In this paper we address the issue of hybrid 2D/3D visual servoing. Contrary to popular approaches, we consider the position-based visual servo as the core of our scheme. 2D information is only added when necessary, that is when the observed object is about to leave from the field of view, even partially. The injection of 2D information is tuned by only one parameter, that simply defines the area where a point is considered to be near to the image border. Simulations allow the comparison of the proposed scheme with both position- based and hybrid schemes, showing nice properties. Finally, experiments are performed on a real object that is tracked by a pose estimation algorithm. Results validate the approach by showing the object stays entirely in the image field of view.