The combination of edge and cloud in the fog computing paradigm enables a new breed of data-intensive applications. These applications, however, have to face a number of fog-specific challenges which developers have to repetitively address for every single application. In this paper, we derive a set of requirements for a replication service that aims to simplify the development of data-intensive fog applications which are caused by the highly distributed and heterogeneous operation environment. Furthermore, we propose the design for such a service which addresses our requirements.