Graph Foundation Model (GFM) is a new trending research topic in the graph domain, aiming to develop a graph model capable of generalizing across different graphs and tasks. However, a versatile GFM has not yet been achieved.The key challenge in building GFM is how to enable positive transfer across graphs with diverse structural patterns. Inspired by the existing foundation models in the CV and NLP domains, we propose a novel perspective for the GFM development by advocating for a "graph vocabulary", in which the basic transferable units underlying graphs encode the invariance on graphs. We ground the graph vocabulary construction from essential aspects including network analysis, theoretical foundations, and stability. Such a vocabulary perspective can potentially advance the future GFM design following the neural scaling laws.