We aimed to assess the potential causal association between Parkinson's disease (PD) and ischemic stroke (IS) with Mendelian randomization methods. Summary statistics data from two large-scale genome-wide association studies (GWAS) for 33,674 PD cases and 40,585 IS cases were used in this study. We used inverse variance-weighted method for primary analysis, and four other Mendelian randomization methods (weighted median, MR-Egger regression methods, robust adjusted profile score, radial regression) to test whether PD was causal for IS and its subtypes. Analyses were bidirectional to assess reverse causality. Primary analysis showed PD had a significantly causal association with IS (OR 1.04; 95% CI, 1.02-1.07; p = 0.0019), and two subtypes of IS, cardioembolic stroke (OR 1.11; 95% CI, 1.06-1.18; p = 0.0001) and large artery stroke (OR 1.08; 95% CI, 1.01-1.15; p = 0.034), but not with small-vessel stroke (p = 0.180). The point estimates from sensitivity analyses were in the same direction. There was no strong evidence for a reverse causal association between PD and IS. Using multiple Mendelian randomization methods based on large-scale GWAS, PD is a potential cause of cardioembolic stroke and large artery stroke, but not small-vessel stroke. Ischemic stroke does not cause PD.© 2021. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.