Classifying brain tumors stands as a critical endeavor in the realm of medical imaging, with the primary goal of precisely distinguishing and categorizing brain abnormalities evident in MRI scans. In this pursuit, supervised machine learning methods, particularly Convolutional Neural Networks (CNNs), have come to the forefront, showcasing their effectiveness. Brain tumors are characterized by irregular cell growth within the brain, carrying substantial health risks and the potential for both benign (non-cancerous) and malignant (cancerous) forms. They may either originate within the brain (referred to as primary tumors) or spread from other bodily regions (metastatic tumors). The timely and accurate diagnosis of these tumors is paramount for patient well-being, and the pivotal role played by medical imaging modalities, like MRI, cannot be overstated in their identification and classification. This study places a specific emphasis on leveraging a CNN-based model to categorize an extensive dataset of brain MRI images into discrete classes, encompassing designations such as ‘no tumor’ and ‘pituitary tumor.’ Notably, the resulting CNN classifier exhibits impressive levels of precision and sensitivity, rendering it a potent instrument for the automation of brain tumor classification. In the end, this study makes a substantial contribution to the field of medical diagnostics and has the potential to improve the precision and efficacy of MRI scans used to identify brain tumors.