Molecular docking constitutes a fundamental computational technique in Structure-Based Drug Design (SBDD), aiming to predict the optimal binding conformation and affinity of a small-molecule ligand within the active site of a target protein. Formulating molecular docking as a multi-objective optimization problem simultaneously minimizing intermolecular interaction energy and intramolecular conformational strain yields a richer set of candidate solutions for medicinal chemists than traditional single-objective formulations. In this paper, a Multi-Objective Water Optimization Algorithm (MO-WAO) is proposed, extending the recently introduced Water Optimization Algorithm (WAO) of Daliri et al. [1] to handle bi-objective docking problems. WAO is a swarm intelligence metaheuristic inspired by the chemical and physical properties of water molecules, including hydrogen bonding, evaporation, and particle motion dynamics. The proposed MO-WAO integrates Pareto dominance-based ranking, crowding distance computation, and an external archive mechanism to approximate the Pareto optimal front of docking conformations. Two competing objective functions are optimized simultaneously: the intermolecular energy capturing ligand–receptor binding interactions (van der Waals, electrostatic, hydrogen bonding, and desolvation terms) and the intramolecular energy reflecting internal ligand conformational strain. Comprehensive benchmark experiments are conducted on eleven standard protein–ligand complexes sourced from the Protein Data Bank (PDB), spanning diverse therapeutic targets including HIV-1 protease, streptavidin, acetylcholinesterase, and cyclin-dependent kinase 2. The performance of MO-WAO is rigorously compared against five established multi-objective metaheuristics Non-dominated Sorting Genetic Algorithm II )NSGA-II(, Speed-constrained Multi-Objective Particle Swarm Optimization (SMPSO), Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D), Generalized Differential Evolution 3 (GDE3), and S-Metric Selection Evolutionary Multi-Objective Algorithm (SMS-EMOA) as well as the Lamarckian Genetic Algorithm (LGA) from AutoDock as a single-objective reference. Evaluation is performed using four Pareto quality indicators: Hypervolume (HV), Inverted Generational Distance (IGD), spread (Δ), and epsilon (ε), supplemented by Root Mean Square Deviation (RMSD) analysis of predicted binding poses. Results demonstrate that MO-WAO achieves competitive or superior Pareto front approximations, benefiting from the balanced exploration–exploitation mechanism inherent in the hydrogen bonding, evaporation, and motion phases of the water-inspired paradigm.