The detection of brain tumors using Magnetic Resonance Images(MRI) is difficult for contemporary medical imaging research. Basically, a brain tumor is an expansion of aberrant brain cells that expand erratically and seemingly uncontrolled. Meningioma, Glioma, and Pituitary are the three kinds of tumors that are most frequently seen. Early identification is essential for the successful treatment of brain tumors. With the development of medical imaging, doctors now employ a variety of imaging methods, such as fMRI, EEG, etc., to diagnose brain tumors. These imaging methods can help clinicians establish a precise diagnosis and create a treatment strategy by providing details on the location, size, and shape of brain tumors. Feature extraction and classification are two steps in the categorization of brain tumors. Two traditional manual feature extraction methods were frequently utilized in certain earlier research to extract details like the intensity and texture of images of brain tumors. This work employs the 'GLCM(Grey Level Co-occurrence Matrix)' approach for feature extraction. The generated feature set is provided to machine learning(ML) algorithms, including 'K-Nearest Neighbours(KNN), Support Vector Machine(SVM), Decision Tree(DT), Naive Bayes(NB), Logistic Regression(LR), Naive Bayes(NB), and Random Forest(RF)'. According to experimental results, random forest yields a maximum accuracy of 91.04%. The proposed methodology helps to classify the different brain tumor classes like glioma, meningioma, pituitary, or else no tumor.