Introduction: Breast cancer is the most prevalent malignancy among women worldwide, and the adverse effects of conventional chemotherapy highlight the need for more selective and less toxic therapeutic alternatives. In this context, bioinformatics approaches have emerged as promising tools for preclinical screening of new chemotherapeutics based on natural compounds. Methodology: The cytotoxic potential and molecular mechanisms of action of the phenylpropanoids verbascoside and isoverbascoside, isolated from Pyrostegia venusta, were evaluated using in silico methods. Cytotoxicity predictions (pIC₅₀) were performed with CLC-Pred 2.0 for the ER-positive tumor cell lines MCF7 and T47D and the non-tumorigenic MCF-10A cell line. Estrogen receptor interactions were assessed using ADMETLab 2.0, and nuclear receptor binding was further evaluated by molecular docking using CB-DOCK2, with tamoxifen used as a reference. Differentially expressed microRNAs were analyzed using CancerMIRNome, including through the creation of ROC curves and Kaplan–Meier survival analyses. Protein–protein interaction networks were constructed to investigate potential molecular mechanisms. Results: Verbascoside and isoverbascoside exhibited higher safety profiles in MCF-10A cells compared to tamoxifen. Tamoxifen showed greater cytotoxicity (pIC₅₀ > 5.3), whereas the natural compounds had lower pIC₅₀ values. Verbascoside stood out with higher predicted growth inhibition (pIG₅₀ = 6.0363), indicating potential antiproliferative effects. Only tamoxifen and isoverbascoside interacted with the nuclear estrogen receptor. The microRNA hsa-miR-21-5p demonstrated high accuracy in tissue discrimination (AUC = 0.97) but no significant prognostic value (HR = 0.99; p = 0.97). Network analysis suggested involvement of PTEN as a molecular target, with isoverbascoside showing a greater binding affinity to the receptor (-8.4 kcal.mol^-1), comparable to that of tamoxifen (-7.5 kcal.mol^-1). Conclusion: The findings indicate that these phenylpropanoids, particularly isoverbascoside, hold promising potential for use as natural antitumor agents for treating breast cancer, exhibiting favorable cellular selectivity and relevant interactions with hormonal receptors and molecular biomarkers.