The purpose of this study was to prospectively investigate the relation between total diet quality and metabolic syndrome in Korean adults. A community-based cohort of the Korean Genome and Epidemiology Study (KoGES) provided basis for this study. During the total follow-up period of 38,171 person-years of 5,549 subjects, a total of 1,891 metabolic syndrome incident cases were identified. Metabolic syndrome was defined by the criteria of the National Cholesterol Education Program Adult Treatment Panel. Mediterranean Diet Score (MDS), Dietary Approaches to Stop Hypertension diet, and Recommended Food Score (RFS) were used to assess total diet quality. Cox proportional hazards regression was used to estimate hazard ratios (HRs) for metabolic syndrome associated with total diet quality. In men, the incidence of metabolic syndrome in the 5th MDS quintile group decreased by approximately 25% compared to the 1st quintile group (p for trend < 0.01) after adjusting for age and energy intake. In women, significant decreasing trend of metabolic syndrome incidence risk was observed across the quintiles of RFS in an age and energy intake-adjusted model (HR [95% CI] of Q5 vs. Q1; 0.662 [0.521–0.842], p for trend < 0.01). However, such associations did not reach at a significance level when additional covariates were included. In this first study looking at prospective relation of metabolic syndrome with total diet quality in a Korean population, study findings suggest some protective role of better diet quality in preventing future metabolic syndrome. But no convincing evidence was observed in this study.