The diversity, volume and complexity of astronomical data increase as new astronomical facilities become online. As a result, tasks like the separation between point and extended sources or morphological classification of galaxies, to name a few, also present new challenges for their implementation. On one hand, new Computer Vision models based on Deep Learning have demonstrated revolutionary results, but there is a gap between these models and their day-to-day application by the astronomical community. We present ChiVo-Tools, an exploratory analysis plugin for Python and as a Web Service, that boasts a powerful instance segmentation engine based on the Mask R-CNN architecture. This new application allows the automatic classification and segmentation of galaxies according to their morphology, especifically between elliptical and spiral classes for SDSS images. From the user perspective, ChiVo-Tools works by taking a small region of the sky selected by the user and then, the Deep Learning engine generates an output catalog with the classification of the sources contained. Moreover, ChiVo-Tools seeks to become a trailblazer for a new generation of scientific tools, which will bring the exploratory analysis of astronomical data based on Deep Learning closer to the users.