Changes in gastric microbiome are associated with gastric carcinogenesis. Studies on the association between gastric mucosa-associated gastric microbiome (MAM) and metachronous gastric cancer are limited. This study aimed to identify gastric MAM as a predictive factor for metachronous recurrence following endoscopic resection of gastric neoplasms. Microbiome analyses were conducted for 81 patients in a prospective cohort to investigate surrogate markers to predict metachronous recurrence. Gastric MAM in non-cancerous corporal biopsy specimens was evaluated using Illumina MiSeq platform targeting 16S ribosomal DNA. Over a median follow-up duration of 53.8months, 16 metachronous gastric neoplasms developed. Baseline gastric MAM varied with Helicobacter pylori infection status, but was unaffected by initial pathologic diagnosis, presence of atrophic gastritis, intestinal metaplasia, or synchronous lesions. The group with metachronous recurrence did not exhibit distinct phylogenetic diversity compared with the group devoid of recurrence but showed significant difference in β-diversity. The study population could be classified into two distinct gastrotypes based on baseline gastric MAM: gastrotype 1, Helicobacter-abundant; gastrotype 2: Akkermansia-abundant. Patients in gastrotype 2 showed higher risk of metachronous recurrence than gastrotype (Cox proportional hazard analysis, adjusted hazard ratio [95% confidence interval]: 5.10 [1.09-23.79]). Gastric cancer patients can be classified into two distinct gastrotype groups by their MAM profiles, which were associated with different risk of metachronous recurrence.