Formation of filter bubbles is known as a risk for democracy and can bring negative consequences like polarisation of the society, users’ tendency to extremist viewpoints, and the proliferation of fake news. Previous studies, including prescriptive studies, focused on limited aspects of filter bubbles. The current study aims to propose a model for an integrated tool that assists users in avoiding filter bubbles in social networks. To this end, a systematic literature review has been adopted and 571 papers in six top-ranked scientific databases have been identified. After excluding irrelevant studies and an in-depth study of the remaining papers, a classification of research studies is proposed. This classification is then used to propose an overall architecture for an integrated tool that synthesises all previous studies and proposes new features for avoiding filter bubbles. The study explains the components and features of the proposed architecture and describes their focus on content and agents.