This paper proposes a stochastic scheduling approach for AC/DC hybrid distribution system considering the output uncertainty of wind and photovoltaic. The energy coordination problem has been formulated as a two-stage resource scheduling problem. The first-stage decision produces an hourly day-ahead pre-scheduling plan for the dispatchable distributed generators. For a set of possible scenarios over the next 24 h, the second stage determines the appropriate corrective decisions to handle the output uncertainty. Besides, the scheduling model for AC/DC hybrid system belongs to the non-convex optimization problem, which is transformed into a mixed integer second-order cone programming problem by second-order cone relaxation and linearization techniques. In this way, the optimization problem can be solved effectively. The proposed model has been tested on a modified IEEE 33 bus AC/DC hybrid system. Simulation results demonstrate that the proposed two-stage stochastic scheduling model can better cope with the renewable energy uncertainty and the active and reactive power coordination scheduling can ensure the safe operation of the entire system.