This repository hosts the first comprehensive survey of Multimodal Chain-of-Thought (MCoT) reasoning, covering methodologies for step-by-step reasoning across multiple data modalities including images, videos, speech, audio, and 3D data within multimodal large language models. It catalogs research approaches, taxonomizes techniques, and reviews applications in robotics, healthcare, and autonomous driving. The work includes an arXiv paper, structured taxonomy, and discussion channels for collaborative research.