Tuberculosis (TB) is one of the leading causes of death of infectious disease in the world. It has asymptomatic infection which is hard to detect. There are several studies on TB disease detection and prevention, but very few of them discussing the creation of an expert system on an application programing interface (API). We aim to build an expert API for TB early detection using Forward Chaining and Certainty Factor methods. We found a satisfactory result for the built application on the proposed expert API.