In recent years, mental health issues have become a significant concern worldwide. To address this, personalized mental health assistance has emerged as a promising approach, leveraging technology to provide tailored support to individuals. This paper presents a study on the development of a personalized mental health assistant using supervised ML algorithms. The main and foremost idea was to build a suitable of predicting mental health conditions based on user input, facilitating early intervention and support. The dataset used in this study was collected through surveys administered to individuals, encompassing a diverse range of demographic and psychological factors. Various supervised ML algorithms were supported, which includes Logistic Regression, Gaussian Naive Bayes, Random Forest, Decision Tree, Support Vector Machine (SVM), and K-Nearest Neighbors (KNNs). These algorithms were trained and tested on the dataset to evaluate their effectiveness in predicting mental health conditions. This research signifies a significant step forward in the realm of personalized mental health assistance, highlighting the feasibility of integrating ML algorithms into support systems. The implications extend beyond predictive accuracy, emphasizing the importance of tailored interventions in enhancing mental well-being. The PMHA holds promise for individuals seeking accessible and individualized mental health support, marking a pivotal advancement in the field.