The present meta-analysis pooled the results from randomized controlled trials (RCTs) to identify and assess the efficacy and safety of thrombin-based hemostatic agent in primary total knee arthroplasty (TKA). Potential academic articles were identified from the Cochrane Library, Medline (1966-2015.5), PubMed (1966-2015.5), Embase (1980-2015.5), and ScienceDirect (1966-2015.5). Relevant journals and the recommendations of expert panels were also searched by using Google search engine. RCTs assessing the efficacy and safety of thrombin-based hemostatic agent in primary TKA were included. Pooling of data was analyzed by RevMan 5.1 (The Cochrane Collaboration, Oxford, UK). A total of four RCTs met the inclusion criteria. The meta-analysis revealed significant differences in postoperative hemoglobin decline (p < 0.00001), total blood loss (p < 0.00001), drainage volume (p = 0.01), and allogenic blood transfusion (p = 0.01) between the treatment group and the control group. No significant differences were found regarding incidence of infection (p = 0.45) and deep vein thrombosis (DVT; p = 0.80) between the groups. Meta-analysis indicated that the application of thrombin-based hemostatic agent before wound closure decreased postoperative hemoglobin decline, drainage volume, total blood loss, and transfusion rate and did not increase the risk of infection, DVT, or other complications. Therefore, the reviewers believe that thrombin-based hemostatic agent is effective and safe in primary TKA.