local\bin\uvx.exe windows-mcp serve"

Replace <user> with your Windows username. The -s user flag makes the server available across all projects.

Restart Claude Code and verify with /mcp.

🖥️ Running Windows-MCP

Windows-MCP runs directly on your Windows machine and exposes its tools to the connected MCP client.

# Runs with stdio transport (default)
uvx windows-mcp serve

# Or with SSE/Streamable HTTP for network access
uvx windows-mcp serve --transport sse --host localhost --port 8000
uvx windows-mcp serve --transport streamable-http --host localhost --port 8000

Optional environment variables can be set to customize behavior — see Environment Variables below.

Security for Remote Access

For network access, enable authentication and TLS:

windows-mcp serve --transport sse --host 0.0.0.0 \
  --auth-key "your_secret_token" \
  --ip-allowlist "203.0.113.0/24" \
  --ssl-certfile cert.pem --ssl-keyfile key.pem

See 🔐 Security & Access Control for all options.

Transport Options

Transport	Command	Use Case
`stdio` (default)	`serve --transport stdio`	Direct connection from MCP clients like Claude Desktop, Cursor, etc.
`sse`	`serve --transport sse --host HOST --port PORT`	Network-accessible via Server-Sent Events
`streamable-http`	`serve --transport streamable-http --host HOST --port PORT`	Network-accessible via HTTP streaming (recommended for production)

🔐 Security & Access Control

Authentication

windows-mcp serve --transport sse --host 0.0.0.0 --auth-key "your_token"

Requires Authorization: Bearer your_token header on all requests.

IP Allowlist

windows-mcp serve --auth-key "token" --ip-allowlist "203.0.113.0/24,198.51.100.5"

Restricts connections to specified CIDR ranges. Blocks private/loopback IPs by default.

CORS Origins

By default, no CORS headers are emitted. Browsers block cross-origin requests via their own Same-Origin Policy, which means arbitrary websites cannot reach the MCP control plane even if the server is on localhost. Host-header validation (DNS rebinding protection) is also applied automatically based on the bind address.

If you need a browser-based MCP client to reach the server, opt in with an explicit origin allowlist:

windows-mcp serve --cors-origins "https://my-client.example.com,https://other.example.com"

Only the listed origins receive Access-Control-Allow-Origin headers; all other cross-origin requests are rejected by the browser. The equivalent environment variable is WINDOWS_MCP_CORS_ORIGINS.

Tool Selection

All tools are enabled by default. Use --tools to whitelist specific tools, or --exclude-tools to block specific ones.

windows-mcp serve --tools "Screenshot,Click,Snapshot"   # Enable only these tools
windows-mcp serve --exclude-tools "PowerShell,Registry" # Disable specific tools

TLS/HTTPS

openssl req -x509 -newkey rsa:4096 -keyout key.pem -out cert.pem -days 365 -nodes

windows-mcp serve --ssl-certfile cert.pem --ssl-keyfile key.pem

OAuth 2.0 + PKCE

For MCP clients that use OAuth (e.g. Claude Desktop) instead of a static API key:

windows-mcp serve --transport streamable-http --host 0.0.0.0 \
  --ssl-certfile ~/.windows-mcp/cert.pem \
  --ssl-keyfile  ~/.windows-mcp/key.pem \
  --oauth-client-id my-client \
  --oauth-client-secret my-secret

Claude Desktop config:

{
  "mcpServers": {
    "windows-mcp": {
      "type": "http",
      "url": "https://<host>:8000/mcp/",
      "oauth": {
        "clientId": "my-client",
        "clientSecret": "my-secret"
      }
    }
  }
}

The OAuth server exposes:

GET /.well-known/oauth-authorization-server — server metadata (RFC 8414)
GET /oauth/authorize — Authorization Code + PKCE (S256 required)
POST /oauth/token — token exchange (client secret required)
POST /oauth/register — disabled; clients must be pre-provisioned

Dynamic client registration is disabled. Redirect URIs must be loopback http(s) only. Auth key and OAuth can coexist — both are accepted as valid Bearer tokens.

Config File (`~/.windows-mcp/config.toml`)

Instead of passing flags every time, store your configuration in ~/.windows-mcp/config.toml. CLI flags always override config file values.

Search order:

--config /path/to/config.toml
~/.windows-mcp/config.toml

stdio — local only, no security needed:

[server]
transport = "stdio"

SSE — network access with auth and IP restriction:

[server]
transport = "sse"
host      = "0.0.0.0"
port      = 8000
auth_key  = "your-secret-key"

[security]
ip_allowlist = ["192.168.1.0/24"]

Streamable HTTP — with auth, TLS, and tool exclusions:

[server]
transport    = "streamable-http"
host         = "0.0.0.0"
port         = 8000
auth_key     = "your-secret-key"
ssl_certfile = "cert.pem"   # resolved relative to ~/.windows-mcp/
ssl_keyfile  = "key.pem"

[security]
ip_allowlist        = ["192.168.1.0/24"]
cors_origins        = ["https://my-client.example.com"]   # optional — browser CORS opt-in
oauth_client_id     = "my-client"      # optional — enables OAuth 2.0 + PKCE
oauth_client_secret = "my-secret"

[tools]
exclude = ["PowerShell", "Registry"]   # disable specific tools

Place cert and key files in the same directory:

~/.windows-mcp/
├── config.toml
├── cert.pem
└── key.pem

Generate a self-signed cert directly into that directory:

mkdir -p ~/.windows-mcp
openssl req -x509 -newkey rsa:4096 \
  -keyout ~/.windows-mcp/key.pem \
  -out ~/.windows-mcp/cert.pem \
  -days 365 -nodes

Desktop control

Desktop control is enabled by default with the relaxed policy: direct desktop actions are gated, while background tools can run as you use the computer. Configure it in ~/.windows-mcp/config.toml (or disable it entirely with enabled = false):

[control]
enabled = true
policy = "relaxed"
idle_timeout_seconds = 10.0

Or override it for one MCP server launch:

windows-mcp serve --no-control
windows-mcp serve --control --control-idle-timeout 3
windows-mcp serve --control-policy strict

In your MCP client's launch arguments, put these options after serve. The priority is CLI > environment variable > TOML > default. --control can explicitly override enabled = false. The timeout accepts finite positive seconds (including fractions); zero does not disable control. The default remains 10 seconds.

Restart the Windows-MCP server process after changing these settings. There is no hot reload or AI configuration tool. ControlStatus reports the effective enabled policy, and idle_timeout_seconds values, with state disabled when control is off.

Disabling control turns off ownership gating, physical input protection, takeover monitoring, and the control indicator. Tools remain available and serialized, with injected key/button cleanup retained. AI desktop actions can then interfere with your own input; PowerShell scripts can also operate the UI. The separate screenshot flash setting is unchanged. When control is enabled, the idle timer restarts with physical input, so shortening it does not allow gated calls while you keep using the computer.

During AI control, small mouse movements remain blocked without pausing the current tool. Mouse takeover adds up the length of each relative raw-input movement, including back-and-forth movement, until it reaches 500 device units by default. A gap of 0.5 seconds without movement starts a new segment; switching devices or starting a new control period also clears the total. Set control.mouse_takeover_units in TOML to change the threshold (40–2000), then restart the server. These are device units, not screen pixels. Devices that do not provide identifiable relative raw input, including some touchpads and remote-input devices, must use Ctrl+Alt+Shift+Backspace to take over. The legacy mouse_takeover_pixels setting is still accepted for compatibility but no longer affects takeover.

Desktop gate policies

Policy	Operations that require desktop ownership
`relaxed` (A, default)	Direct input: Click, Type, Scroll, Move, Shortcut, MultiSelect, MultiEdit; App `switch` and `resize`.
`balanced` (B)	Everything in A, plus PowerShell, Notification, App `launch`/`launch_executable`, Process `kill`, and Clipboard `set`.
`strict` (C)	All tools except ControlStatus, matching the previous gate behavior.

FileSystem, Registry, Snapshot, Screenshot, Scrape, Wait, WaitFor, DisplayInventory, Process list, and Clipboard get bypass ownership in A and B. This classification concerns desktop interference, not permissions or data safety. PowerShell can still operate the UI, and file/registry operations can have other side effects.

Ungated calls do not acquire or extend the desktop lease, activate its indicator, or wait for its tool lock. Existing resource constraints still apply: UI Automation operations share a dedicated worker, so a long WaitFor can delay other UIA work. The separate screenshot flash is unchanged. --no-control retains its existing all-tools serialization and overrides the policy's ownership checks.

In relaxed mode, agents should prefer background work and coordinate known desktop interference with the user. Obtain permission before knowingly disrupting a user's process or taking focus, reusing existing authorization. These are tool-use guidelines, not server-enforced approval or process ownership tracking. Clipboard continues to use the real Windows clipboard; no virtual clipboard is introduced.

For contributors: tool categories and the few mode-specific exceptions live in src/windows_mcp/tools/control_policy.py. Update that table when adding tools or modes; registration coverage tests detect omissions. Unknown extensions conservatively use the gate. Keep policy decisions out of individual tool implementations.

`auth` Helper

Generate an auth key and save a working config to ~/.windows-mcp/config.toml:

windows-mcp auth

Generate auth plus a self-signed TLS certificate:

windows-mcp auth --transport streamable-http --host 0.0.0.0 --port 8000 --with-tls

This command writes the auth key into the config file, can generate cert.pem and key.pem, and prints an example MCP client configuration for the selected transport.

SSRF Protection

Scrape tool blocks: private IPs, loopback, link-local, credentials-in-URLs, non-HTTP schemes.

⚙️ Environment Variables

All variables are optional unless noted. Set them via the env key in claude_desktop_config.json (or your MCP client's equivalent config).

Screenshot & Snapshot

Variable	Default	Description
`WINDOWS_MCP_SCREENSHOT_SCALE`	`1.0`	Scale factor applied to screenshots before encoding. Accepts a float in the range `0.1`–`1.0`. Useful on high-resolution displays (1440p, 4K) where the default produces images that exceed Claude Desktop's 1 MB tool-result limit. Set to `0.5` to halve both dimensions (quarter the file size).
`WINDOWS_MCP_SCREENSHOT_BACKEND`	`auto`	Screenshot capture backend. Accepted values: `auto` (tries dxcam → mss → pillow in order), `dxcam`, `mss`, `pillow`. Use `mss` or `pillow` if `dxcam` is unavailable or causes issues on your GPU.
`WINDOWS_MCP_PROFILE_SNAPSHOT`	(disabled)	Set to `1`, `true`, `yes`, or `on` to emit per-stage timing logs for Screenshot/Snapshot calls. Useful for diagnosing slow captures.
`WINDOWS_MCP_DISABLE_FLASH`	(disabled)	Set to `1`, `true`, `yes`, or `on` to suppress the orange-red glowing border that briefly highlights the captured area after every screenshot. The flash is rendered on a transparent always-on-top window after capture so it never appears in the captured image.

Excluding processes from UI Automation traversal

Variable	Default	Description
`WINDOWS_MCP_EXCLUDE_PROCESSES`	(none)	Comma-separated process basenames whose windows are excluded from UI Automation tree traversal, e.g. `Code.exe,Cursor.exe`. Matching is case-insensitive and exact — no wildcards or regular expressions. Unset or empty preserves current behaviour.

Some applications expose accessibility trees that can become slow or unresponsive during UI Automation traversal. Snapshot and WaitFor may traverse the active window and other top-level handles selected for tree capture, so one pathological accessibility provider can stall the capture.

Set:

WINDOWS_MCP_EXCLUDE_PROCESSES=Code.exe,Cursor.exe

Process names are comma-separated executable basenames. They are matched case-insensitively after surrounding whitespace is stripped; empty entries are ignored and duplicates are harmless.

A window is excluded before any UI Automation call is made against it, so its accessibility provider is never entered. Excluded applications may still appear in the window list, but Windows-MCP will not traverse their accessibility trees, and they are not reported as failed captures. If the owning process of a window cannot be resolved, the window is traversed as usual.

This is an exclusion mechanism — a mitigation, not a complete fix for every form of #383. It only skips the processes you name; a pathological window you have not listed can still stall a capture.

Desktop control settings

If a physical key/button release event is missed, the input monitor checks residual holds after the configured idle wait. Five consecutive all-released samples, at least 100 ms apart, clear the stale records. New physical input or a reported held key/button resets confirmation. This is best-effort: a zero GetAsyncKeyState result counts as released even when Windows cannot provide the state; repeated sampling filters transient readings but cannot distinguish persistent query failure.

Variable	Default	Description
`WINDOWS_MCP_CONTROL`	`true`	Enable desktop control coordination. Set to `false` to disable. Equivalent to `--control/--no-control`; restart required.
`WINDOWS_MCP_CONTROL_POLICY`	`relaxed`	Gate policy: `relaxed`, `balanced`, or `strict`. Equivalent to `--control-policy`; restart required.
`WINDOWS_MCP_CONTROL_IDLE_TIMEOUT`	`10.0`	Finite positive idle wait in seconds. Equivalent to `--control-idle-timeout`; restart required.

Security

Variable	Default	Description
`WINDOWS_MCP_AUTH_KEY`	(none)	Bearer token required on all HTTP requests. Alternative to `--auth-key` CLI flag.
`WINDOWS_MCP_IP_ALLOWLIST`	(none)	Comma-separated list of allowed client IPs or CIDR ranges (e.g., `203.0.113.0/24,198.51.100.5`). Alternative to `--ip-allowlist` CLI flag.
`WINDOWS_MCP_CORS_ORIGINS`	(none)	Comma-separated list of origins permitted to make cross-origin browser requests (e.g., `https://my-client.example.com`). No CORS headers are emitted when unset. Alternative to `--cors-origins` CLI flag.
`WINDOWS_MCP_TOOLS`	(all enabled)	Comma-separated explicit list of tools to enable (e.g., `Screenshot,Click,Snapshot`). Alternative to `--tools` CLI flag.
`WINDOWS_MCP_EXCLUDE_TOOLS`	(none)	Comma-separated list of tools to disable (e.g., `PowerShell,Registry`). Alternative to `--exclude-tools` CLI flag.
`WINDOWS_MCP_SSL_CERTFILE`	(none)	Path to TLS certificate file (.pem) for HTTPS. Must be provided with `WINDOWS_MCP_SSL_KEYFILE`.
`WINDOWS_MCP_SSL_KEYFILE`	(none)	Path to TLS private key file (.pem) for HTTPS. Must be provided with `WINDOWS_MCP_SSL_CERTFILE`.
`WINDOWS_MCP_OAUTH_CLIENT_ID`	(none)	OAuth client ID for HTTP transports. Must be provided with `WINDOWS_MCP_OAUTH_CLIENT_SECRET`.
`WINDOWS_MCP_OAUTH_CLIENT_SECRET`	(none)	OAuth client secret for HTTP transports. Must be provided with `WINDOWS_MCP_OAUTH_CLIENT_ID`.
`WINDOWS_MCP_STATELESS_HTTP`	`false`	Set to `1`, `true`, `yes`, or to run without connection state. Useful for reconnects after restarts and for horizontally scaled deployments.

Telemetry

Variable	Default	Description
`ANONYMIZED_TELEMETRY`	`true`	Set to `false` to disable anonymous usage telemetry. No personal data, tool arguments, or outputs are ever collected regardless of this setting.
`POSTHOG_API_KEY`	Project default	Override the PostHog project write key used for anonymous telemetry. Set to an empty string to skip PostHog client initialization.
`POSTHOG_HOST`	`https://us.i.posthog.com`	Override the PostHog host for anonymous telemetry, such as for a self-hosted PostHog deployment.

Debug

Variable	Default	Description
`WINDOWS_MCP_DEBUG`	`false`	Set to `1`, `true`, `yes`, or `on` to enable debug mode, which sets the log level to DEBUG for verbose output. Also available as the `--debug` CLI flag.

WatchDog

Variable	Default	Description
`WINDOWS_MCP_WATCHDOG`	`false`	Set to `on`, `1`, `true`, `yes`, or `enabled` (case-insensitive) to run the UIA focus watchdog. It is off by default because its only remaining effect is debug logging of focus changes, while it costs a background thread and a long-lived UIA event subscription that can crash the server on unstable UIA environments after long uptime (e.g. across a sleep/resume or session change). The accessibility tree is built on demand for every tool call either way, so tool behaviour is unaffected.

Example claude_desktop_config.json:

Local (no security):

{
  "mcpServers": {
    "windows-mcp": {
      "command": "uvx",
      "args": ["windows-mcp", "serve"],
      "env": { "WINDOWS_MCP_SCREENSHOT_SCALE": "0.5" }
    }
  }
}

Remote (with auth + IP allowlist + TLS):

{
  "mcpServers": {
    "windows-mcp": {
      "command": "uvx",
      "args": ["windows-mcp", "serve", "--transport", "sse", "--host", "0.0.0.0"],
      "env": {
        "WINDOWS_MCP_AUTH_KEY": "your_token",
        "WINDOWS_MCP_IP_ALLOWLIST": "203.0.113.0/24",
        "WINDOWS_MCP_SSL_CERTFILE": "/path/to/cert.pem",
        "WINDOWS_MCP_SSL_KEYFILE": "/path/to/key.pem"
      }
    }
  }
}

🔨MCP Tools

MCP Client can access the following tools to interact with Windows:

Click: Click on the screen at the given coordinates.
Type: Type text on an element (optionally clears existing text).
Scroll: Scroll vertically or horizontally on the window or specific regions.
Move: Move mouse pointer or drag (set drag=True) to coordinates. For deterministic drag, set from_loc=[x, y] with drag=True to press at an explicit start point and release at loc in one tool call. Optional duration adds bounded intermediate movement.
Shortcut: Press keyboard shortcuts (Ctrl+c, Alt+Tab, etc).
Wait: Pause for a defined duration.
WaitFor: Wait until text, an active window, an element, or a focused element appears by polling UI state inside one tool call.
ControlStatus: Read the desktop control owner and remaining user-idle wait. It stays available when user takeover blocks new tool calls. During AI control, a visible edge and cursor glow indicate ownership; moving the physical mouse substantially or pressing Ctrl+Alt+Shift+Backspace returns control to the user until 10 seconds of inactivity. During screenshot capture, the indicator is temporarily hidden and physical input is released; any physical input during this interval preempts AI control, although ControlStatus can briefly still report ai until that event is processed. Stepwise desktop input stops at its next checkpoint, but an already-running external command (for example PowerShell or an App launch) may continue after takeover; this control gate does not cancel processes or undo completed side effects. On a detected hook fault, injected keys and mouse buttons are released asynchronously, so physical input can briefly overlap a still-held AI key or button. Windows may also silently remove a low-level hook without notifying this process; periodic hook replacement reduces but does not eliminate that undetected window. User takeover is therefore best-effort, not a security boundary or a guarantee of exclusive control. Sessionless MCP 2026-07-28 clients cannot receive unsolicited control-state logs; they should query ControlStatus when they need the current owner.
DisplayInventory: Read display layout, work areas, effective DPI, and scale metadata.
Screenshot: Fast screenshot-first desktop capture 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, and (virtual-desktop pixel coordinates) to capture just that rectangle instead of the whole screen — cheaper on tokens when you already know which area matters. takes precedence over when both are given; an invalid or out-of-bounds region raises an error. After capture, a brief orange-red glowing border is drawn inside the captured area as a visual confirmation (set to disable).

🤝 Connect with Us

Stay updated and join our community:

📢 Follow us on X for the latest news and updates
💬 Join our Discord Community

Star History

👥 Contributors

Thanks to all the amazing people who have contributed to Windows-MCP! 🎉

We appreciate every contribution, whether it's code, documentation, bug reports, or feature suggestions. Want to contribute? Check out our Contributing Guidelines!

🔒 Security

Important: Windows-MCP operates with full system access and can perform irreversible operations. Please review our comprehensive security guidelines before deployment.

For detailed security information, including:

Tool-specific risk assessments
Deployment recommendations
Vulnerability reporting procedures
Compliance and auditing guidelines

Please read our Security Policy.

📊 Telemetry

Windows-MCP collects usage data to help improve the MCP server. No personal information, no tool arguments, no outputs are tracked.

To disable telemetry, set ANONYMIZED_TELEMETRY to false in your MCP client configuration:

{
  "mcpServers": {
    "windows-mcp": {
      "command": "uvx",
      "args": [
        "windows-mcp",
        "serve"
      ],
      "env": {
        "ANONYMIZED_TELEMETRY": "false"
      }
    }
  }
}

See the Environment Variables section for the full list of configurable options.

For detailed information on what data is collected and how it is handled, please refer to the Telemetry and Data Privacy section in our Security Policy.

📝 Limitations

Selecting specific sections of the text in a paragraph, as the MCP is relying on a11y tree. (⌛ Working on it.)
Type-Tool is meant for typing text, not programming in IDE because of it types program as a whole in a file. (⌛ Working on it.)
This MCP server can't be used to play video games 🎮.

🪪 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgements

Windows-MCP makes use of several excellent open-source projects that power its Windows automation features:

UIAutomation

Huge thanks to the maintainers and contributors of these libraries for their outstanding work and open-source spirit.

🤝Contributing

Contributions are welcome! Please see CONTRIBUTING for setup instructions and development guidelines.

Made with ❤️ by CursorTouch

Citation

@software{
  author       = {CursorTouch},
  title        = {Windows-MCP: Lightweight open-source project for integrating LLM agents with Windows},
  year         = {2024},
  publisher    = {GitHub},
  url={https://github.com/CursorTouch/Windows-MCP}
}

Add this server

Host a copy with our keys and logs.

Server facts

Tools

Questions

How do I install Windows?

Does Windows need an API key?

What transport does Windows use?

When was Windows last checked?

Documentation

Updates

Supported Operating Systems

🎥 Demos

✨ Key Features

🛠️Installation

Prerequisites

Run at Login

🖥️ Running Windows-MCP

Security for Remote Access

Transport Options

🔐 Security & Access Control

Authentication

IP Allowlist

CORS Origins

Tool Selection

TLS/HTTPS

OAuth 2.0 + PKCE

Config File (~/.windows-mcp/config.toml)

Desktop control

Desktop gate policies

auth Helper

SSRF Protection

⚙️ Environment Variables

Screenshot & Snapshot

Excluding processes from UI Automation traversal

Desktop control settings

Security

Telemetry

Debug

WatchDog

🔨MCP Tools

🤝 Connect with Us

Star History

👥 Contributors

🔒 Security

📊 Telemetry

📝 Limitations

🪪 License

🙏 Acknowledgements

🤝Contributing

Citation

Config File (`~/.windows-mcp/config.toml`)

`auth` Helper