The collection, processing, and analysis of data generated by varied sources can help us better understand the functioning and demands of the cities. However, developing efficient solutions to explore urban data is challenging due to the large volume, heterogeneity, and lack of accessibility and integration of this kind of data. In this work, we identify the main requirements of a data integration system to support decision-making in cities, focusing on its challenges. We analyze some existing data integration solutions, to uncover their features and limitations. Based on these results, we propose a new microservice architecture to support the development of software platforms for integrating smart cities’ heterogeneous data and a guideline to assess their performance. We also present details of a proof-of-concept implementation of the proposed architecture and its performance evaluation. The results demonstrate that the platform can scale horizontally to handle the highly dynamic demands of a smart city while maintaining low response times.