Intrauterine administration of autologous peripheral blood mononuclear cells (PBMC) has been proposed to improve implantation rates in women with recurrent implantation failure (RIF). The objective of this study was to evaluate whether intrauterine administration of PBMC improves clinical pregnancy and live birth in couples with RIF. Various databases were searched including Medline, Embase, Scopus, Web of Science and Cochrane Central Register of Controlled Trials up to April 2018. This review included all studies that compared intervention of PBMC in infertile women undergoing any form of assisted reproductive technology (ART). Two independent reviewers assessed eligibility; methodological quality; and extracted data. Meta-analysis using a random-effects model was performed to calculate the pooled estimates. Eight studies involving 886 patients were included. The probability of clinical pregnancy was significantly higher in women who received PBMC compared with control (RR: 1.92, 95% CI: 1.48–2.49; P < 0.001). No difference was observed in the studies that transmitted the embryo at blastocyst (RR: 2.44, 95% CI: 1.42–4.20; P = 0.001), or cleavage stage (RR: 2.01, 95% CI: 1.36–2.96; P < 0.001). There was no difference between studies that transmitted the embryo in fresh (RR: 2.14, 95% CI: 1.38–3.32; P < 0.001), or frozen condition (RR: 1.79, 95% CI: 1.32–2.43; P < 0.001). The probability of live birth was significantly higher in women who received PBMC compared with control (RR: 1.93, 95% CI: 1.35–2.76; P < 0.001). Administration of PBMC, irrespective of embryo stage and cycle type, increases clinical pregnancy and live birth in patients experienced RIF. However, these overall estimates should be considered with caution due to the small number, quasi-experimental design and poor quality of most included studies.