computer-control-mcp 0.3.3__tar.gz → 0.3.4__tar.gz

{computer_control_mcp-0.3.3 → computer_control_mcp-0.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: computer-control-mcp
-Version: 0.3.3
+Version: 0.3.4
 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
@@ -88,13 +88,19 @@ computer-control-mcp # instead of uvx computer-control-mcp, so you can use the l
 - `click_screen(x: int, y: int)`: Click at specified screen coordinates
 - `move_mouse(x: int, y: int)`: Move mouse cursor to specified coordinates
 - `drag_mouse(from_x: int, from_y: int, to_x: int, to_y: int, duration: float = 0.5)`: Drag mouse from one position to another
+- `mouse_down(button: str = "left")`: Hold down a mouse button ('left', 'right', 'middle')
+- `mouse_up(button: str = "left")`: Release a mouse button ('left', 'right', 'middle')
 
 ### Keyboard Control
 - `type_text(text: str)`: Type the specified text at current cursor position
 - `press_key(key: str)`: Press a specified keyboard key
+- `key_down(key: str)`: Hold down a specific keyboard key until released
+- `key_up(key: str)`: Release a specific keyboard key
+- `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, with_ocr_text_and_coords: bool = False, scale_percent_for_ocr: int = 100, save_to_downloads: bool = False)`: Capture screen or window with optional OCR
+- `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_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
 - `activate_window(title_pattern: str, use_regex: bool = False, threshold: int = 60)`: Bring specified window to foreground
@@ -113,6 +119,21 @@ pip install -e .
 
 # Start server
 python -m computer_control_mcp.core
+
+# -- OR --
+
+# Build
+hatch build
+
+# Non-windows
+pip install dist/*.whl --upgrade
+
+# Windows
+$latest = Get-ChildItem .\dist\*.whl | Sort-Object LastWriteTime -Descending | Select-Object -First 1
+pip install $latest.FullName --upgrade 
+
+# Run
+computer-control-mcp
 ```
 
 ### Running Tests

{computer_control_mcp-0.3.3 → computer_control_mcp-0.3.4}/README.md

@@ -57,13 +57,19 @@ computer-control-mcp # instead of uvx computer-control-mcp, so you can use the l
 - `click_screen(x: int, y: int)`: Click at specified screen coordinates
 - `move_mouse(x: int, y: int)`: Move mouse cursor to specified coordinates
 - `drag_mouse(from_x: int, from_y: int, to_x: int, to_y: int, duration: float = 0.5)`: Drag mouse from one position to another
+- `mouse_down(button: str = "left")`: Hold down a mouse button ('left', 'right', 'middle')
+- `mouse_up(button: str = "left")`: Release a mouse button ('left', 'right', 'middle')
 
 ### Keyboard Control
 - `type_text(text: str)`: Type the specified text at current cursor position
 - `press_key(key: str)`: Press a specified keyboard key
+- `key_down(key: str)`: Hold down a specific keyboard key until released
+- `key_up(key: str)`: Release a specific keyboard key
+- `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, with_ocr_text_and_coords: bool = False, scale_percent_for_ocr: int = 100, save_to_downloads: bool = False)`: Capture screen or window with optional OCR
+- `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_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
 - `activate_window(title_pattern: str, use_regex: bool = False, threshold: int = 60)`: Bring specified window to foreground
@@ -82,6 +88,21 @@ pip install -e .
 
 # Start server
 python -m computer_control_mcp.core
+
+# -- OR --
+
+# Build
+hatch build
+
+# Non-windows
+pip install dist/*.whl --upgrade
+
+# Windows
+$latest = Get-ChildItem .\dist\*.whl | Sort-Object LastWriteTime -Descending | Select-Object -First 1
+pip install $latest.FullName --upgrade 
+
+# Run
+computer-control-mcp
 ```
 
 ### Running Tests

{computer_control_mcp-0.3.3 → computer_control_mcp-0.3.4}/computer_control_mcp/core.py

@@ -242,8 +242,7 @@ def take_screenshot(
     save_to_downloads: 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.
+    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
@@ -384,9 +383,7 @@ def take_screenshot_with_ocr(
     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.
+    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

{computer_control_mcp-0.3.3 → computer_control_mcp-0.3.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "computer-control-mcp"
-version = "0.3.3"
+version = "0.3.4"
 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"