Urban spaces possess diverse visual qualities that significantly impact comfort, aesthetics, and navigation. This paper introduces a novel approach towards classifying urban spaces based on their visual characteristics through isovist analysis. An isovist is the polygon representing the visible areas from a given vantage point. The geometrical attributes of the isovist polygon enables a quantitative measure of visual qualities in the urban setting. However, the potential for classifying urban spaces based on the geometrical attributes of isovist polygons remains largely untapped. This paper presents a methodology to systematically categorise urban spaces using isovists and their geometrical attributes. By aggregating ten dimensions of geometrical attributes through a Gaussian Mixture Model (GMM) clustering analysis, this workflow produces a classifier that categorises urban spaces into 10 distinct spatial types, each possessing unique visual and spatial characteristics. This method successfully captures intrinsic spatial typologies across diverse urban contexts and can reflect the values embedded in urban design schemes. By facilitating meaningful and discussions in urban planning and design, this research contributes to a deeper and numerical understanding of the spatial and visual aspects of urban design. Further research avenues include the extension of this methodology to 3D analysis and refining tessellation algorithms for improved computational efficiency and accuracy.