Transit-oriented development (TOD) has been widely seen as one of the most feasible strategies to achieve green mobility. Although existing literature offers vast evidence on the impact of TOD on travel, studies on how to quantitatively design a sketch of metro station-based land use planning integrated with the greenway network are still limited. To fill this gap, we propose a multi-objective optimization model that determines land use type, floor area ratio, and greenway network design of station-level TOD planning, which is solved by an improved immune genetic algorithm. To test the effectiveness of the model and algorithm, this study conducts a case study based on Nanshao Station in Beijing, China. A solution that balances all the planning objectives is analyzed in detail. This study offers a designing method of the TOD planning sketch in cities across the world.