The association between Asp312Asn and Lys751Gln polymorphisms of Xeroderma pigmentosum Group D (XPD) and prostate cancer risk are still inconclusive. For better understanding of the effects of these two polymorphisms on prostate cancer risk, a meta-analysis was performed. An extensive search was performed to identify all case-control studies investigating such association. The strength of association between these two polymorphisms and prostate cancer risk was assessed by odds ratio (OR) with the corresponding 95 % confidence interval (95 % CI). A total of seven case-control studies were identified, among which five studies (1,257 cases and 1,956 controls) were eligible for Asp312Asn polymorphism and six studies (1,451 cases and 2,375 controls) were eligible for Lys751Gln polymorphism. Asp312Asn polymorphism was associated with an increased risk of prostate cancer in additive and recessive genetic models (additive model: OR = 1.68, 95 % CI = 1.28-2.22, P = 0.00; recessive model: OR = 1.65, 95 % CI = 1.27-2.15, P = 0.00). In the subgroup analysis, Asp312Asn polymorphism was associated with an increased risk of prostate cancer among Asians in all three genetic models (additive model: OR = 2.09, 95 % CI = 1.39-3.14, P = 0.00; dominant model: OR = 1.49, 95 % CI = 1.12-1.98, P = 0.01; recessive model: OR = 1.93, 95 % CI = 1.31-2.83, P = 0.00). However, no significant associations were found between Lys751Gln polymorphism and prostate cancer risk in the overall analyses or the subgroup analyses by ethnicity. The results of this meta-analysis indicate that the XPD Asp312Asn polymorphism is a risk factor for prostate cancer development.