In an age of data overload and scenarios that require fast-distributed situational understanding, we envision that content summarization services will become a critical capability of underlying networked systems. Previous work, called InfoMax, proposed such a service in the transport layer to minimize semantic redundancy of transmitted content and maximize information coverage. Here, we extended this work in three ways. First, we adapted summarization to the needs of streaming content and developed a corresponding publish-subscribe protocol (called Pub/Sub-Sum) with on-the-fly extractive summarization of continuous content streams (as opposed to extractive summarization of fixed data sets). Next, we supported many-to-many communication between publishers and subscribers, as opposed to InfoMax, which was designed to disseminate data from one producer to multiple consumers. Lastly, we introduce a new type of congestion handling mechanism that adaptively controls the level of summarization by considering available network bandwidth. We conducted experiments for functionality and performance on Mininet (a network emulator) and on a real device testbed. Evaluation results indicated that the new protocol summarizes data appropriately to available network resources, offering an improved compromise between received data quality and resource consumption.