Early diagnosis of breast cancer is crucial, enabling the establishment of appropriate treatment plans and markedly enhancing patient prognosis. While direct magnetic resonance imaging (MRI)-guided biopsy demonstrates promising performance in detecting cancer lesions, its practical application is limited by prolonged procedure times and high costs. To overcome these issues, an indirect MRI-guided biopsy that allows the procedure to be performed outside of the MRI room has been proposed, but it still faces challenges in creating an accurate real-time deformable breast model. In our study, we propose DeformMLP, a deformation prediction method that uses graph topology-assisted multilayer perceptrons (MLPs) as the main backbone architecture. DeformMLP is able to effectively predict the deformation of nodal surfaces given a point force with significantly faster training and low memory requirements. As DeformMLP is designed to take force vectors and graph features as input, along with nontrivial graph structure encoding, which performs feature propagation based on the underlying graph constructed from the element information. Our experimental results demonstrate that DeformMLP outperforms graph neural network (GNN)-based alternatives with respect to both test root mean squared error (RMSE) and efficiency in time and memory costs. The source code is publicly available at https://github.com/jordan7186/DeformMLP .