Urban health in Morocco is increasingly threatened by climate variability, with rising heatwaves, Saharan dust, and pollution events intensifying disease burdens in rapidly growing cities. However, existing health surveillance systems remain largely reactive, fragmented, and limited to coarse regional indicators, lacking the spatial and temporal resolution necessary for effective early warning and climate adaptation. This gap leaves vulnerable populations without timely protection against climate-sensitive health risks. We present a climate-adaptive health surveillance framework that integrates Artificial Intelligence (AI) and Internet of Things (IoT) technologies to generate actionable, real-time insights for Moroccan smart cities. Using multimodal data sources, including Google Trends health-seeking behaviors, meteorological and air quality monitoring, and urban mobility data, our machine learning models achieved strong predictive performance (R2 0.82–0.97) for respiratory, allergy, air-quality, and heat-related health outcomes. Validation revealed Mediterranean-relevant seasonal patterns and regional disparities, highlighting both urban–coastal gradients and socio-digital inequities. These findings demonstrate how digital health intelligence can bridge critical surveillance gaps, strengthen climate-health resilience, and provide a scalable model for Moroccan and North African smart cities.