Introduction: Tuberculosis (TB) is a leading cause of death due to a single infectious agent. The disease is treatable by a minimum of six months of anti-TB drugs. However, prolonged duration of treatment using directly observed therapy (DOT) causes significant inconvenience to patients and is ineffective in improving treatment outcomes. Therefore, incorporating the Health Belief Model into the development of digital technology could help change behaviour and improve adherence. This study aimed to determine the effectiveness of mobile applications in improving TB medication adherence. Methods: This study proposed to conduct a randomized trial among TB patients in the Kota Kinabalu, Penampang, and Putatan districts of Sabah, Malaysia. The eligible sample will be randomly assigned to the mobile application DOT arm and standard DOT arm. The primary outcome is the adherence level calculated by the percentage of medication observed divided by the intended dose taken in two months, with 80% and more successfully observed treatment considered highly adherent. The secondary outcomes are health-related quality of life, satisfaction, and monthly household income. Multiple logistic regression and repeated measures ANCOVA will be used to determine the effectiveness of interventions to achieve primary and secondary outcomes. Discussion: The findings from this study could hopefully provide insight into rethinking TB care delivery to achieve better TB treatment outcomes. Trial Registration: This study protocol has been approved by the Medical Research Ethics Committee (MREC), Ministry of Health Malaysia (NMRR ID-21-01949-73X) and registered with ClinicalTrials. gov (NCT05259254).