Mental disorders seriously affect people’s health and social stability. This Mendelian randomization (MR) study was designed to investigate the causal relationship between circulating vitamin C (VC) or 25-hydroxyvitamin D (25(OH)D) levels and mental disorders. The data used for the MR analysis were derived from the summary genome-wide association studies (GWAS) database for VC and 25(OH)D and from the FinnGen consortium for fourteen mental disorders. Based on the inverse variance weighted (IVW) method, we found a potential causal association between circulating VC and anxiety disorders (IVW:OR = 1.139, 95% CI: 1.023-1.269, P = 0.018). However, no causal association was found between VC or 25(OH)D and other mental disorders (P > 0.05). In the reverse MR analysis, individuals with Alzheimer’s disease was causally associated with higher concentrations of circulating VC (P = 0.012), while individuals with anxiety disorders had a negative association between the concentrations of 25(OH)D (P = 0.012). However, the current evidence does not support a causal relationship between VC or 25(OH)D and other mental disorders. In addition, there was no causal association between circulating VC and 25(OH)D (P > 0.05). Future studies are needed to confirm these findings and to elucidate the mechanisms of potential causality.