🪟 Windows-MCP

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 7
• Windows 8, 8.1
• Windows 10
• Windows 11

🎥 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 3.13+
• UV (Package Manager) from Astra, install with pip install uv or curl -LsSf https://astral.sh/uv/install.sh | sh
• English as the default language in Windows preferred else disable the App-Tool in the MCP Server for Windows with other languages.

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.

1. Install Claude Desktop.

npm install -g @anthropic-ai/mcpb

2. 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

1. Clone the repository:

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

2. 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"
      ]
    }
  }
}

3. 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:

1. The config file is located at: %LOCALAPPDATA%\Packages\Claude_pzs8sxrjxfjjc\LocalCache\Roaming\Claude\claude_desktop_config.json (not %APPDATA%\Claude\).
2. 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

1. In a terminal, run uv tool install windows-mcp.
2. 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.

1. Install Perplexity Desktop.
2. Open Perplexity Desktop and go to Settings -> Connectors -> Add Connector -> Advanced.
3. 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"
  ]
}

4. 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.

1. Install Gemini CLI.

npm install -g @google/gemini-cli

2. Open %USERPROFILE%/.gemini/settings.json.
3. 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"].

4. Restart Gemini CLI.

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

2. Open %USERPROFILE%/.qwen/settings.json.
3. 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"].

4. Restart Qwen Code.

npm install -g @openai/codex

2. Open %USERPROFILE%/.codex/config.toml.
3. 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"].

4. 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.

1. Install Claude Code:

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

2. 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

1. Clone the repository:

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

2. 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.

3. 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:

1. Install uv on Windows (from a PowerShell terminal):

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

2. 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.

3. 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:

1. --config /path/to/config.toml
2. ~/.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

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.

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 on to run streamable-http without Mcp-Session-Id 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