In this paper, a direct adaptive fuzzy tracking con-trol scheme is presented for a class of stochastic un-certain nonlinear systems with unknown dead-zone input. A direct adaptive fuzzy tracking controller is developed by using the backstepping approach. It is proved that the design scheme ensures that all the error variables are bounded in probability while the mean square tracking error becomes semiglobally uniformly ultimately bounded (SGUUB) in an arbi-trarily small area around the origin. Simulation re-sults show the effectiveness of the control scheme.