This paper presents the development and implementation of a novel approach for Solar Energy Potential Mapping, integrating the Segment Anything Model (SAM) for accurate rooftop segmentation with real-time meteorological data from the Solar Anywhere API. The system effectively identifies suitable areas for solar panel installation by leveraging SAM's advanced image segmentation capabilities to detect rooftops, and other surfaces from high-resolution satellite images. Real-time solar irradiance data is then utilized to calculate the energy generation potential for each identified area. The proposed solution is implemented as a user-friendly web application, delivering precise solar potential assessments and visualizations in the form of interactive charts. This paper discusses the methodology, implementation, and results of the working system, demonstrating its effectiveness in optimizing solar energy potential mapping. The findings highlight the advantages of combining advanced machine learning models with real-time data to provide accurate and actionable insights for solar energy deployment, contributing to sustainable energy planning and decision-making. Keywords: - Solar Energy, Rooftop Segmentation, Segment Anything Model (SAM), Solar Anywhere API, Real-Time Meteorological Data, Image Segmentation, Solar Potential Mapping, Machine Learning, Satellite Imagery, Renewable Energy, Urban Solar Assessment, Energy Generation Potential, Web Application, Interactive Visualization.