In service networks, the location of servers and allocation of demand nodes to them have a strong impact on the congestion at each server. The previous efforts in this area have concentrated on enhancing the reliability and quality of service with a probabilistic and fuzzy orientation. This paper considers the uncertain nature of such services and utilizes uncertainty theory to develop an uncertain queuing maximal covering location-allocation model. Our model considers one type of service call, one type of server and includes one constraint on the quality of queue length. To solve the proposed model, we design a hybrid intelligent algorithm which integrates 99-method and differential evolution algorithm. Finally, a numerical example is performed to show the application of the model and the algorithm.