Background: Mild cognitive impairment (MCI) is an intermediary state between normal aging and dementia. It has a high risk of progression in patients with Alzheimer's disease (AD). Repetitive transcranial magnetic stimulation (rTMS) is a non-invasive brain stimulation technique used to improve cognitive deficits in patients with MCI and AD. Although previous meta-analyses included studies carried on patients with MCI and AD, few studies have analyzed patients with MCI independently. This meta-analysis aimed to evaluate the effects and safety of rTMS on cognition function in patients with MCI and factors that may influence such effects.Methods: Data used in this study were searched and screened from different databases, including PubMed, Web of Science, Embase, the Cochrane Library, Chinese National Knowledge Infrastructure (CNKI), Chinese Technical Periodicals (VIP), Wanfang Database, and China BioMedical Literature Database (SinoMed). The retrieved studies were carefully reviewed, data were extracted, and the quality of data was assessed.Results: A total of 12 studies involving 329 patients with MCI were included in the present meta-analysis. The analyses results revealed that rTMS improved cognitive function [standardized mean difference (SMD) = 0.83, 95% confidence interval (CI) = 0.44–1.22, p = 0.0009] and memory function (SMD = 0.73, 95% CI = 0.48–0.97, p < 0.00001) in the MCI + rTMS active group when compared to the sham stimulation group. The showed that: (1) cognitive improvement was more pronounced under high-frequency rTMS stimulation of multiple sites, such as the bilateral dorsolateral prefrontal cortex and (2) more than 10 rTMS stimulation sessions produced higher improvement on cognition function in patients with MCI.Conclusions: This study shows that rTMS can improve cognitive function in patients with MCI, especially when applied at high frequency, multi-site, and for a prolonged period. However, further studies are required to validate these findings and explore more effective stimulation protocols and targets.Systematic Review Registration: [http://www.crd.york.ac.uk/PROSPERO/], identifier: CRD 42021238708.