"author:maxritter0714-sketch" matching MCP servers:

Enables AI clients to list configured cameras, fetch current JPEG frames from video files, webcams, or RTSP/HTTP streams, run local YOLO object detection, and count objects inside named polygonal zones using normalized coordinates. Answers come back as compact JSON with timestamps and image age, so a model can respond to questions like "Is anyone there?" or "How many cars are parked?" while only requesting the actual image when needed.