This paper introduces modular and context-aware evaporative cooling for the outdoor urban environment as a physical structure that could be implemented at various scales and physical contexts. We propose a technique for collecting occupancy and climatic data to create a computational context and optimise its operation. We then outline a concept for developing a predictive algorithm that would further enhance its performance. The research focuses on the interaction between the proposed system and the environment and establishes an evidence-based technique to balance the temperature drop and the humidity it generates. The study combines architectural design, mechanical engineering and computer science to enable the upscaled application of evaporative cooling to help reduce local heat accumulation in cities.