Student mental health is a crucial aspect of supporting academic success and individual well-being. Various academic and social pressures, along with the transition to independent living, make university students a group vulnerable to mental health disorders such as stress, anxiety, and depression. However, many students remain reluctant or find it difficult to access professional services due to limited information, lack of social support, and low mental health literacy.This research aims to design and implement an early detection system for student mental health based on an expert system using the Forward Chaining algorithm. The Forward Chaining method is employed to perform reasoning from symptoms selected by the user toward a conclusion regarding their mental health condition, based on rules stored in the knowledge base. The system was developed using the DASS 21 (Depression, Anxiety, Stress Scale - 21) instrument to assist in mental health diagnosis.The system was built through several stages, including literature review, data collection, requirements analysis, system design, implementation, and testing. The results indicate that the system is capable of identifying the initial mental health conditions of students by displaying the level of the mental condition, a description of the condition, and appropriate treatment recommendations. Testing using black-box and white-box methods shows that all system functions and logic operate according to the design without any functional or logical errors. Thus, this system can serve as a tool for the early detection of student mental health to support prevention efforts and increase awareness of the importance of mental health in higher education environments.