Windows Automation MCP Server
Provides browser automation capabilities including launching browsers, navigating to web pages, clicking elements, inputting text, taking screenshots, and extracting text from elements.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Windows Automation MCP Server take a screenshot of my desktop and save it to the Pictures folder"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Windows 完全自动化 MCP 服务器
这是一个功能强大的 Windows 自动化 MCP 服务器,提供完整的 Windows 系统控制能力。
🎯 功能特性
1. 文件系统操作
✅ 读写文件
✅ 创建/删除/移动/复制文件
✅ 列出目录内容
✅ 搜索文件
2. 进程管理
✅ 启动应用程序
✅ 结束进程
✅ 列出进程
✅ 获取进程信息
3. 鼠标键盘控制
⚠️ 移动鼠标
⚠️ 鼠标点击
⚠️ 输入文本
⚠️ 按键模拟
⚠️ 获取鼠标位置
⚠️ 获取屏幕尺寸
⚠️ 注意:鼠标键盘功能需要
robotjs,需要 Windows Build Tools
4. 窗口管理
✅ 列出所有窗口
✅ 获取当前活动窗口
✅ 激活窗口
✅ 关闭窗口
✅ 最小化窗口
5. 屏幕截图
✅ 全屏截图
✅ 区域截图
✅ 自定义保存路径
6. 剪贴板操作
✅ 获取剪贴板内容
✅ 设置剪贴板内容
✅ 清空剪贴板
7. PowerShell/CMD
✅ 执行 PowerShell 命令
✅ 执行 CMD 命令
✅ 获取系统信息
✅ 获取磁盘信息
✅ 获取网络信息
8. 浏览器自动化
⚠️ 启动浏览器
⚠️ 导航到网页
⚠️ 点击元素
⚠️ 输入文本
⚠️ 截图
⚠️ 获取元素文本
⚠️ 注意:浏览器功能需要
puppeteer
📦 安装
1. 基础安装(必需)
cd windows-automation-mcp
npm install2. 可选依赖
鼠标键盘控制(robotjs)
# 需要先安装 Windows Build Tools
npm install --global windows-build-tools
# 然后安装 robotjs
npm install robotjs浏览器自动化(puppeteer)
npm install puppeteer🚀 使用方法
1. 在 Cursor 中配置
在 Cursor 的 MCP 配置文件中添加:
{
"mcpServers": {
"windows-automation": {
"command": "node",
"args": ["c:\\Users\\Administrator\\Desktop\\cursor工作盘\\windows-automation-mcp\\src\\server.js"]
}
}
}2. 重启 Cursor
配置后重启 Cursor,MCP 服务器将自动启动。
📚 工具使用示例
文件操作
请帮我读取桌面上的 test.txt 文件
请在 D:\\temp 目录下创建一个名为 hello.txt 的文件,内容是 "Hello World"
请列出 C:\\Users 目录下的所有文件和文件夹进程管理
请帮我打开记事本
请列出所有正在运行的 chrome 进程
请结束所有 notepad.exe 进程窗口管理
请列出所有打开的窗口
请激活标题包含"记事本"的窗口
请关闭标题包含"Chrome"的窗口屏幕截图
请截取当前屏幕并保存到桌面
请截取屏幕左上角 800x600 的区域剪贴板
请获取当前剪贴板的内容
请将"Hello World"复制到剪贴板PowerShell
请执行 PowerShell 命令获取系统信息
请获取所有磁盘的使用情况
请获取当前的网络配置浏览器自动化
请启动浏览器并访问 https://www.baidu.com
请在搜索框中输入"hello world"并点击搜索按钮
请截取当前网页的完整截图⚠️ 注意事项
权限要求:某些操作可能需要管理员权限
安全性:请谨慎使用 PowerShell 和 CMD 执行功能
依赖项:部分功能需要额外安装依赖
Windows 专用:此 MCP 服务器仅支持 Windows 系统
🔧 故障排除
robotjs 安装失败
# 1. 安装 Windows Build Tools
npm install --global windows-build-tools
# 2. 重新安装 robotjs
npm install robotjspuppeteer 下载失败
# 使用国内镜像
set PUPPETEER_DOWNLOAD_HOST=https://npmmirror.com/mirrors
npm install puppeteer📝 工具列表
完整的工具列表:
文件系统 (8 个工具)
read_file, write_file, list_directory, create_directory
delete_file, copy_file, move_file, search_files
进程管理 (4 个工具)
launch_application, kill_process, list_processes, get_process_info
鼠标键盘 (6 个工具)
move_mouse, mouse_click, type_text, press_key
get_mouse_position, get_screen_size
窗口管理 (6 个工具)
list_windows, get_active_window, activate_window
close_window, minimize_window, maximize_window
屏幕截图 (2 个工具)
take_screenshot, take_screenshot_region
剪贴板 (3 个工具)
get_clipboard, set_clipboard, clear_clipboard
PowerShell (5 个工具)
run_powershell, run_cmd, get_system_info
get_disk_info, get_network_info
浏览器 (7 个工具)
browser_launch, browser_navigate, browser_click
browser_type, browser_screenshot, browser_get_text, browser_close
📄 许可证
MIT License
Available Tools
41 toolsactivate_windowC
激活指定窗口(通过标题)
Inputs: title (required).
browser_clickD
点击元素
Inputs: selector (required), sessionId.
browser_closeB
关闭浏览器
Inputs: sessionId.
browser_get_textC
获取元素文本
Inputs: selector (required), sessionId.
browser_launchC
启动浏览器
Inputs: headless, sessionId.
browser_screenshotC
截取网页截图
Inputs: path, fullPage, sessionId.
browser_typeC
输入文本到元素
Inputs: selector (required), text (required), sessionId.
clear_clipboardB
清空剪贴板
Inputs: no named parameters.
close_windowC
关闭指定窗口
Inputs: title (required).
copy_fileC
复制文件
Inputs: source (required), destination (required).
create_directoryD
创建目录
Inputs: path (required).
delete_fileC
删除文件或目录
Inputs: path (required).
get_active_windowB
获取当前激活的窗口
Inputs: no named parameters.
get_clipboardB
获取剪贴板内容
Inputs: no named parameters.
get_disk_infoC
获取磁盘信息
Inputs: no named parameters.
get_mouse_positionB
获取当前鼠标位置
Inputs: no named parameters.
get_network_infoD
获取网络信息
Inputs: no named parameters.
get_process_infoC
获取进程详细信息
Inputs: name (required).
get_screen_sizeD
获取屏幕尺寸
Inputs: no named parameters.
get_system_infoC
获取系统信息
Inputs: no named parameters.
kill_processC
结束进程
Inputs: name (required), force.
launch_applicationC
启动应用程序
Inputs: path (required), args, wait.
list_directoryC
列出目录内容
Inputs: path (required).
list_processesC
列出正在运行的进程
Inputs: filter.
list_windowsC
列出所有打开的窗口
Inputs: filter.
maximize_windowC
最大化窗口
Inputs: title (required).
minimize_windowD
最小化窗口
Inputs: title (required).
mouse_clickD
鼠标点击
Inputs: button, double.
move_fileC
移动或重命名文件
Inputs: source (required), destination (required).
move_mouseC
移动鼠标到指定位置
Inputs: x (required), y (required), smooth.
press_keyC
按下键盘按键
Inputs: key (required), modifiers.
read_fileC
读取文件内容
Inputs: path (required).
run_cmdC
执行 CMD 命令
Inputs: command (required), timeout.
run_powershellC
执行 PowerShell 命令或脚本
Inputs: command (required), timeout.
search_filesC
搜索文件(支持通配符)
Inputs: directory (required), pattern (required).
set_clipboardC
设置剪贴板内容
Inputs: text (required).
take_screenshotC
截取屏幕截图
Inputs: path, format.
take_screenshot_regionC
截取屏幕区域
Inputs: x (required), y (required), width (required), height (required), +1 more.
type_textC
输入文本
Inputs: text (required), delay.
write_fileD
写入文件内容
Inputs: path (required), content (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 41 tools
Most tools have distinct purposes targeting specific Windows automation tasks like window management, browser control, file operations, and system monitoring. However, some overlap exists: 'take_screenshot' and 'take_screenshot_region' are closely related, and 'browser_type' vs 'type_text' could cause confusion in web vs general input contexts. Descriptions help clarify, but minor ambiguity remains.
Tool names follow a highly consistent verb_noun pattern throughout, using snake_case uniformly. Examples include 'activate_window', 'browser_click', 'copy_file', and 'get_system_info'. This predictability makes the set easy to navigate and understand at a glance.
With 41 tools, the count feels heavy for a single server, potentially overwhelming for agents. While Windows automation is broad, many tools (e.g., 'get_mouse_position', 'move_mouse', 'mouse_click') could be consolidated into fewer, more general tools. It's borderline but leans toward excessive given the scope.
The tool surface comprehensively covers Windows automation domains: file management (CRUD operations), process control, window manipulation, browser automation, system monitoring, and input simulation. No obvious gaps are present; agents can perform end-to-end workflows without dead ends.
Related MCP Connectors
Connect ChatGPT, Claude, Cursor or VS Code to your Windows PC: files, terminal, browser, apps.
Control your authorized Windows computers via OAuth: files, shell, apps, and task status.
Securely control computers you explicitly pair through files, terminals, processes, screenshots, desktop UI/input, clipboard, browser automation, diagnostics, and document tools.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.