Kinetic equations play a major role in modeling large systems of interacting parti cles/agents with a proven effectiveness in describing real world phenomena ranging from plasma physics to biological dynamics. Their formulation has often to face with physical forces deduced through experimental data of which we have at most statistical information. To that aim, we consider in this talk the presence of random inputs in the form of uncertain parameters as a structural feature of the kinetic modeling. More in detail, we deal with uncertainty quantification for the Vlasov-Fokker-Planck equations and we discuss a numerical method employing a micro-macro approach based on stochastic Galerkin methods which preserves the large time equilibrium distribution of the system. The theoretical properties of the scheme as well as numerical experiments will be discussed during the talk.