The various implementations described herein include methods and systems for displaying a summary of media content items. In one aspect, a method is performed at a server system that includes processors and memory storing programs for execution by the processors. The server system: (1) detects presentation of a media content item at a first device in proximity to a second device, including receiving from the second device content identification information; (2) identifies the media content item; (3) identifies entities related to the identified media content item; (4) determines a level of interest with respect to a user of the second device, for each of the identified entities; (5) selects a subset of the identified plurality of entities based on the determined level of interest; and (6) sends to the second device, a summary of the media content item, for presenting at the second device.