Kuding tea, which is a widely consumed tea in China and other southeastern Asian countries made from the leaves of Ilex kudingcha C.J. Tseng, possesses numerous beneficial effects on human health. Several studies have demonstrated that triterpenoid saponins are the main bioactive components of Kuding tea, which can be used in the treatment of various metabolic disorders. The present study deals with the development of a predict-filter strategy combined with the ultra-high-performance liquid chromatography coupled with tandem quadrupole/time-of-flight mass spectrometry for the rapid characterization of saponins in Kuding tea extract. Structural elucidation of all triterpenoid saponins was performed by using an in-house spectral library based on existing literature. A total of 80 compounds in Kuding tea were found to be saponins with high probability, of which 9 seems to be novel. Furthermore, the proportion of different saponins classified by the type of aglycones and monosaccharides on the glycosidic chain were evaluated. Overall results showed that the our predict-filter strategy can be used to filter saponins as well as other compounds possessing similar structures.