Background <p>Previous observational studies have indicated that circulating micronutrients may influence obesity risk. This study aimed to explore the causal relationship between micronutrient levels and obesity through multivariable Mendelian randomization (MR) analysis.</p> Methods <p>Single nucleotide polymorphisms (SNPs) significantly associated with 15 micronutrients (selenium, zinc, copper, calcium, beta-carotene, folate, iron, magnesium, potassium, and vitamins A, B6, B12, C, D, and E) from published genome-wide association studies (GWAS) were used as instrumental variables (IVs). Three obesity-related datasets were obtained from the GWAS. Inverse variance weighted (IVW) is the main method used for MR analysis. Leave-one-out analysis, MR-Pleiotropy Residual Sum and Outlier method (MR-PRESSO), weighted median, and MR-Egger method were used to assess pleiotropy and heterogeneity.</p> Results <p>Genetically predicted levels of circulating selenium and calcium are causally related to the risk of obesity (calcium odds ratio [OR]: 1.478, 95% confidence interval [CI] 1.128–1.935, <i>p</i> = 0.005; selenium OR: 1.478, 95% CI 1.128–1.935, <i>p</i> = 0.005). Multivariate MR analysis suggested a causal relationship between circulating selenium and calcium levels and obesity risk (calcium OR: 1.625, 95% CI 1.260–2.097; selenium OR: 1.080, 95% CI 1.003–1.163, <i>p</i> = 0.041). The p-value obtained in the Cochrane <i>Q</i> test, MR-Egger intercept test, and MR-PRESSO were &gt; 0.05, suggesting no significant evidence of pleiotropy or heterogeneity.</p> Conclusion <p>Our study revealed, for the first time, a positive correlation between elevated circulating calcium and selenium levels and an increased obesity risk. These findings provide valuable insights into obesity’s underlying mechanisms. Nevertheless, further large-scale clinical studies are required to confirm our results.</p> <p><i>Level of evidence</i>: Level III, Mendelian randomization.</p>