There is provided a medical image processing apparatus including: an association processing section configured to associate multiple medical captured images in which an observation target is imaged by each of multiple imaging devices including imaging devices in which one or both of an in-focus position and an in-focus range are different; and a compositing processing section configured to depth-composite each of a medical captured image for a right eye and a medical captured image for a left eye among the multiple medical captured images by using an associated other medical captured image.