Layout Detector MCP

Instructions

Implementation Reference

• src/layout_detector/server.py:159-176 (handler)

  The handler logic for the 'get_screenshot_info' tool within the call_tool function. It validates the screenshot path, calls the helper to get dimensions, formats the result as JSON, and returns it as TextContent.
  elif name == "get_screenshot_info": screenshot_path = arguments["screenshot_path"] if not Path(screenshot_path).exists(): return [TextContent( type="text", text=json.dumps({"error": f"Screenshot not found: {screenshot_path}"}) )] width, height = get_screenshot_dimensions(screenshot_path) result = { "path": screenshot_path, "width": width, "height": height, } return [TextContent(type="text", text=json.dumps(result, indent=2))]
• src/layout_detector/server.py:81-97 (schema)

  The tool schema definition including name, description, and inputSchema for 'get_screenshot_info', provided in the list_tools handler.
  Tool( name="get_screenshot_info", description=( "Get basic information about a screenshot image, including its " "dimensions (width and height in pixels)." ), inputSchema={ "type": "object", "properties": { "screenshot_path": { "type": "string", "description": "Absolute path to the screenshot image file", }, }, "required": ["screenshot_path"], }, ),
• src/layout_detector/server.py:22-98 (registration)

  Registration of the 'get_screenshot_info' tool (among others) in the @server.list_tools() handler, returning a list of Tool objects.
  return [ Tool( name="find_assets_in_screenshot", description=( "Find known image assets within a screenshot. Uses template matching " "to locate each asset and return its position (x, y, width, height). " "Useful for determining where specific images appear in a webpage screenshot." ), inputSchema={ "type": "object", "properties": { "screenshot_path": { "type": "string", "description": "Absolute path to the screenshot image file", }, "asset_paths": { "type": "array", "items": {"type": "string"}, "description": "List of absolute paths to asset images to find", }, "threshold": { "type": "number", "description": "Match confidence threshold (0-1). Default 0.8", "default": 0.8, }, }, "required": ["screenshot_path", "asset_paths"], }, ), Tool( name="analyze_layout", description=( "Analyze the layout of assets in a screenshot. Finds all assets, " "identifies the center/hero element, calculates relative positions " "(angle and distance from center), and detects the layout pattern " "(radial, grid, or freeform). Returns structured data for rebuilding " "the layout with semantic CSS." ), inputSchema={ "type": "object", "properties": { "screenshot_path": { "type": "string", "description": "Absolute path to the screenshot image file", }, "asset_paths": { "type": "array", "items": {"type": "string"}, "description": "List of absolute paths to asset images to find", }, "threshold": { "type": "number", "description": "Match confidence threshold (0-1). Default 0.8", "default": 0.8, }, }, "required": ["screenshot_path", "asset_paths"], }, ), Tool( name="get_screenshot_info", description=( "Get basic information about a screenshot image, including its " "dimensions (width and height in pixels)." ), inputSchema={ "type": "object", "properties": { "screenshot_path": { "type": "string", "description": "Absolute path to the screenshot image file", }, }, "required": ["screenshot_path"], }, ), ]
• src/layout_detector/template_match.py:123-127 (helper)

  Core helper function that implements the screenshot dimension extraction by loading the image with load_image and reading its shape.
  def get_screenshot_dimensions(screenshot_path: str) -> tuple[int, int]: """Get the dimensions of a screenshot.""" img = load_image(screenshot_path) h, w = img.shape[:2] return (w, h)