computer-control-mcp 0.3.0__tar.gz → 0.3.3__tar.gz

{computer_control_mcp-0.3.0 → computer_control_mcp-0.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: computer-control-mcp
-Version: 0.3.0
+Version: 0.3.3
 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
@@ -18,12 +18,14 @@ Classifier: Topic :: Utilities
 Requires-Python: >=3.10
 Requires-Dist: fuzzywuzzy==0.18.0
 Requires-Dist: mcp[cli]==1.13.0
-Requires-Dist: onnxruntime==1.22.1
+Requires-Dist: mss>=7.0.0
+Requires-Dist: onnxruntime==1.22.0
 Requires-Dist: opencv-python==4.12.0.88
 Requires-Dist: pillow==11.3.0
 Requires-Dist: pyautogui==0.9.54
 Requires-Dist: pygetwindow==0.0.9
-Requires-Dist: rapidocr-onnxruntime==1.4.4
+Requires-Dist: pywinctl==0.4.1
+Requires-Dist: rapidocr-onnxruntime==1.2.3
 Requires-Dist: rapidocr==3.3.1
 Description-Content-Type: text/markdown
 
@@ -31,12 +33,15 @@ Description-Content-Type: text/markdown
 
 ### 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.
 
-* *Only tested on Windows. Should work on other platforms.*
-
-<div style="text-align:center;font-family: monospace; display: flex; align-items: center; justify-content: center; width: 100%; gap: 10px">
-        <a href="https://discord.gg/ZeeqSBpjU2"><img src="https://img.shields.io/discord/1095854826786668545" alt="Discord"></a>
-        <a href="https://img.shields.io/badge/License-MIT-yellow.svg"><img
-                src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a>
+<div align="center" style="text-align:center;font-family: monospace; display: flex; align-items: center; justify-content: center; width: 100%; gap: 10px">
+    <a href="https://nextjs-boilerplate-ashy-nine-64.vercel.app/demo-computer-control"><img
+            src="https://komarev.com/ghpvc/?username=AB498&label=DEMO&style=for-the-badge&color=CC0000" /></a>
+    <a href="https://discord.gg/ZeeqSBpjU2"><img
+            src="https://img.shields.io/discord/1095854826786668545?style=for-the-badge&color=0000CC" alt="Discord"></a>
+    <a href="https://img.shields.io/badge/License-MIT-yellow.svg"><img
+            src="https://img.shields.io/badge/License-MIT-yellow.svg?style=for-the-badge&color=00CC00" alt="License: MIT"></a>
+    <a href="https://pypi.org/project/computer-control-mcp"><img
+            src="https://img.shields.io/pypi/v/computer-control-mcp?style=for-the-badge" alt="PyPi"></a>
 </div>
 
 ---

{computer_control_mcp-0.3.0 → computer_control_mcp-0.3.3}/README.md

@@ -2,12 +2,15 @@
 
 ### 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.
 
-* *Only tested on Windows. Should work on other platforms.*
-
-<div style="text-align:center;font-family: monospace; display: flex; align-items: center; justify-content: center; width: 100%; gap: 10px">
-        <a href="https://discord.gg/ZeeqSBpjU2"><img src="https://img.shields.io/discord/1095854826786668545" alt="Discord"></a>
-        <a href="https://img.shields.io/badge/License-MIT-yellow.svg"><img
-                src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a>
+<div align="center" style="text-align:center;font-family: monospace; display: flex; align-items: center; justify-content: center; width: 100%; gap: 10px">
+    <a href="https://nextjs-boilerplate-ashy-nine-64.vercel.app/demo-computer-control"><img
+            src="https://komarev.com/ghpvc/?username=AB498&label=DEMO&style=for-the-badge&color=CC0000" /></a>
+    <a href="https://discord.gg/ZeeqSBpjU2"><img
+            src="https://img.shields.io/discord/1095854826786668545?style=for-the-badge&color=0000CC" alt="Discord"></a>
+    <a href="https://img.shields.io/badge/License-MIT-yellow.svg"><img
+            src="https://img.shields.io/badge/License-MIT-yellow.svg?style=for-the-badge&color=00CC00" alt="License: MIT"></a>
+    <a href="https://pypi.org/project/computer-control-mcp"><img
+            src="https://img.shields.io/pypi/v/computer-control-mcp?style=for-the-badge" alt="PyPi"></a>
 </div>
 
 ---

{computer_control_mcp-0.3.0 → computer_control_mcp-0.3.3}/computer_control_mcp/core.py

@@ -17,23 +17,28 @@ import uuid
 import datetime
 from pathlib import Path
 import tempfile
+from typing import Union
 
 # --- Auto-install dependencies if needed ---
 import pyautogui
 from mcp.server.fastmcp import FastMCP, Image
-import pygetwindow as gw
+import mss
+from PIL import Image as PILImage
+
+try:
+    import pywinctl as gw
+except (NotImplementedError, ImportError):
+    import pygetwindow as gw
 from fuzzywuzzy import fuzz, process
 
 import cv2
 from rapidocr import RapidOCR
-from rapidocr_onnxruntime import VisRes
 
 from pydantic import BaseModel
 
-BaseModel.model_config = {'arbitrary_types_allowed': True}
+BaseModel.model_config = {"arbitrary_types_allowed": True}
 
 engine = RapidOCR()
-vis = VisRes()
 
 
 DEBUG = True  # Set to False in production
@@ -43,9 +48,19 @@ RELOAD_ENABLED = True  # Set to False to disable auto-reload
 mcp = FastMCP("ComputerControlMCP")
 
 
+# Determine mode automatically
+IS_DEVELOPMENT = os.getenv("ENV") == "development"
+
+
 def log(message: str) -> None:
-    """Log a message to stderr."""
-    print(f"STDOUT: {message}", file=sys.stderr)
+    """Log to stderr in dev, to stdout or file in production."""
+    if IS_DEVELOPMENT:
+        # In dev, write to stderr
+        print(f"[DEV] {message}", file=sys.stderr)
+    else:
+        # In production, write to stdout or a file
+        print(f"[PROD] {message}", file=sys.stdout)
+        # or append to a file: open("app.log", "a").write(message+"\n")
 
 
 def get_downloads_dir() -> Path:
@@ -62,6 +77,36 @@ def get_downloads_dir() -> Path:
         return Path.home() / "Downloads"
 
 
+def _mss_screenshot(region=None):
+    """Take a screenshot using mss and return PIL Image.
+
+    Args:
+        region: Optional tuple (left, top, width, height) for region capture
+
+    Returns:
+        PIL Image object
+    """
+    with mss.mss() as sct:
+        if region is None:
+            # Full screen screenshot
+            monitor = sct.monitors[0]  # All monitors combined
+        else:
+            # Region screenshot
+            left, top, width, height = region
+            monitor = {
+                "left": left,
+                "top": top,
+                "width": width,
+                "height": height,
+            }
+
+        screenshot = sct.grab(monitor)
+        # Convert to PIL Image
+        return PILImage.frombytes(
+            "RGB", screenshot.size, screenshot.bgra, "raw", "BGRX"
+        )
+
+
 def save_image_to_downloads(
     image, prefix: str = "screenshot", directory: Path = None
 ) -> Tuple[str, bytes]:
@@ -106,7 +151,7 @@ def _find_matching_window(
     windows: any,
     title_pattern: str = None,
     use_regex: bool = False,
-    threshold: int = 60,
+    threshold: int = 10,
 ) -> Optional[Dict[str, Any]]:
     """Helper function to find a matching window based on title pattern.
 
@@ -153,6 +198,7 @@ def _find_matching_window(
 
 # --- MCP Function Handlers ---
 
+
 @mcp.tool()
 def click_screen(x: int, y: int) -> str:
     """Click at the specified screen coordinates."""
@@ -191,28 +237,168 @@ def type_text(text: str) -> str:
 def take_screenshot(
     title_pattern: str = None,
     use_regex: bool = False,
-    threshold: int = 60,
-    with_ocr_text_and_coords: bool = False,
+    threshold: int = 10,
     scale_percent_for_ocr: int = None,
     save_to_downloads: bool = False,
-) -> Image | List[Tuple[List[List[int]], str, float]]:
+) -> Image:
     """
-    Get screenshot and  OCR text with absolute coordinates (returned after adding the window offset from true (0, 0) of screen to the OCR coordinates, so clicking is on-point. Recommended to click in the middle of OCR Box) and confidence from window with the specified title pattern.
+    Get screenshot Image as MCP Image object.
     If no title pattern is provided, get screenshot of entire screen and all text on the screen.
 
     Args:
         title_pattern: Pattern to match window title, if None, take screenshot of entire screen
         use_regex: If True, treat the pattern as a regex, otherwise best match with fuzzy matching
         threshold: Minimum score (0-100) required for a fuzzy match
-        with_ocr_text_and_coords: If True, get OCR text with absolute coordinates from the screenshot
         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
 
     Returns:
-        Returns a single screenshot as MCP Image object, if with_ocr_text_and_coords is True, returns a MCP Image object followed by list of UI elements as [[4 corners of box], text, confidence], "content type image not supported" means preview isnt supported but Image object is there.
+        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.
     """
     try:
+        all_windows = gw.getAllWindows()
+
+        # Convert to list of dictionaries for _find_matching_window
+        windows = []
+        for window in all_windows:
+            if window.title:  # Only include windows with titles
+                windows.append(
+                    {
+                        "title": window.title,
+                        "window_obj": window,  # Store the actual window object
+                    }
+                )
+
+        log(f"Found {len(windows)} windows")
+        window = _find_matching_window(windows, title_pattern, use_regex, threshold)
+        window = window["window_obj"] if window else None
+
+        import ctypes
+        import time
+
+        def force_activate(window):
+            """Force a window to the foreground on Windows."""
+            try:
+                hwnd = window._hWnd  # pywinctl window handle
+
+                # Restore if minimized
+                if window.isMinimized:
+                    window.restore()
+                    time.sleep(0.1)
+
+                # Bring to top and set foreground
+                ctypes.windll.user32.SetForegroundWindow(hwnd)
+                ctypes.windll.user32.BringWindowToTop(hwnd)
+                window.activate()  # fallback
+                time.sleep(0.3)  # wait for OS to update
+
+            except Exception as e:
+                print(f"Warning: Could not force window: {e}", file=sys.stderr)
+
+        # Take the screenshot
+        if not window:
+            log("No matching window found, taking screenshot of entire screen")
+            screenshot = _mss_screenshot()
+        else:
+            try:
+                # Re-fetch window handle to ensure it's valid
+                window = gw.getWindowsWithTitle(window.title)[0]
+                current_active_window = gw.getActiveWindow()
+                log(f"Taking screenshot of window: {window.title}")
+
+                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:
+                    try:
+                        if sys.platform == "win32":
+                            force_activate(current_active_window)
+                        else:
+                            current_active_window.activate()
+                        pyautogui.sleep(0.2)
+                    except Exception as e:
+                        log(f"Error restoring previous window: {str(e)}")
+            except Exception as e:
+                log(f"Error taking screenshot of window: {str(e)}")
+                screenshot = _mss_screenshot()  # fallback to full screen
+
+        # Create temp directory
+        temp_dir = Path(tempfile.mkdtemp())
+
+        # Save screenshot and get filepath
+        filepath, _ = save_image_to_downloads(
+            screenshot, prefix="screenshot", directory=temp_dir
+        )
+
+        # Create Image object from filepath
+        image = Image(filepath)
+
+        if save_to_downloads:
+            log("Copying screenshot from temp to downloads")
+            shutil.copy(filepath, get_downloads_dir())
+
+        return image  # MCP Image object
+
+    except Exception as e:
+        log(f"Error in screenshot or getting UI elements: {str(e)}")
+        import traceback
+
+        stack_trace = traceback.format_exc()
+        log(f"Stack trace:\n{stack_trace}")
+        return f"Error in screenshot or getting UI elements: {str(e)}\nStack trace:\n{stack_trace}"
+
+
+def is_low_spec_pc() -> bool:
+    try:
+        import psutil
+
+        cpu_low = psutil.cpu_count(logical=False) < 4
+        ram_low = psutil.virtual_memory().total < 8 * 1024**3
+        return cpu_low or ram_low
+    except Exception:
+        # Fallback if psutil not available or info unavailable
+        return False
+
 
+@mcp.tool()
+def 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,
+) -> str:
+    """
+    Get OCR text from screenshot with absolute coordinates as JSON string of List[Tuple[List[List[int]], str, float]] (returned after adding the window offset from true (0, 0) of screen to the OCR coordinates, so clicking is on-point. Recommended to click in the middle of OCR Box) and using confidence from window with the specified title pattern.
+    If no title pattern is provided, get screenshot of entire screen and all text on the screen.
+    Know that OCR takes around 20 seconds on an mid spec pc at 1080p resolution.
+
+    Args:
+        title_pattern: Pattern to match window title, if None, take screenshot of entire screen
+        use_regex: If True, treat the pattern as a regex, otherwise best match with fuzzy matching
+        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
+
+    Returns:
+        Returns a list of UI elements as List[Tuple[List[List[int]], str, float]] where each tuple is [[4 corners of box], text, confidence], "content type image not supported" means preview isnt supported but Image object is there.
+    """
+    try:
         all_windows = gw.getAllWindows()
 
         # Convert to list of dictionaries for _find_matching_window
@@ -235,23 +421,24 @@ def take_screenshot(
         # Take the screenshot
         if not window:
             log("No matching window found, taking screenshot of entire screen")
-            screenshot = pyautogui.screenshot()
+            screenshot = _mss_screenshot()
         else:
             current_active_window = gw.getActiveWindow()
             log(f"Taking screenshot of window: {window.title}")
             # Activate the window and wait for it to be fully in focus
             try:
-                    
                 window.activate()
                 pyautogui.sleep(0.5)  # Wait for 0.5 seconds to ensure window is active
-                screenshot = pyautogui.screenshot(
+                screenshot = _mss_screenshot(
                     region=(window.left, window.top, window.width, window.height)
                 )
                 # Restore the previously active window
                 if current_active_window:
                     try:
                         current_active_window.activate()
-                        pyautogui.sleep(0.2)  # Wait a bit to ensure previous window is restored
+                        pyautogui.sleep(
+                            0.2
+                        )  # Wait a bit to ensure previous window is restored
                     except Exception as e:
                         log(f"Error restoring previous window: {str(e)}")
             except Exception as e:
@@ -269,9 +456,6 @@ def take_screenshot(
         # Create Image object from filepath
         image = Image(filepath)
 
-        if not with_ocr_text_and_coords:
-            return image  # MCP Image object
-
         # Copy from temp to downloads
         if save_to_downloads:
             log("Copying screenshot from temp to downloads")
@@ -282,7 +466,7 @@ def take_screenshot(
 
         if scale_percent_for_ocr is None:
             # Calculate percent to scale height to 360 pixels
-            scale_percent_for_ocr = 100 # 360 / img.shape[0] * 100
+            scale_percent_for_ocr = 100  # 360 / img.shape[0] * 100
 
         # Lower down resolution before processing
         width = int(img.shape[1] * scale_percent_for_ocr / 100)
@@ -291,20 +475,28 @@ def take_screenshot(
         resized_img = cv2.resize(img, dim, interpolation=cv2.INTER_AREA)
         # save resized image to pwd
         # cv2.imwrite("resized_img.png", resized_img)
-   
+
         output = engine(resized_img)
-        boxes  = output.boxes
-        txts   = output.txts
+        boxes = output.boxes
+        txts = output.txts
         scores = output.scores
         zipped_results = list(zip(boxes, txts, scores))
         zipped_results = [
-            (box.tolist(), text, float(score))  # convert np.array -> list, ensure score is float
+            (
+                box.tolist(),
+                text,
+                float(score),
+            )  # convert np.array -> list, ensure score is float
             for box, text, score in zipped_results
         ]
         log(f"Found {len(zipped_results)} text items in OCR result.")
         log(f"First 5 items: {zipped_results[:5]}")
-        return json.dumps(zipped_results)
-        # ...existing code...
+        return (
+            ",\n".join([str(item) for item in zipped_results])
+            if zipped_results
+            else "No text found"
+        )
+
     except Exception as e:
         log(f"Error in screenshot or getting UI elements: {str(e)}")
         import traceback
@@ -324,6 +516,26 @@ def move_mouse(x: int, y: int) -> str:
         return f"Error moving mouse to coordinates ({x}, {y}): {str(e)}"
 
 
+@mcp.tool()
+def mouse_down(button: str = "left") -> str:
+    """Hold down a mouse button ('left', 'right', 'middle')."""
+    try:
+        pyautogui.mouseDown(button=button)
+        return f"Held down {button} mouse button"
+    except Exception as e:
+        return f"Error holding {button} mouse button: {str(e)}"
+
+
+@mcp.tool()
+def mouse_up(button: str = "left") -> str:
+    """Release a mouse button ('left', 'right', 'middle')."""
+    try:
+        pyautogui.mouseUp(button=button)
+        return f"Released {button} mouse button"
+    except Exception as e:
+        return f"Error releasing {button} mouse button: {str(e)}"
+
+
 @mcp.tool()
 async def drag_mouse(
     from_x: int, from_y: int, to_x: int, to_y: int, duration: float = 0.5
@@ -353,14 +565,69 @@ async def drag_mouse(
         return f"Error dragging from ({from_x}, {from_y}) to ({to_x}, {to_y}): {str(e)}"
 
 
+import pyautogui
+from typing import Union, List
+
+
 @mcp.tool()
-def press_key(key: str) -> str:
-    """Press the specified keyboard key."""
+def key_down(key: str) -> str:
+    """Hold down a specific keyboard key until released."""
     try:
-        pyautogui.press(key)
-        return f"Successfully pressed key: {key}"
+        pyautogui.keyDown(key)
+        return f"Held down key: {key}"
+    except Exception as e:
+        return f"Error holding key {key}: {str(e)}"
+
+
+@mcp.tool()
+def key_up(key: str) -> str:
+    """Release a specific keyboard key."""
+    try:
+        pyautogui.keyUp(key)
+        return f"Released key: {key}"
+    except Exception as e:
+        return f"Error releasing key {key}: {str(e)}"
+
+
+@mcp.tool()
+def press_keys(keys: Union[str, List[Union[str, List[str]]]]) -> str:
+    """
+    Press keyboard keys.
+
+    Args:
+        keys:
+            - Single key as string (e.g., "enter")
+            - Sequence of keys as list (e.g., ["a", "b", "c"])
+            - Key combinations as nested list (e.g., [["ctrl", "c"], ["alt", "tab"]])
+
+    Examples:
+        press_keys("enter")
+        press_keys(["a", "b", "c"])
+        press_keys([["ctrl", "c"], ["alt", "tab"]])
+    """
+    try:
+        if isinstance(keys, str):
+            # Single key
+            pyautogui.press(keys)
+            return f"Pressed single key: {keys}"
+
+        elif isinstance(keys, list):
+            for item in keys:
+                if isinstance(item, str):
+                    # Sequential key press
+                    pyautogui.press(item)
+                elif isinstance(item, list):
+                    # Key combination (e.g., ctrl+c)
+                    pyautogui.hotkey(*item)
+                else:
+                    return f"Invalid key format: {item}"
+            return f"Successfully pressed keys sequence: {keys}"
+
+        else:
+            return "Invalid input: must be str or list"
+
     except Exception as e:
-        return f"Error pressing key {key}: {str(e)}"
+        return f"Error pressing keys {keys}: {str(e)}"
 
 
 @mcp.tool()
@@ -455,6 +722,7 @@ def main():
 
     try:
         # Run the server
+        log("Computer Control MCP Server Started...")
         mcp.run()
 
     except KeyboardInterrupt:

{computer_control_mcp-0.3.0 → computer_control_mcp-0.3.3}/computer_control_mcp/test.py

@@ -13,6 +13,8 @@ import tempfile
 # --- Auto-install dependencies if needed ---
 import pyautogui
 from mcp.server.fastmcp import FastMCP, Image
+import mss
+from PIL import Image as PILImage
 import pygetwindow as gw
 from fuzzywuzzy import fuzz, process
 
@@ -39,6 +41,34 @@ def get_downloads_dir() -> Path:
         return Path.home() / "Downloads"
 
 
+def _mss_screenshot(region=None):
+    """Take a screenshot using mss and return PIL Image.
+    
+    Args:
+        region: Optional tuple (left, top, width, height) for region capture
+        
+    Returns:
+        PIL Image object
+    """
+    with mss.mss() as sct:
+        if region is None:
+            # Full screen screenshot
+            monitor = sct.monitors[0]  # All monitors combined
+        else:
+            # Region screenshot
+            left, top, width, height = region
+            monitor = {
+                "left": left,
+                "top": top,
+                "width": width,
+                "height": height,
+            }
+        
+        screenshot = sct.grab(monitor)
+        # Convert to PIL Image
+        return PILImage.frombytes("RGB", screenshot.size, screenshot.bgra, "raw", "BGRX")
+
+
 def save_image_to_downloads(
     image, prefix: str = "screenshot", directory: Path = None
 ) -> Tuple[str, bytes]:
@@ -171,13 +201,13 @@ def take_screenshot(
         # Take the screenshot
         if not window:
             print("No matching window found, taking screenshot of entire screen")
-            screenshot = pyautogui.screenshot()
+            screenshot = _mss_screenshot()
         else:
             print(f"Taking screenshot of window: {window.title}")
             # Activate the window and wait for it to be fully in focus
             window.activate()
             pyautogui.sleep(0.5)  # Wait for 0.5 seconds to ensure window is active
-            screenshot = pyautogui.screenshot(
+            screenshot = _mss_screenshot(
                 region=(window.left, window.top, window.width, window.height)
             )
             # Restore the previously active window
@@ -252,13 +282,13 @@ def get_ocr_from_screenshot(
         # Take the screenshot
         if not window:
             log("No matching window found, taking screenshot of entire screen")
-            screenshot = pyautogui.screenshot()
+            screenshot = _mss_screenshot()
         else:
             log(f"Taking screenshot of window: {window.title}")
             # Activate the window and wait for it to be fully in focus
             window.activate()
             pyautogui.sleep(0.5)  # Wait for 0.5 seconds to ensure window is active
-            screenshot = pyautogui.screenshot(
+            screenshot = _mss_screenshot(
                 region=(window.left, window.top, window.width, window.height)
             )
             # Restore the previously active window

{computer_control_mcp-0.3.0 → computer_control_mcp-0.3.3}/pyproject.toml

@@ -1,48 +1,50 @@
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
-
-[project]
-name = "computer-control-mcp"
-version = "0.3.0"
-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 = ">=3.10"
-license = {text = "MIT"}
-authors = [{name = "AB498", email = "abcd49800@gmail.com"}]
-classifiers = [
-    "Development Status :: 4 - Beta",
-    "Intended Audience :: Developers",
-    "License :: OSI Approved :: MIT License",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.12",
-    "Topic :: Software Development :: Libraries",
-    "Topic :: Utilities"
-]
-dependencies = [
-    "pyautogui==0.9.54",
-    "mcp[cli]==1.13.0",
-    "pillow==11.3.0",
-    "pygetwindow==0.0.9",
-    "fuzzywuzzy==0.18.0",
-    "rapidocr==3.3.1",
-    "onnxruntime==1.22.1",
-    "rapidocr_onnxruntime==1.4.4",
-    "opencv-python==4.12.0.88"
-]
-
-[project.urls]
-Homepage = "https://github.com/AB498/computer-control-mcp"
-Issues = "https://github.com/AB498/computer-control-mcp/issues"
-Documentation = "https://github.com/AB498/computer-control-mcp#readme"
-
-[project.scripts]
-computer-control-mcp = "computer_control_mcp.cli:main"
-computer-control-mcp-server = "computer_control_mcp.server:main"
-
-[tool.hatch.build]
-sources = ["src"]
-packages = ["src/computer_control_mcp"]
-
-[tool.hatch.build.targets.wheel]
-packages = ["src/computer_control_mcp"]
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "computer-control-mcp"
+version = "0.3.3"
+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 = ">=3.10"
+license = {text = "MIT"}
+authors = [{name = "AB498", email = "abcd49800@gmail.com"}]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Libraries",
+    "Topic :: Utilities"
+]
+dependencies = [
+    "pyautogui==0.9.54",
+    "mcp[cli]==1.13.0",
+    "pillow==11.3.0",
+    "pygetwindow==0.0.9",
+    "pywinctl==0.4.1",
+    "fuzzywuzzy==0.18.0",
+    "rapidocr==3.3.1",
+    "onnxruntime==1.22.0",
+    "rapidocr_onnxruntime==1.2.3",
+    "opencv-python==4.12.0.88",
+    "mss>=7.0.0"
+]
+
+[project.urls]
+Homepage = "https://github.com/AB498/computer-control-mcp"
+Issues = "https://github.com/AB498/computer-control-mcp/issues"
+Documentation = "https://github.com/AB498/computer-control-mcp#readme"
+
+[project.scripts]
+computer-control-mcp = "computer_control_mcp.cli:main"
+computer-control-mcp-server = "computer_control_mcp.server:main"
+
+[tool.hatch.build]
+sources = ["src"]
+packages = ["src/computer_control_mcp"]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/computer_control_mcp"]