During the course of development of Mechanical Engineering, a large number of mechanisms (that is, linkages to perform various types of tasks) have been conceived and developed. Quite a few atlases and catalogues were prepared by the designers of machines and mechanical systems. However, often it is felt that a clustering technique for handling the list of large number of mechanisms can be very useful,if it is developed based on a scientiﬁc principle. In this paper, it has been shown that the concept of fuzzy sets can be conveniently used for this purpose, if an adequate number of properly chosen attributes (also called characteristics) are identiﬁed. Using two clustering techniques, the mechanisms have been classiﬁed in the present work and in future, it may be extended to develop an expert system, which can automate type synthesis phase of mechanical design. To the best of the authors’ knowledge, this type of clustering of mechanisms has not been attempted before. Thus, this is the ﬁrst attempt to cluster the mechanisms based on some quantitative measures. It may help the engineers to carry out type synthesis of the mechanisms.