io.github.hiphopanda/windows-computer-use-mcp
Control Windows desktop via MCP: mouse, keyboard, screenshots, clipboard, and apps.
Open source Open in the app JSON README (API)
About
Control Windows desktop via MCP: mouse, keyboard, screenshots, clipboard, and apps.
Details
- Kind
- MCP servers
- Topic
- Web search, scraping & browser
- Publisher
- hiphopanda
- Origin
- official
- Category
- ferramentas
- Transport
- local
- Version
- 0.1.0
- Forks
- 1
- Last push
- 2026-04-03T10:57:45Z
- Repository state
- ativo
- Language
- TypeScript
- Added
- 2026-08-29 04:00:07
- Updated
- 2026-08-29 04:00:07
- Origin id
io.github.hiphopanda/windows-computer-use-mcp
README
# Windows Computer Use MCP Server
**English** | [中文](#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
| Tool | Description |
|------|-------------|
| `screenshot` | Take a screenshot of the current screen |
| `zoom` | Take a screenshot of a specific region |
| `mouse_move` | Move the mouse cursor to coordinates |
| `left_click` | Left-click at coordinates or current position |
| `right_click` | Right-click at coordinates |
| `double_click` | Double-click at coordinates |
| `left_click_drag` | Click and drag from one point to another |
| `scroll` | Scroll the mouse wheel |
| `type` | Type a string of text |
| `key` | Press a key combination (e.g. `ctrl+c`, `alt+f4`) |
| `hold_key` | Hold a key for a duration |
| `cursor_position` | Get current cursor position |
| `list_running_applications` | List all running apps with visible windows |
| `get_frontmost_application` | Get the currently focused app |
| `open_application` | Open an app by name or path |
| `list_displays` | List connected displays |
| `read_clipboard` | Read clipboard text |
| `write_clipboard` | Write text to clipboard |
## Installation
### Prerequisites
- [Bun](https://bun.sh/) >= 1.3.11
- Windows 10/11
### Install via npm
```bash
npm install -g windows-computer-use-mcp
```
### Install via npx (no install needed)
```bash
npx windows-computer-use-mcp
```
### Build from source
```bash
git clone https://github.com/hiphopanda/windows-computer-use-mcp.git
cd windows-computer-use-mcp
bun install
bun run build
```
## Configuration
Add to your MCP client settings (e.g. Claude Desktop):
```json
{
"mcpServers": {
"computer-use": {
"type": "stdio",
"command": "npx",
"args": ["windows-computer-use-mcp"]
}
}
}
```
Or if installed globally:
```json
{
"mcpServers": {
"computer-use": {
"type": "stdio",
"command": "windows-computer-use-mcp"
}
}
}
```
## Development
```bash
bun install # Install dependencies
bun run dev # Run in development mode
bun run build # Build to dist/
bun run start # Run built version
```
## Architecture
- **Runtime**: Bun + TypeScript
- **Transport**: stdio (MCP protocol)
- **Platform Layer**: All desktop operations go through PowerShell scripts executed via `Bun.spawn`
- **Low-level Input**: Uses Win32 P/Invoke (`user32.dll`) loaded at runtime — no precompiled native modules needed
## License
[MIT](LICENSE)
---
# 中文
一个基于 MCP（Model Context Protocol）协议的 Windows 桌面自动化服务器。通过 MCP 协议控制鼠标、键盘、截屏、剪贴板，以及管理应用程序。
> **注意**：本服务器仅支持 **Windows** 系统。
## 功能特性
- **截屏** — 全屏或指定区域截图，返回 base64 PNG
- **鼠标控制** — 移动、单击、双击、右击、拖拽、滚轮滚动
- **键盘输入** — 输入文本、按键组合、长按按键
- **光标位置** — 获取当前光标坐标
- **剪贴板** — 读写剪贴板文本
- **应用管理** — 列出运行中的应用、获取前台应用、打开应用
- **显示器信息** — 列出已连接的显示器及分辨率
## 工具列表
| 工具 | 说明 |
|------|------|
| `screenshot` | 截取当前屏幕 |
| `zoom` | 截取指定区域 |
| `mouse_move` | 移动鼠标到指定坐标 |
| `left_click` | 左键点击 |
| `right_click` | 右键点击 |
| `double_click` | 双击 |
| `left_click_drag` | 左键拖拽 |
| `scroll` | 滚动鼠标滚轮 |
| `type` | 输入文本 |
| `key` | 按键组合（如 `ctrl+c`、`alt+f4`） |
| `hold_key` | 长按按键 |
| `cursor_position` | 获取光标当前位置 |
| `list_running_applications` | 列出所有运行中的应用 |
| `get_frontmost_application` | 获取当前前台应用 |
| `open_application` | 按名称或路径打开应用 |
| `list_displays` | 列出已连接的显示器 |
| `read_clipboard` | 读取剪贴板文本 |
| `write_clipboard` | 写入文本到剪贴板 |
## 安装
### 环境要求
- [Bun](https://bun.sh/) >= 1.3.11
- Windows 10/11
### 通过 npm 安装
```bash
npm install -g windows-computer-use-mcp
```
### 通过 npx 运行（无需安装）
```bash
npx windows-computer-use-mcp
```
### 从源码构建
```bash
git clone https://github.com/hiphopanda/windows-computer-use-mcp.git
cd windows-computer-use-mcp
bun install
bun run build
```
## 配置
在 MCP 客户端配置中添加（如 Claude Desktop）：
```json
{
"mcpServers": {
"computer-use": {
"type": "stdio",
"command": "npx",
"args": ["windows-computer-use-mcp"]
}
}
}
```
或全局安装后：
```json
{
"mcpServers": {
"computer-use": {
"type": "stdio",
"command": "windows-computer-use-mcp"
}
}
}
```
## 开发
```bash
bun install # 安装依赖
bun run dev # 开发模式运行
bun run build # 构建到 dist/
bun run start # 运行构建产物
```
## 架构
- **运行时**：Bun + TypeScript
- **传输层**：stdio（MCP 协议）
- **平台层**：所有桌面操作通过 `Bun.spawn` 执行 PowerShell 脚本
- **底层输入**：通过 Win32 P/Invoke（`user32.dll`）在运行时加载 — 无需预编译原生模块
## 许可证
[MIT](LICENSE)