Abstract In MMO (massively multi-player online) games, the interaction among thousands of players can produce both positive and negative network effects. It is therefore crucial for a company managing MMO games to establish how the entire user base should be distributed across different game instances (‘servers’) in order to optimize the players’ game experience and, ultimately, the company’s revenues. While splitting the user base onto different game servers is a common measure in the industry, there is a conspicuous lack of clear guidelines as to when launching new game servers would be advisable. Our work notably fills this gap: for a popular MMO real-time strategy game, our counterfactual simulation shows that a division of the user base across different game servers can lead to additional revenues if implemented at the right time. For the game in focus, our results indicate that launching multiple new game servers would be beneficial in terms of revenue when the game was new, and additional servers every 90–120 days when it was in decline.