This paper presents our first attempt to apply Support Vector Machines to the problem of automatically tuning CP search algorithms. More precisely, we exploit instances features to dynamically adapt the search strategy of a CP solver in order to more efficiently solve a given instance. In these preliminary results, adaptation is restricted to restart points, and the number of times the strategy changes is also restricted. We report very encouraging results where our adaptation outperforms what is currently considered as one of the state of the art dynamic variable selection strategy.