Since Graph Neural Networks (GNNs) made a big impact on graph structured datasets, they are widely utilized in the field of chemistry. However, the reasons behind the prediction of GNNs are not always obvious, so they are considered as black-box models. In this paper, we introduce a graphical user interface (GUI) which can be used for explaining the predictions of GNNs. We aim to integrate our GUI into the user’s research directly to make the predictions of GNNs more understandable in both classification and regression tasks. Furthermore, we offer the option to use the built-in GNN models to train custom datasets directly. Additionally, the system incorporates several explainable artificial intelligence (XAI) techniques, and also allows users to assess the accuracy of explanation findings using various assessment metrics and thus to compare the explanation outcomes. Using the well-known datasets in the field, this tool can also be used for education purposes. The interface provides a comprehensive platform for examining and interpreting the predictions provided by the GNNs and merging several GNN models with XAI approaches. This will facilitate a deeper understanding and possibly lead to new discoveries in researchers’ respective domains in understanding the underlying elements that influence the model’s explainability. The code is made publicly available at https://github.com/ChemGraphExplainer/ChemGraphExplainer .