This dataset provides 20-year tree cover (TC) estimates at 30-m spatial resolution for Mexico from 2000 to 2019 using Landsat time series, airborne LiDAR, and machine learning. The TC data (hereafter, CMS-TC) offers accurate and consistent national-scale percent tree cover estimates with an overall coefficient of determination (R squared) of 0.81 and a root mean square error (RMSE) of 11.90%. The CMS-TC product is essential for tracking tree cover and aboveground biomass changes, monitoring land use dynamics, supporting biodiversity conservation, and informing climate and land use policy decisions. The data are provided in GeoTIFF format.