MarS is a financial market simulation engine driven by a generative foundational model (LMM), capable of dynamically generating sequences of orders based on historical financial market data in response to various conditions, including user-injected interactive orders, fuzzy target scenario descriptions, and current/recent market data. MarS matches generated order sequences and user interactive orders in real-time within a simulation clearinghouse, producing fine-grained simulated market trajectories. The flexibility of MarS allows it to support various downstream applications such as forecasting, detection systems, analysis platforms, and agent training environments.