VideoCapture MCP provides AI assistants with access to webcams and video sources through OpenCV, enabling image capture and camera control capabilities. The server exposes tools for capturing still images, managing camera connections, adjusting video properties like brightness and resolution, and performing basic image transformations such as horizontal flipping. Developed by 13rac1, this implementation focuses on still image capture only (no video streaming) and is designed to integrate seamlessly with Claude Desktop, making it ideal for AI applications that need to analyze real-world objects or environments through webcam imagery.
Aucun avis encore. Soyez le premier à donner votre avis !
Connectez-vous pour rejoindre la conversation
Quickly open a camera, capture a single frame, and close it. Parameters: device_index (int, default 0), flip (bool, default False). Returns the captured frame as an Image object.
Open a connection to a camera device. Parameters: device_index (int, default 0), name (optional string). Returns the connection ID for the opened camera.
Capture a single frame from the specified video source. Parameters: connection_id (string), flip (bool, default False). Returns the captured frame as an Image object.
Get properties of the video source. Parameters: connection_id (string). Returns a dictionary of video properties (width, height, fps, etc.).
Set a property of the video source. Parameters: connection_id (string), property_name (string), value (float). Returns True if successful, False otherwise.
Close a video connection and release resources. Parameters: connection_id (string). Returns True if successful.
List all active video connections. Returns a list of active connection IDs.
