The mechanisms underlying mitophagy and mitochondrial dynamics (MD) in cervical cancer (CC), a disease with a high mortality rate, remain poorly understood. This study aimed to assess the prognostic significance of these processes in CC. Mendelian randomization (MR) and 101 machine learning models were employed to identify mitophagy- and MD-associated prognostic genes in CC. A subsequent risk model was developed to stratify patients by risk. Further analyses included functional pathway enrichment, immune infiltration, and single-cell RNA sequencing (scRNA-seq) analysis. The results identified PLOD3, SBK1, and SLC39A10 as prognostic genes for CC. Among these, PLOD3 and SLC39A10 were associated with poor prognosis, while SBK1 was protective. The risk model demonstrated high accuracy, with area under the curve (AUC) values exceeding 0.6. Following this, a prognostic nomogram was constructed incorporating risk score and pathological T stage, achieving high predictive accuracy. Gene Set Enrichment Analysis (GSEA) revealed significant enrichment in pathways such as ECM receptor interaction and olfactory transduction in high-risk groups. Additionally, SBK1 showed the strongest correlation with neutrophil infiltration. Expression pattern alterations of prognostic genes were observed in endothelial cells, T cells, and epithelial cells. In conclusion, a risk model based on mitophagy- and MD-related prognostic genes was established, offering a promising approach for the personalized management of patients with CC.