The current pandemic of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused more than 2,000,000 deaths worldwide . Currently, vaccine development and drug repurposing have been the main strategies to find a COVID-19 treatment . However, the development of new drugs could be the solution if the main strategies fail . Here, a virtual screening of pentapeptides was applied in order to identify peptides with high affinity to SARS-CoV-2 main protease (Mpro). Over 70,000 peptides were screened employing a genetic algorithm that uses a docking score as the fitness function . The algorithm was coupled with a RESTful API to persist data and avoid redundancy . The docking exhaustiveness was adapted to the number of peptides in each virtual screening step, where the higher the number of peptides, the lower the docking exhaustiveness . Two potential peptides were selected (HHYWH and HYWWT), which have higher affinity to Mpro than to human proteases . Albeit preliminary, the data presented here provide some basis for the rational design of peptide-based drugs to treat COVID-19.