Gastric cancer is the second most common malignancy and one of the principal causes of cancer-related mortality worldwide. Early diagnostic and screening methods for gastric cancer are limited at present, most of them involving invasive procedures. We aimed to investigate the characteristics of the oral microbiome in gastric cancer individuals and to conduct a screening method for gastric cancer by oral microbiome detection. We used high-throughput sequencing to examine the total bacterial profile of saliva and plaque samples of 50 subjects, including 37 individuals with gastric cancer and 13 controls. The Venn diagram and species abundance clusters were generated from the data. The results indicated that the oral bacteria were more complex in patients with gastric cancer. Based on the characteristics of the oral microbiome in individuals with gastric cancer, a scoring system was designed to screen gastric cancer. In the present study, 36 out of 37 individuals in the gastric cancer group were identified as a high-risk population, giving a sensitivity rate of 97%. One out of 13 individuals in the control group was identified as a high-risk population, providing a false-positive rate of 7.7%. The scoring system we designed may be a potential method for screening suspected gastric cancer patients by oral microbiome detection. Further calibration of this scoring system is needed by recruiting a larger study population.