Quantitative structure-activity relationship of nineteen matrix metalloproteinase inhibitors based on topological descriptors has been studied. For QSAR prediction, the 3D structures of the inhibitors have been drawn and their geometries have been optimized with the help of CAChe software by using PM3 hamiltonian. In developing QSAR models, topological descriptors used as independent variables and the observed biological activity in term of IC50 values as dependent variable. The Project Leader program associated with CAChe Pro of Fujitsu has been used for multiple linear regressions (MLR) analysis and ninety equations were developed. The study concluded that topological descriptors, connectivity index of first order in combination with valence connectivity index of zero order and kappa shape index of third order provide reliable QSAR model of rCV^2 (0.988954) and r^2 (0.996732). The model can be used to access the biological activity of the compounds of the same series.