Urinary exosome metabolite analysis has demonstrated notable advantages in uncovering disease status, yet its potential in decoding the intricacies of clear cell renal cell carcinoma (ccRCC) remains untapped. To address this, a core-shell magnetic titanium organic framework was designed to capture urinary exosomes and assist laser desorption/ionization mass spectrometry (LDI MS) to decipher the exosomal metabolic profile of ccRCC, with high sensitivity, throughput, and speed. A total of 492 urinary exosome metabolite fingerprints (UEMFs) from 176 samples were extracted for exploring the differences between ccRCC and healthy individuals. Leveraging machine learning algorithms, the exosomal metabolic profile was disclosed, achieving accurate differentiation and prediction of ccRCC patients versus healthy individuals, with an accuracy exceeding 97.3%. Furthermore, an optimized algorithm panel comprising five key features demonstrated consistent and high diagnosing accuracy rates of over 94.0% both in the training and blind test sets for ccRCC, underscoring the remarkable effectiveness and superiority of this strategy in ccRCC detection. This study not only refines the LDI MS method for metabolite analysis in urinary exosomes but also introduces a promising technical approach for unraveling the mysteries of ccRCC.