Software-based solutions such as virtual reality simulators and serious games can be useful assets for training minimally invasive surgery technical skills. However, their high cost and lack of realism/fidelity can sometimes be a drawback for their incorporation in training facilities. In this sense, the hardware interface plays an important role as the physical connection between the learner and the virtual world. This article presents the first efforts in integrating the EVA Tracking System, based on computer vision, to control a virtual serious game with real laparoscopic instruments. Integration between the game engine and the tracking system is achieved using ZeroC Ice and Apache Thrift frameworks. Control of the game is viable in this manner, though there are several functional limitations (grasping, rotation), as well as a need to compromise between robustness and lag. Validation with real users will be the next step towards establishing the acceptance and viability of this new solution.