Windows-MCP

[![MseeP.ai Security Assessment Badge](https://mseep.net/pr/cursortouch-windows-mcp-badge.png)](https://mseep.ai/app/cursortouch-windows-mcp)

<div align="center">
  <h1>🪟 Windows-MCP</h1>

  <a href="https://github.com/CursorTouch/Windows-MCP/blob/main/LICENSE">
    <img src="https://img.shields.io/badge/license-MIT-green" alt="License">
  </a>
  <img src="https://img.shields.io/badge/python-3.13%2B-blue" alt="Python">
  <img src="https://img.shields.io/badge/platform-Windows%207–11-blue" alt="Platform: Windows 7 to 11">
  <img src="https://img.shields.io/github/last-commit/CursorTouch/Windows-MCP" alt="Last Commit">
  <br>
  <a href="https://x.com/CursorTouch">
    <img src="https://img.shields.io/badge/follow-%40CursorTouch-1DA1F2?logo=twitter&style=flat" alt="Follow on Twitter">
  </a>
  <a href="https://discord.com/invite/Aue9Yj2VzS">
    <img src="https://img.shields.io/badge/Join%20on-Discord-5865F2?logo=discord&logoColor=white&style=flat" alt="Join us on Discord">
  </a>

</div>

<br>

**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](https://claude.ai/directory). 
- Try out [🪟Windows-Use](https://pypi.org/project/windows-use/), an agent built using Windows-MCP.
- Windows-MCP is now available on [PyPI](https://pypi.org/project/windows-mcp/) (thus supports `uvx windows-mcp`)
- Windows-MCP is added to [MCP Registry](https://github.com/modelcontextprotocol/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:

```shell
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:

```shell
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`.

<details>
  <summary>Install in Claude Desktop</summary>

  1. Install [Claude Desktop](https://claude.ai/download).

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

  **Option B: Install from Source**

  1. Clone the repository:
  ```shell
  git clone https://github.com/CursorTouch/Windows-MCP.git
  cd Windows-MCP
  ```

  2. Add this to your `claude_desktop_config.json`:
  ```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:
  ```json
  {
    "mcpServers": {
      "windows-mcp": {
        "command": "C:\\Users\\<user>\\.local\\bin\\windows-mcp.exe",
        "args": ["serve"]
      }
    }
  }
  ```

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

  **Option C: Install from Source**
  ```json
  {
    "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](https://modelcontextprotocol.io/quickstart/server#claude-for-desktop-integration-issues).
</details>

<details>
  <summary>Install in Perplexity Desktop</summary>

  1. Install [Perplexity Desktop](https://apps.microsoft.com/detail/xp8jnqfbqh6pvf).
  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)**

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

  **Option B: Install from Source**

  ```json
  {
    "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](https://www.perplexity.ai/help-center/en/articles/11502712-local-and-remote-mcps-for-perplexity). The documentation includes helpful tips for checking logs and resolving common issues.
</details>

<details>
  <summary> Install in Gemini CLI</summary>

  1. Install Gemini CLI.

```shell
npm install -g @google/gemini-cli
```

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

```json
{
  "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.
</details>

<details>
  <summary>Install in Qwen Code</summary>
  1. Install Qwen Code.

```shell
npm install -g @qwen-code/qwen-code@latest
```
  2. Open `%USERPROFILE%/.qwen/settings.json`.
  3. Add the `windows-mcp` config and save it.

```json
{
  "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.
</details>

<details>
  <summary>