Agriculture is the foundation of socio-economic development and is highly influenced by weather and climate conditions.  Drought is one of the most significant threats to agricultural development and food security.  Currently, in-situ drought monitoring based on weather stations and based on remote sensing data has limitations, including infrequent updates, limited coverage, and low accuracy.  This study leverages multi-source remote sensing data to monitor agricultural drought in Heilongjiang Province, China.  We developed multi-source composite drought indices (MCDIs) at various timescales (3, 6, 9, and 12 months) by integrating precipitation, land surface temperature, soil moisture, and vegetation indices.  Utilizing remote sensing data from various sources, we calculated a series of single drought indices, which are the precipitation condition index, soil moisture condition index, vegetation condition index, and temperature condition index.  These are then integrated into MCDIs using a multivariable linear regression approach.  The analysis reveals that MCDIs correlate more with standardized precipitation evapotranspiration index (SPEI) than single drought indices.  When examining the correlation between different MCDIs and the affected area of crops and major grain production, MCDI-9 showed the highest correlation with the affected area of crops, while MCDI-12 showed the highest correlation with grain production.  This suggests that these two MCDIs at different timescales are better indicators of agricultural drought.  The spatio-temporal analysis of MCDI indicates that drought in Heilongjiang Province primarily occurs in early spring, gradually spreading from the Greater Khingan Mountains region to the southeastern plains.  The drought gradually alleviates during the summer, ending by the autumn harvest period.  Therefore, the MCDIs constructed in this study can serve as effective methods and indicators for drought monitoring in Heilongjiang Province and similar regions.