Windows Automation MCP Server

Instructions

Implementation Reference

• src/tools/window.js:159-187 (handler)

  The main handler function `getActiveWindow()` that executes a PowerShell script using Windows API calls (GetForegroundWindow and GetWindowText) to retrieve and return the title of the currently active (foreground) window.

    async getActiveWindow() {
      try {
        const script = `
          Add-Type @"
            using System;
            using System.Runtime.InteropServices;
            using System.Text;
            public class Win32 {
              [DllImport("user32.dll")]
              public static extern IntPtr GetForegroundWindow();
              [DllImport("user32.dll")]
              public static extern int GetWindowText(IntPtr hWnd, StringBuilder lpString, int nMaxCount);
            }
  "@
          $hWnd = [Win32]::GetForegroundWindow()
          $title = New-Object System.Text.StringBuilder 256
          [Win32]::GetWindowText($hWnd, $title, 256)
          $title.ToString()
        `;
  
        const { stdout } = await execAsync(`powershell -Command "${script.replace(/"/g, '\\"')}"`, {
          shell: 'powershell.exe'
        });
  
        return { success: true, window: stdout.trim() };
      } catch (error) {
        return { success: false, error: error.message };
      }
    }

• src/tools/window.js:22-29 (schema)

  Tool definition including name, description, and input schema (empty object, no parameters required).

  {
    name: 'get_active_window',
    description: '获取当前激活的窗口',
    inputSchema: {
      type: 'object',
      properties: {},
    },
  },

• src/tools/window.js:87-88 (registration)

  Switch case in `executeTool` method that registers and dispatches calls to the `get_active_window` tool by invoking the handler method.

  case 'get_active_window':
    return await this.getActiveWindow();

• src/server.js:47-52 (registration)

  Instantiation of WindowTools class in the main tools registry object, enabling discovery and execution of its tools including get_active_window.

    window: new WindowTools(),
    screen: new ScreenTools(),
    clipboard: new ClipboardTools(),
    powershell: new PowerShellTools(),
    browser: new BrowserTools(),
  };

• src/tools/window.js:78-80 (helper)

  The `canHandle` method's tools list explicitly includes 'get_active_window' for tool name validation.

  const tools = ['list_windows', 'get_active_window', 'activate_window', 
                 'close_window', 'minimize_window', 'maximize_window'];
  return tools.includes(toolName);