While the mobile networks are evolving to a content-centric paradigm, the surging traffic demands keep stressing the ever-increasing network capacities. In-network caching and particularly edge caching offer an effective means to alleviate the traffic pressure by saving bandwidth resources and balancing traffic loads. In this paper, we consider an integrated content distribution model with universal in-network caching in an end-to-end scope. Based on this model, we formulate two key problems to enable collaborative content distribution across domains, i.e., a request screening problem at the mobile edge and a request routing problem at the integrated edge-core. We propose effective solutions for the two problems, which include a joint device caching and matching algorithm for request screening, and a joint source selection and flow routing algorithm for request routing. The simulation results demonstrate that the proposed solutions achieve significant performance gain over traditional approaches in relieving network congestion by exploiting network dynamics and user contexts. INDEX TERMS Mobile edge computing, content distribution, context-aware, in-network caching, network congestion.