Obesity has become an outstanding public health issue in most countries around the world. Many attempts have been made to address this issue that ranges from taking medication to doing exercise to following a diet plan to playing games. Few approaches combine exercise and game to engage the obese people in playing fun-based games or purposeful games, also known as serious games, while monitoring their biosignals. However, existing work hardly provides a configurable, scalable and context-aware serious game framework that can be used as a support for obesity treatment. In this paper, we take an attempt to propose such a framework. The proposed framework facilitates bio-signal monitoring based on body sensor network, context-awareness based on pervasive sensors, and on-the-spot activity recommendation based on current game-playing context. It uses the cloud computing platform as infrastructural support that ensures the scalability of the framework. In order to demonstrate the suitability of the proposed framework, we developed a sample serious game; deploy it over a cloud platform; and experiment with it by capturing some psycho-physical data while the obese are engaged in game-play. We observed that the obese people were very much engaged in game-play and they had positive experience using the system.