In accordance with an embodiment, described herein is a system and method for enabling use of a media content bot in a social messaging environment that supports group chat. A conversational agent, generally referred to as a “bot”, can leverage a user's interaction with the bot, to access a media server, which in turn can determine one or more items of media content appropriate for the user and/or their interaction. During a group chat, the bot can recognize music commands within the context of a particular discussion, and/or utilize music recommendation services provided by a digital media content environment, to determine items of media content appropriate for the group of users and/or their interaction. The system enables the use of media playback controls within the group chat, enabling the group of users to determine how and which media content is to be played.