BACKGROUND: Previous studies suggest an association between schizophrenia and stroke, but no studies have investigated stroke subtypes. We examined potential causal associations between schizophrenia and a range of atherosclerotic, embolic, and hemorrhagic stroke outcomes. METHODS AND RESULTS: Two-sample Mendelian randomization analyses were conducted. The summary-level data (restricted to European ancestry) were obtained for schizophrenia and stroke: ischemic stroke, large-artery stroke, small-vessel stroke, cardioembolic stroke, and intracerebral hemorrhage. The associations between schizophrenia and each outcome were analyzed by an inverse variance weighting method primarily and Mendelian randomization Egger, weighted median, and weighted mode subsequently. The presence of pleiotropy was also tested by Cochran Q statistic, I 2 index, and Mendelian randomization Egger intercept with scatter and funnel plots. We found associations between schizophrenia and cardioembolic stroke (odds ratio [OR], 1.070 [95% CI, 1.023–1.119]) and intracerebral hemorrhage (OR, 1.089 [95% CI, 1.005–1.180]) using inverse variance weighting. Little evidence of associations with the other stroke subtypes was found. Different Mendelian randomization methods corroborated the association with cardioembolic stroke but not intracerebral hemorrhage. CONCLUSIONS: We have provided evidence of a potentially causal association between schizophrenia and cardioembolic stroke. Our findings suggest that cardiac evaluation should be considered for those with schizophrenia.