Background: The accurate diagnosis of tuberculous pleurisy is still a clinical challenge. Many studies reported that interferon-gamma-induced protein of 10 kDa (IP-10) plays a role in diagnosing tuberculous pleurisy, but with considerable variance of results. This meta-analysis aimed to evaluate the overall diagnostic accuracy of IP-10 for tuberculous pleurisy. Methods: PubMed, EMBASE, and other databases were searched for studies examining accuracy of pleural IP-10 for diagnosing tuberculous pleurisy. Related data were extracted and sensitivity/specificity, positive/negative likelihood ratio (PLR/NLR), and diagnostic odds ratio (DOR) were pooled. Summary receiver operating characteristic curve and area under the curve (AUC) were performed and calculated to summarize the overall test performance. Results: Fourteen studies involving 1382 subjects met inclusion criteria, including 715 cases of tuberculous pleurisy and 667 controls. Summary estimates of the diagnostic performance of the IP-10 for tuberculous pleurisy were listed as follows: sensitivity, 0.84 (95%CI 0.81 to 0.87); specificity, 0.90 (95% CI 0.88 to 0.92); PLR, 7.96 (95% CI 5.59 to 11.32); NLR, 0.19 (95% CI 0.15 to 0.24); DOR, 49.82 (95% CI 28.08 to 88.38); and AUC 0.94. No publication bias was detected. Conclusion: Pleural IP-10 is a useful diagnostic marker for tuberculous pleurisy. Nevertheless, its result should be interpreted together with the results of conventional test and clinical information of patients.