computer-control-mcp 0.3.7__tar.gz → 0.3.8__tar.gz

{computer_control_mcp-0.3.7 → computer_control_mcp-0.3.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: computer-control-mcp
-Version: 0.3.7
+Version: 0.3.8
 Summary: MCP server that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI, RapidOCR, ONNXRuntime. Similar to 'computer-use' by Anthropic. With Zero External Dependencies.
 Project-URL: Homepage, https://github.com/AB498/computer-control-mcp
 Project-URL: Issues, https://github.com/AB498/computer-control-mcp/issues
@@ -28,6 +28,7 @@ Requires-Dist: python-levenshtein>=0.20.9
 Requires-Dist: pywinctl==0.4.1
 Requires-Dist: rapidocr-onnxruntime==1.2.3
 Requires-Dist: rapidocr==3.3.1
+Requires-Dist: windows-capture>=1.0.0; sys_platform == 'win32'
 Description-Content-Type: text/markdown
 
 # Computer Control MCP
@@ -82,6 +83,99 @@ computer-control-mcp # instead of uvx computer-control-mcp, so you can use the l
 - List and activate windows
 - Press keyboard keys
 - Drag and drop operations
+- Enhanced screenshot capture for GPU-accelerated windows (Windows only)
+
+## Why Windows Graphics Capture (WGC) is Needed
+
+Traditional screenshot methods like GDI/PrintWindow cannot capture the content of GPU-accelerated windows, resulting in black screens. This affects:
+
+- **Games and 3D applications** that use DirectX/OpenGL
+- **Media players** with hardware-accelerated video decoding
+- **Electron applications** like Discord, WhatsApp, and Slack
+- **Browsers** with GPU acceleration enabled
+- **Streaming/recording software** like OBS Studio
+- **CAD and design software** that utilize GPU rendering
+
+WGC solves this by using the modern Windows Graphics Capture API, which can capture frames directly from the GPU composition surface, bypassing the limitations of traditional capture methods.
+
+## Configuration
+
+### Custom Screenshot Directory
+
+By default, screenshots are saved to the OS downloads directory. You can customize this by setting the `COMPUTER_CONTROL_MCP_SCREENSHOT_DIR` environment variable:
+
+```json
+{
+  "mcpServers": {
+    "computer-control-mcp": {
+      "command": "uvx",
+      "args": ["computer-control-mcp@latest"],
+      "env": {
+        "COMPUTER_CONTROL_MCP_SCREENSHOT_DIR": "C:\\Users\\YourName\\Pictures\\Screenshots"
+      }
+    }
+  }
+}
+```
+
+Or set it system-wide:
+```bash
+# Windows (PowerShell)
+$env:COMPUTER_CONTROL_MCP_SCREENSHOT_DIR = "C:\Users\YourName\Pictures\Screenshots"
+
+# macOS/Linux
+export COMPUTER_CONTROL_MCP_SCREENSHOT_DIR="/home/yourname/Pictures/Screenshots"
+```
+
+If the specified directory doesn't exist, the server will fall back to the default downloads directory.
+
+### Automatic WGC for Specific Windows
+
+You can configure the system to automatically use Windows Graphics Capture (WGC) for specific windows by setting the `COMPUTER_CONTROL_MCP_WGC_PATTERNS` environment variable. This variable should contain comma-separated patterns that match window titles:
+
+```json
+{
+  "mcpServers": {
+    "computer-control-mcp": {
+      "command": "uvx",
+      "args": ["computer-control-mcp@latest"],
+      "env": {
+        "COMPUTER_CONTROL_MCP_WGC_PATTERNS": "obs, discord, game, steam"
+      }
+    }
+  }
+}
+```
+
+Or set it system-wide:
+```bash
+# Windows (PowerShell)
+$env:COMPUTER_CONTROL_MCP_WGC_PATTERNS = "obs, discord, game, steam"
+
+# macOS/Linux
+export COMPUTER_CONTROL_MCP_WGC_PATTERNS="obs, discord, game, steam"
+```
+
+When this variable is set, any window whose title contains any of the specified patterns will automatically use WGC for screenshot capture, eliminating black screens for GPU-accelerated applications.
+
+## Windows Graphics Capture (WGC) Support
+
+On Windows 10 version 1803 and later, this package supports the Windows Graphics Capture (WGC) API for enhanced screenshot capabilities. This is particularly useful for capturing GPU-accelerated windows such as:
+
+- OBS Studio
+- Games and 3D applications
+- Discord, WhatsApp (Electron applications)
+- Video players with hardware decode
+- Browsers with GPU acceleration
+
+To enable WGC support, install the optional dependency:
+```bash
+pip install windows-capture
+```
+
+When WGC is available, the [take_screenshot](file:///D:/code/mcp/computer-control-mcp/src/computer_control_mcp/core.py#L305-L424) tool will automatically attempt to use it for window captures when:
+1. The `use_wgc` parameter is set to `True`
+2. The window title matches any pattern defined in the `COMPUTER_CONTROL_MCP_WGC_PATTERNS` environment variable
 
 ## Available Tools
 
@@ -100,7 +194,7 @@ computer-control-mcp # instead of uvx computer-control-mcp, so you can use the l
 - `press_keys(keys: Union[str, List[Union[str, List[str]]]])`: Press keyboard keys (supports single keys, sequences, and combinations)
 
 ### Screen and Window Management
-- `take_screenshot(title_pattern: str = None, use_regex: bool = False, threshold: int = 60, scale_percent_for_ocr: int = None, save_to_downloads: bool = False)`: Capture screen or window
+- `take_screenshot(title_pattern: str = None, use_regex: bool = False, threshold: int = 60, scale_percent_for_ocr: int = None, save_to_downloads: bool = False, use_wgc: bool = False)`: Capture screen or window
 - `take_screenshot_with_ocr(title_pattern: str = None, use_regex: bool = False, threshold: int = 10, scale_percent_for_ocr: int = None, save_to_downloads: bool = False)`: Extract adn return text with coordinates using OCR from screen or window
 - `get_screen_size()`: Get current screen resolution
 - `list_windows()`: List all open windows
@@ -116,15 +210,17 @@ computer-control-mcp # instead of uvx computer-control-mcp, so you can use the l
 git clone https://github.com/AB498/computer-control-mcp.git
 cd computer-control-mcp
 
-# Install in development mode
+# Build/Run:
+
+# 1. Install in development mode | Meaning that your edits to source code will be reflected in the installed package.
 pip install -e .
 
-# Start server
-python -m computer_control_mcp.core
+# Then Start server | This is equivalent to `uvx computer-control-mcp@latest` just the local code is used
+computer-control-mcp
 
 # -- OR --
 
-# Build after `pip install hatch`
+# 2. Build after `pip install hatch` | This needs version increment in orer to reflect code changes
 hatch build
 
 # Windows
@@ -155,4 +251,4 @@ MIT
 ## For more information or help
 
 - [Email (abcd49800@gmail.com)](mailto:abcd49800@gmail.com)
-- [Discord (CodePlayground)](https://discord.gg/ZeeqSBpjU2)
+- [Discord (CodePlayground)](https://discord.gg/ZeeqSBpjU2)

{computer_control_mcp-0.3.7 → computer_control_mcp-0.3.8}/README.md

@@ -50,6 +50,99 @@ computer-control-mcp # instead of uvx computer-control-mcp, so you can use the l
 - List and activate windows
 - Press keyboard keys
 - Drag and drop operations
+- Enhanced screenshot capture for GPU-accelerated windows (Windows only)
+
+## Why Windows Graphics Capture (WGC) is Needed
+
+Traditional screenshot methods like GDI/PrintWindow cannot capture the content of GPU-accelerated windows, resulting in black screens. This affects:
+
+- **Games and 3D applications** that use DirectX/OpenGL
+- **Media players** with hardware-accelerated video decoding
+- **Electron applications** like Discord, WhatsApp, and Slack
+- **Browsers** with GPU acceleration enabled
+- **Streaming/recording software** like OBS Studio
+- **CAD and design software** that utilize GPU rendering
+
+WGC solves this by using the modern Windows Graphics Capture API, which can capture frames directly from the GPU composition surface, bypassing the limitations of traditional capture methods.
+
+## Configuration
+
+### Custom Screenshot Directory
+
+By default, screenshots are saved to the OS downloads directory. You can customize this by setting the `COMPUTER_CONTROL_MCP_SCREENSHOT_DIR` environment variable:
+
+```json
+{
+  "mcpServers": {
+    "computer-control-mcp": {
+      "command": "uvx",
+      "args": ["computer-control-mcp@latest"],
+      "env": {
+        "COMPUTER_CONTROL_MCP_SCREENSHOT_DIR": "C:\\Users\\YourName\\Pictures\\Screenshots"
+      }
+    }
+  }
+}
+```
+
+Or set it system-wide:
+```bash
+# Windows (PowerShell)
+$env:COMPUTER_CONTROL_MCP_SCREENSHOT_DIR = "C:\Users\YourName\Pictures\Screenshots"
+
+# macOS/Linux
+export COMPUTER_CONTROL_MCP_SCREENSHOT_DIR="/home/yourname/Pictures/Screenshots"
+```
+
+If the specified directory doesn't exist, the server will fall back to the default downloads directory.
+
+### Automatic WGC for Specific Windows
+
+You can configure the system to automatically use Windows Graphics Capture (WGC) for specific windows by setting the `COMPUTER_CONTROL_MCP_WGC_PATTERNS` environment variable. This variable should contain comma-separated patterns that match window titles:
+
+```json
+{
+  "mcpServers": {
+    "computer-control-mcp": {
+      "command": "uvx",
+      "args": ["computer-control-mcp@latest"],
+      "env": {
+        "COMPUTER_CONTROL_MCP_WGC_PATTERNS": "obs, discord, game, steam"
+      }
+    }
+  }
+}
+```
+
+Or set it system-wide:
+```bash
+# Windows (PowerShell)
+$env:COMPUTER_CONTROL_MCP_WGC_PATTERNS = "obs, discord, game, steam"
+
+# macOS/Linux
+export COMPUTER_CONTROL_MCP_WGC_PATTERNS="obs, discord, game, steam"
+```
+
+When this variable is set, any window whose title contains any of the specified patterns will automatically use WGC for screenshot capture, eliminating black screens for GPU-accelerated applications.
+
+## Windows Graphics Capture (WGC) Support
+
+On Windows 10 version 1803 and later, this package supports the Windows Graphics Capture (WGC) API for enhanced screenshot capabilities. This is particularly useful for capturing GPU-accelerated windows such as:
+
+- OBS Studio
+- Games and 3D applications
+- Discord, WhatsApp (Electron applications)
+- Video players with hardware decode
+- Browsers with GPU acceleration
+
+To enable WGC support, install the optional dependency:
+```bash
+pip install windows-capture
+```
+
+When WGC is available, the [take_screenshot](file:///D:/code/mcp/computer-control-mcp/src/computer_control_mcp/core.py#L305-L424) tool will automatically attempt to use it for window captures when:
+1. The `use_wgc` parameter is set to `True`
+2. The window title matches any pattern defined in the `COMPUTER_CONTROL_MCP_WGC_PATTERNS` environment variable
 
 ## Available Tools
 
@@ -68,7 +161,7 @@ computer-control-mcp # instead of uvx computer-control-mcp, so you can use the l
 - `press_keys(keys: Union[str, List[Union[str, List[str]]]])`: Press keyboard keys (supports single keys, sequences, and combinations)
 
 ### Screen and Window Management
-- `take_screenshot(title_pattern: str = None, use_regex: bool = False, threshold: int = 60, scale_percent_for_ocr: int = None, save_to_downloads: bool = False)`: Capture screen or window
+- `take_screenshot(title_pattern: str = None, use_regex: bool = False, threshold: int = 60, scale_percent_for_ocr: int = None, save_to_downloads: bool = False, use_wgc: bool = False)`: Capture screen or window
 - `take_screenshot_with_ocr(title_pattern: str = None, use_regex: bool = False, threshold: int = 10, scale_percent_for_ocr: int = None, save_to_downloads: bool = False)`: Extract adn return text with coordinates using OCR from screen or window
 - `get_screen_size()`: Get current screen resolution
 - `list_windows()`: List all open windows
@@ -84,15 +177,17 @@ computer-control-mcp # instead of uvx computer-control-mcp, so you can use the l
 git clone https://github.com/AB498/computer-control-mcp.git
 cd computer-control-mcp
 
-# Install in development mode
+# Build/Run:
+
+# 1. Install in development mode | Meaning that your edits to source code will be reflected in the installed package.
 pip install -e .
 
-# Start server
-python -m computer_control_mcp.core
+# Then Start server | This is equivalent to `uvx computer-control-mcp@latest` just the local code is used
+computer-control-mcp
 
 # -- OR --
 
-# Build after `pip install hatch`
+# 2. Build after `pip install hatch` | This needs version increment in orer to reflect code changes
 hatch build
 
 # Windows
@@ -123,4 +218,4 @@ MIT
 ## For more information or help
 
 - [Email (abcd49800@gmail.com)](mailto:abcd49800@gmail.com)
-- [Discord (CodePlayground)](https://discord.gg/ZeeqSBpjU2)
+- [Discord (CodePlayground)](https://discord.gg/ZeeqSBpjU2)

{computer_control_mcp-0.3.7 → computer_control_mcp-0.3.8}/computer_control_mcp/cli.py

@@ -1,128 +1,128 @@
-"""
-Command-line interface for Computer Control MCP.
-
-This module provides a command-line interface for interacting with the Computer Control MCP.
-"""
-
-import argparse
-import sys
-from computer_control_mcp.core import mcp, main as run_server
-
-def parse_args():
-    """Parse command-line arguments."""
-    parser = argparse.ArgumentParser(description="Computer Control MCP CLI")
-
-    subparsers = parser.add_subparsers(dest="command", help="Command to run")
-
-    # Server command
-    server_parser = subparsers.add_parser("server", help="Run the MCP server")
-
-    # Click command
-    click_parser = subparsers.add_parser("click", help="Click at specified coordinates")
-    click_parser.add_argument("x", type=int, help="X coordinate")
-    click_parser.add_argument("y", type=int, help="Y coordinate")
-
-    # Type text command
-    type_parser = subparsers.add_parser("type", help="Type text at current cursor position")
-    type_parser.add_argument("text", help="Text to type")
-
-    # Screenshot command
-    screenshot_parser = subparsers.add_parser("screenshot", help="Take a screenshot")
-    screenshot_parser.add_argument("--mode", choices=["all_windows", "single_window", "whole_screen"],
-                                  default="whole_screen", help="Screenshot mode")
-    screenshot_parser.add_argument("--title", help="Window title pattern (for single_window mode)")
-    screenshot_parser.add_argument("--regex", action="store_true", help="Use regex for title matching")
-    screenshot_parser.add_argument("--output", help="Output file path (if not provided, saves to downloads directory)")
-    screenshot_parser.add_argument("--no-save", action="store_true", help="Don't save images to downloads directory")
-
-    # List windows command
-    subparsers.add_parser("list-windows", help="List all open windows")
-
-    # GUI command
-    subparsers.add_parser("gui", help="Launch the GUI test harness")
-
-    return parser.parse_args()
-
-def main():
-    """Main entry point for the CLI."""
-    args = parse_args()
-
-    if args.command == "server":
-        run_server()
-
-    elif args.command == "click":
-        # Call the tool using the call_tool method
-        import asyncio
-        result = asyncio.run(mcp.call_tool("click_screen", {"x": args.x, "y": args.y}))
-        print(result)
-
-    elif args.command == "type":
-        # Call the tool using the call_tool method
-        import asyncio
-        result = asyncio.run(mcp.call_tool("type_text", {"text": args.text}))
-        print(result)
-
-    elif args.command == "screenshot":
-        if args.mode == "single_window" and not args.title:
-            print("Error: --title is required for single_window mode")
-            sys.exit(1)
-
-        # Call the tool using the call_tool method
-        import asyncio
-        result = asyncio.run(mcp.call_tool("take_screenshot", {
-            "mode": args.mode,
-            "title_pattern": args.title,
-            "use_regex": args.regex,
-            "save_to_downloads": not args.no_save
-        }))
-
-        if args.output:
-            # Save the screenshot to a specific file path provided by user
-            with open(args.output, "wb") as f:
-                f.write(result.image.data)
-            print(f"Screenshot saved to {args.output}")
-        elif hasattr(result, 'file_path'):
-            # If image was saved to downloads, show the path
-            print(f"Screenshot saved to {result.file_path}")
-        else:
-            print("Screenshot taken successfully")
-
-        # If we have multiple results (all_windows mode)
-        if args.mode == "all_windows" and isinstance(result, list):
-            print("\nAll screenshots:")
-            for i, item in enumerate(result):
-                if hasattr(item, 'file_path'):
-                    window_title = item.window_info.title if hasattr(item, 'window_info') else f"Window {i+1}"
-                    print(f"{i+1}. {window_title}: {item.file_path}")
-
-    elif args.command == "list-windows":
-        # Call the tool using the call_tool method
-        import asyncio
-        result = asyncio.run(mcp.call_tool("list_windows", {}))
-
-        # Parse the result
-        windows = []
-        for item in result:
-            if hasattr(item, 'text'):
-                try:
-                    import json
-                    window_info = json.loads(item.text)
-                    windows.append(window_info)
-                except json.JSONDecodeError:
-                    print(f"Failed to parse window info: {item.text}")
-
-        # Display the windows
-        for i, window in enumerate(windows):
-            print(f"{i+1}. {window.get('title')} ({window.get('width')}x{window.get('height')})")
-
-    elif args.command == "gui":
-        from computer_control_mcp.gui import main as run_gui
-        run_gui()
-
-    else:
-        # When no command is specified, run the server by default
-        print("MCP server started!")
-        run_server()
-
-if __name__ == "__main__":
-    main()
+"""
+Command-line interface for Computer Control MCP.
+
+This module provides a command-line interface for interacting with the Computer Control MCP.
+"""
+
+import argparse
+import sys
+from computer_control_mcp.core import mcp, main as run_server
+
+def parse_args():
+    """Parse command-line arguments."""
+    parser = argparse.ArgumentParser(description="Computer Control MCP CLI")
+
+    subparsers = parser.add_subparsers(dest="command", help="Command to run")
+
+    # Server command
+    server_parser = subparsers.add_parser("server", help="Run the MCP server")
+
+    # Click command
+    click_parser = subparsers.add_parser("click", help="Click at specified coordinates")
+    click_parser.add_argument("x", type=int, help="X coordinate")
+    click_parser.add_argument("y", type=int, help="Y coordinate")
+
+    # Type text command
+    type_parser = subparsers.add_parser("type", help="Type text at current cursor position")
+    type_parser.add_argument("text", help="Text to type")
+
+    # Screenshot command
+    screenshot_parser = subparsers.add_parser("screenshot", help="Take a screenshot")
+    screenshot_parser.add_argument("--mode", choices=["all_windows", "single_window", "whole_screen"],
+                                  default="whole_screen", help="Screenshot mode")
+    screenshot_parser.add_argument("--title", help="Window title pattern (for single_window mode)")
+    screenshot_parser.add_argument("--regex", action="store_true", help="Use regex for title matching")
+    screenshot_parser.add_argument("--output", help="Output file path (if not provided, saves to downloads directory)")
+    screenshot_parser.add_argument("--no-save", action="store_true", help="Don't save images to downloads directory")
+
+    # List windows command
+    subparsers.add_parser("list-windows", help="List all open windows")
+
+    # GUI command
+    subparsers.add_parser("gui", help="Launch the GUI test harness")
+
+    return parser.parse_args()
+
+def main():
+    """Main entry point for the CLI."""
+    args = parse_args()
+
+    if args.command == "server":
+        run_server()
+
+    elif args.command == "click":
+        # Call the tool using the call_tool method
+        import asyncio
+        result = asyncio.run(mcp.call_tool("click_screen", {"x": args.x, "y": args.y}))
+        print(result)
+
+    elif args.command == "type":
+        # Call the tool using the call_tool method
+        import asyncio
+        result = asyncio.run(mcp.call_tool("type_text", {"text": args.text}))
+        print(result)
+
+    elif args.command == "screenshot":
+        if args.mode == "single_window" and not args.title:
+            print("Error: --title is required for single_window mode")
+            sys.exit(1)
+
+        # Call the tool using the call_tool method
+        import asyncio
+        result = asyncio.run(mcp.call_tool("take_screenshot", {
+            "mode": args.mode,
+            "title_pattern": args.title,
+            "use_regex": args.regex,
+            "save_to_downloads": not args.no_save
+        }))
+
+        if args.output:
+            # Save the screenshot to a specific file path provided by user
+            with open(args.output, "wb") as f:
+                f.write(result.image.data)
+            print(f"Screenshot saved to {args.output}")
+        elif hasattr(result, 'file_path'):
+            # If image was saved to downloads, show the path
+            print(f"Screenshot saved to {result.file_path}")
+        else:
+            print("Screenshot taken successfully")
+
+        # If we have multiple results (all_windows mode)
+        if args.mode == "all_windows" and isinstance(result, list):
+            print("\nAll screenshots:")
+            for i, item in enumerate(result):
+                if hasattr(item, 'file_path'):
+                    window_title = item.window_info.title if hasattr(item, 'window_info') else f"Window {i+1}"
+                    print(f"{i+1}. {window_title}: {item.file_path}")
+
+    elif args.command == "list-windows":
+        # Call the tool using the call_tool method
+        import asyncio
+        result = asyncio.run(mcp.call_tool("list_windows", {}))
+
+        # Parse the result
+        windows = []
+        for item in result:
+            if hasattr(item, 'text'):
+                try:
+                    import json
+                    window_info = json.loads(item.text)
+                    windows.append(window_info)
+                except json.JSONDecodeError:
+                    print(f"Failed to parse window info: {item.text}")
+
+        # Display the windows
+        for i, window in enumerate(windows):
+            print(f"{i+1}. {window.get('title')} ({window.get('width')}x{window.get('height')})")
+
+    elif args.command == "gui":
+        from computer_control_mcp.gui import main as run_gui
+        run_gui()
+
+    else:
+        # When no command is specified, run the server by default
+        print("MCP server started!")
+        run_server()
+
+if __name__ == "__main__":
+    main()

{computer_control_mcp-0.3.7 → computer_control_mcp-0.3.8}/computer_control_mcp/core.py

@@ -18,6 +18,7 @@ import datetime
 from pathlib import Path
 import tempfile
 from typing import Union
+import threading
 
 # --- Auto-install dependencies if needed ---
 import pyautogui
@@ -48,6 +49,14 @@ RELOAD_ENABLED = True  # Set to False to disable auto-reload
 mcp = FastMCP("ComputerControlMCP")
 
 
+# Try to import Windows Graphics Capture API
+try:
+    from windows_capture import WindowsCapture, Frame, InternalCaptureControl
+    WGC_AVAILABLE = True
+except ImportError:
+    WGC_AVAILABLE = False
+
+
 # Determine mode automatically
 IS_DEVELOPMENT = os.getenv("ENV") == "development"
 
@@ -64,7 +73,21 @@ def log(message: str) -> None:
 
 
 def get_downloads_dir() -> Path:
-    """Get the OS downloads directory."""
+    """Get the directory for saving screenshots.
+
+    Checks for COMPUTER_CONTROL_MCP_SCREENSHOT_DIR environment variable first,
+    then falls back to the OS downloads directory.
+    """
+    # Check for custom directory from environment variable
+    custom_dir = os.getenv("COMPUTER_CONTROL_MCP_SCREENSHOT_DIR")
+    if custom_dir:
+        custom_path = Path(custom_dir)
+        if custom_path.exists() and custom_path.is_dir():
+            return custom_path
+        else:
+            log(f"Warning: COMPUTER_CONTROL_MCP_SCREENSHOT_DIR path '{custom_dir}' does not exist or is not a directory. Falling back to default.")
+
+    # Default: OS downloads directory
     if os.name == "nt":  # Windows
         import winreg
 
@@ -77,6 +100,39 @@ def get_downloads_dir() -> Path:
         return Path.home() / "Downloads"
 
 
+def _should_use_wgc_by_default(window_title: str) -> bool:
+    """Check if WGC should be used for a window based on environment variable patterns.
+    
+    Checks the COMPUTER_CONTROL_MCP_WGC_PATTERNS environment variable, which should
+    contain comma-separated patterns. If any pattern matches the window title,
+    WGC will be used by default.
+    
+    Args:
+        window_title: Title of the window to check
+        
+    Returns:
+        True if WGC should be used by default for this window, False otherwise
+    """
+    # Get patterns from environment variable
+    patterns_str = os.getenv("COMPUTER_CONTROL_MCP_WGC_PATTERNS")
+    if not patterns_str:
+        return False
+    
+    # Split patterns by comma and trim whitespace
+    patterns = [pattern.strip().lower() for pattern in patterns_str.split(",") if pattern.strip()]
+    
+    # Convert window title to lowercase for case-insensitive matching
+    title_lower = window_title.lower()
+    
+    # Check if any pattern matches
+    for pattern in patterns:
+        if pattern in title_lower:
+            log(f"Window '{window_title}' matches WGC pattern: {pattern}")
+            return True
+    
+    return False
+
+
 def _mss_screenshot(region=None):
     """Take a screenshot using mss and return PIL Image.
 
@@ -107,6 +163,88 @@ def _mss_screenshot(region=None):
         )
 
 
+def _wgc_screenshot(window_title: str) -> Optional[Tuple[bytes, int, int]]:
+    """Capture a window using Windows Graphics Capture API.
+    
+    Args:
+        window_title: Title of the window to capture
+        
+    Returns:
+        Tuple of (image_bytes, width, height) or None if failed
+    """
+    if not WGC_AVAILABLE:
+        log("Windows Graphics Capture API not available")
+        return None
+        
+    captured_frame = {"data": None, "width": 0, "height": 0, "error": None}
+    capture_event = threading.Event()
+
+    try:
+        capture = WindowsCapture(
+            cursor_capture=False,
+            draw_border=False,
+            monitor_index=None,
+            window_name=window_title,
+        )
+
+        @capture.event
+        def on_frame_arrived(frame: Frame, capture_control: InternalCaptureControl):
+            try:
+                # Save frame to temp file, then read it back
+                with tempfile.NamedTemporaryFile(suffix=".png", delete=False) as tmp:
+                    tmp_path = tmp.name
+
+                frame.save_as_image(tmp_path)
+
+                with open(tmp_path, "rb") as f:
+                    captured_frame["data"] = f.read()
+
+                # Get dimensions from the saved image
+                with PILImage.open(tmp_path) as img:
+                    captured_frame["width"] = img.width
+                    captured_frame["height"] = img.height
+
+                os.unlink(tmp_path)
+            except Exception as e:
+                captured_frame["error"] = str(e)
+            finally:
+                capture_control.stop()
+                capture_event.set()
+
+        @capture.event
+        def on_closed():
+            capture_event.set()
+
+        # Start capture in a thread
+        def run_capture():
+            try:
+                capture.start()
+            except Exception as e:
+                captured_frame["error"] = str(e)
+                capture_event.set()
+
+        thread = threading.Thread(target=run_capture, daemon=True)
+        thread.start()
+
+        # Wait for frame (with timeout)
+        if not capture_event.wait(timeout=5.0):
+            captured_frame["error"] = "Capture timed out"
+
+        if captured_frame["error"]:
+            log(f"WGC capture error: {captured_frame['error']}")
+            return None
+
+        if captured_frame["data"] is None:
+            log("No frame captured with WGC")
+            return None
+
+        return captured_frame["data"], captured_frame["width"], captured_frame["height"]
+
+    except Exception as e:
+        log(f"WGC capture failed: {e}")
+        return None
+
+
 def save_image_to_downloads(
     image, prefix: str = "screenshot", directory: Path = None
 ) -> Tuple[str, bytes]:
@@ -240,6 +378,7 @@ def take_screenshot(
     threshold: int = 10,
     scale_percent_for_ocr: int = None,
     save_to_downloads: bool = False,
+    use_wgc: bool = False,
 ) -> Image:
     """
     Get screenshot Image as MCP Image object. If no title pattern is provided, get screenshot of entire screen and all text on the screen.
@@ -250,6 +389,7 @@ def take_screenshot(
         threshold: Minimum score (0-100) required for a fuzzy match
         scale_percent_for_ocr: Percentage to scale the image down before processing, you wont need this most of the time unless your pc is extremely old or slow
         save_to_downloads: If True, save the screenshot to the downloads directory and return the absolute path
+        use_wgc: If True, use Windows Graphics Capture API for window capture (recommended for GPU-accelerated windows)
 
     Returns:
         Returns a single screenshot as MCP Image object. "content type image not supported" means preview isnt supported but Image object is there and returned successfully.
@@ -305,22 +445,55 @@ def take_screenshot(
                 current_active_window = gw.getActiveWindow()
                 log(f"Taking screenshot of window: {window.title}")
 
-                if sys.platform == "win32":
-                    force_activate(window)
+                # Determine if we should use WGC:
+                # 1. If explicitly requested via use_wgc parameter
+                # 2. If the window matches patterns defined in environment variable
+                should_use_wgc = use_wgc or _should_use_wgc_by_default(window.title)
+                
+                # Try WGC capture first if requested or if it's likely a GPU-accelerated window
+                if should_use_wgc and WGC_AVAILABLE:
+                    log("Attempting WGC capture")
+                    wgc_result = _wgc_screenshot(window.title)
+                    if wgc_result:
+                        image_bytes, width, height = wgc_result
+                        screenshot = PILImage.open(BytesIO(image_bytes))
+                        log(f"WGC capture successful: {width}x{height}")
+                    else:
+                        log("WGC capture failed, falling back to MSS")
+                        # Fall back to MSS if WGC fails
+                        if sys.platform == "win32":
+                            force_activate(window)
+                        else:
+                            window.activate()
+                        pyautogui.sleep(0.5)  # Give Windows time to focus
+
+                        screen_width, screen_height = pyautogui.size()
+
+                        screenshot = _mss_screenshot(
+                            region=(
+                                max(window.left, 0),
+                                max(window.top, 0),
+                                min(window.width, screen_width),
+                                min(window.height, screen_height),
+                            )
+                        )
                 else:
-                    window.activate()
-                pyautogui.sleep(0.5)  # Give Windows time to focus
-
-                screen_width, screen_height = pyautogui.size()
-
-                screenshot = _mss_screenshot(
-                    region=(
-                        max(window.left, 0),
-                        max(window.top, 0),
-                        min(window.width, screen_width),
-                        min(window.height, screen_height),
+                    if sys.platform == "win32":
+                        force_activate(window)
+                    else:
+                        window.activate()
+                    pyautogui.sleep(0.5)  # Give Windows time to focus
+
+                    screen_width, screen_height = pyautogui.size()
+
+                    screenshot = _mss_screenshot(
+                        region=(
+                            max(window.left, 0),
+                            max(window.top, 0),
+                            min(window.width, screen_width),
+                            min(window.height, screen_height),
+                        )
                     )
-                )
 
                 # Restore previously active window
                 if current_active_window and current_active_window != window:
@@ -737,6 +910,16 @@ def main():
     """Main entry point for the MCP server."""
     pyautogui.FAILSAFE = True
 
+    if WGC_AVAILABLE:
+        log("Windows Graphics Capture API is available for enhanced window capture")
+        # Check if any WGC patterns are configured
+        wgc_patterns = os.getenv("COMPUTER_CONTROL_MCP_WGC_PATTERNS")
+        if wgc_patterns:
+            patterns = [p.strip() for p in wgc_patterns.split(",") if p.strip()]
+            log(f"WGC patterns configured: {patterns}")
+    else:
+        log("Windows Graphics Capture API not available. Using standard capture methods.")
+
     try:
         # Run the server
         log("Computer Control MCP Server Started...")
@@ -749,4 +932,4 @@ def main():
 
 
 if __name__ == "__main__":
-    main()
+    main()

{computer_control_mcp-0.3.7 → computer_control_mcp-0.3.8}/computer_control_mcp/server.py

@@ -1,15 +1,15 @@
-"""
-Server module for Computer Control MCP.
-
-This module provides a simple way to run the MCP server.
-"""
-
-from computer_control_mcp.core import main as run_server
-
-def main():
-    """Run the MCP server."""
-    print("Starting Computer Control MCP server...")
-    run_server()
-
-if __name__ == "__main__":
-    main()
+"""
+Server module for Computer Control MCP.
+
+This module provides a simple way to run the MCP server.
+"""
+
+from computer_control_mcp.core import main as run_server
+
+def main():
+    """Run the MCP server."""
+    print("Starting Computer Control MCP server...")
+    run_server()
+
+if __name__ == "__main__":
+    main()

{computer_control_mcp-0.3.7 → computer_control_mcp-0.3.8}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "computer-control-mcp"
-version = "0.3.7"
+version = "0.3.8"
 description = "MCP server that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI, RapidOCR, ONNXRuntime. Similar to 'computer-use' by Anthropic. With Zero External Dependencies."
 readme = "README.md"
 requires-python = ">=3.8"
@@ -31,7 +31,8 @@ dependencies = [
     "rapidocr_onnxruntime==1.2.3",
     "opencv-python==4.12.0.88",
     "python-Levenshtein>=0.20.9",
-    "mss>=7.0.0"
+    "mss>=7.0.0",
+    "windows-capture>=1.0.0; sys_platform=='win32'"
 ]
 
 [project.urls]