computer-control-mcp 0.2.0__tar.gz → 0.2.1__tar.gz

{computer_control_mcp-0.2.0 → computer_control_mcp-0.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: computer-control-mcp
-Version: 0.2.0
+Version: 0.2.1
 Summary: Computer control capabilities using PyAutoGUI through a Model Context Protocol (MCP) server
 Project-URL: Homepage, https://github.com/AB498/computer-control-mcp
 Project-URL: Issues, https://github.com/AB498/computer-control-mcp/issues
@@ -27,7 +27,7 @@ Description-Content-Type: text/markdown
 
 # Computer Control MCP
 
-A Python package that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI through a Model Context Protocol (MCP) server. With Zero External Dependencies.
+MCP server that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI, RapidOCR, ONNXRuntime. With Zero External Dependencies.
 
 ## Quick Usage (MCP Setup Using `uvx`)
 

{computer_control_mcp-0.2.0 → computer_control_mcp-0.2.1}/README.md

@@ -1,6 +1,6 @@
 # Computer Control MCP
 
-A Python package that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI through a Model Context Protocol (MCP) server. With Zero External Dependencies.
+MCP server that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI, RapidOCR, ONNXRuntime. With Zero External Dependencies.
 
 ## Quick Usage (MCP Setup Using `uvx`)
 

{computer_control_mcp-0.2.0 → computer_control_mcp-0.2.1}/computer_control_mcp/core.py

@@ -149,7 +149,7 @@ def _find_matching_window(
 @mcp.tool()
 def tool_version() -> str:
     """Get the version of the tool."""
-    return "0.2.0"
+    return "0.2.1"
 
 
 @mcp.tool()
@@ -268,24 +268,24 @@ def take_screenshot(
 
 
 @mcp.tool()
-def get_screenshot_with_ocr(
+def get_ocr_from_screenshot(
     title_pattern: str = None,
     use_regex: bool = False,
     threshold: int = 60,
     scale_percent: int = 100,
-) -> any:
+) -> List[Tuple[List[List[int]], str, float]]:
     """
-    Get OCR text from the specified title pattern and save them to the downloads directory with absolute paths returned.
-    If no title pattern is provided, get all Text on the screen.
+    Get 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.
+    If no title pattern is provided, get all text on the screen.
 
     Args:
         title_pattern: Pattern to match window title, if None, get all UI elements on the screen
         use_regex: If True, treat the pattern as a regex, otherwise best match with fuzzy matching
-        save_to_downloads: If True, save the screenshot to the downloads directory and return the absolute path
         threshold: Minimum score (0-100) required for a fuzzy match
+        scale_percent: Percentage to scale the image down before processing, you wont need this most of the time unless your pc is extremely old or slow
 
     Returns:
-        List of UI elements as MCP Image objects
+        List of UI elements as [[4 corners of box], text, confidence]
     """
     try:
 
@@ -357,10 +357,10 @@ def get_screenshot_with_ocr(
 
         result, elapse_list = engine(resized_img)
         boxes, txts, scores = list(zip(*result))
-
+        boxes = [[[x + window.left, y + window.top] for x, y in box] for box in boxes]
         zipped_results = list(zip(boxes, txts, scores))
-        
-        return [image, *zipped_results]
+
+        return zipped_results
 
     except Exception as e:
         log(f"Error getting UI elements: {str(e)}")

{computer_control_mcp-0.2.0 → computer_control_mcp-0.2.1}/computer_control_mcp/test.py

@@ -208,7 +208,7 @@ def take_screenshot(
         return f"Error taking screenshot: {str(e)}"
 
 
-def get_screenshot_with_ocr(
+def get_ocr_from_screenshot(
     title_pattern: str = None,
     use_regex: bool = False,
     threshold: int = 60,
@@ -297,10 +297,10 @@ def get_screenshot_with_ocr(
 
         result, elapse_list = engine(resized_img)
         boxes, txts, scores = list(zip(*result))
-
+        boxes = [[[x + window.left, y + window.top] for x, y in box] for box in boxes]
         zipped_results = list(zip(boxes, txts, scores))
-        import json
-        return json.dumps([*zipped_results])
+
+        return zipped_results
 
     except Exception as e:
         log(f"Error getting UI elements: {str(e)}")
@@ -310,4 +310,7 @@ def get_screenshot_with_ocr(
         log(f"Stack trace:\n{stack_trace}")
         return f"Error getting UI elements: {str(e)}\nStack trace:\n{stack_trace}"
 
-print(get_screenshot_with_ocr("chrome"))
+
+import json
+
+print(json.dumps(get_ocr_from_screenshot("chrome")))

{computer_control_mcp-0.2.0 → computer_control_mcp-0.2.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "computer-control-mcp"
-version = "0.2.0"
+version = "0.2.1"
 description = "Computer control capabilities using PyAutoGUI through a Model Context Protocol (MCP) server"
 readme = "README.md"
 requires-python = ">=3.12"