Rational design of entry inhibitors is an active area for the discovery of new and effective anti-HIV agents. C-C Chemokine receptors represent key targets for the HIV entry process. Several of these proteins with features to be HIV co-receptors have not been sufficiently studied or used for the design of novel entry inhibitors. With the purpose to overcome this problem, we develop here a fragment-based approach for the design of multi-target inhibitors against four C-C chemokine receptors. This approach was focused on the construction of a multi-target QSAR discriminant model using a large and heterogeneous database of compounds and substructural descriptors for the classification and prediction of inhibitors for C-C chemokine receptors. The model correctly classified more than 89% of active and inactive compounds in both: training and prediction series. As principal advantage, this model permitted the automatic and fast extraction of fragments responsible for the inhibitory activity against the different C-C chemokine receptors under study and new molecular entities were suggested as possible versatile inhibitors for these proteins.