Background: Prediction of the compound cytotoxicity is a crucial issue in the development of new drugs and potential biomedical applications. Experimental studies are time-consuming and expensive. Machine learning models can quickly predict the cytotoxicity of compounds, by extracting new insights from large materials and biological data sets, and provide further guidance for experimental studies. Results: Here, we identify the most relevant features that are responsible for the cytotoxic behavior of layered MXenes materials. The most important result of our work is the identification of 2D MXenes specific surface parameters as responsible for the potential cytotoxicity of these materials, in particular, the presence of transition metal oxides and Lithium atoms on the surface. After successful verification of the correct predictions of our model,we have also succeeded in predicting toxicity for 2D MXenes not tested in vitro. Hence, we have been able to complement the existing knowledge coming from in vitro studies. Conclusions: Our results allow for the future selection of synthesis methods preventing surface oxidation, which should allow production of non-toxic 2D MXenes. Such materials might find application in many fields of science and technology, especially in biotechnology and nanomedicine.