Polyp segmentation is critical in medical image analysis. While traditional methods produce precise outputs, they often struggle with blurry areas in images, potentially introducing ambiguity in decision-making processes. Enhancing the accuracy and reliability of medical diagnosis demands more advanced approaches capable of effectively handling and interpreting these uncertainty. So we propose multi-scale uncertainty modeling for polyp segmentation grounded in evidence theory. Our method leverages the Dirichlet distribution to classify pixels within polyp images while integrating uncertainty across different scales. We first employ an Uncertainty Region Enhancement Process (UREP) to refine uncertain regions and Integrated Balance Module (IBM) to generate semantic fusion feature maps. Subsequently, we utilize two feature extraction sub-networks to learn feature representations from original images and semantic fusion feature maps. We further develop a Multi-scale Evidence Integration Network (MEIN) to robustly model uncertainty through subjective logic, merging results from two sub-networks to ensure a comprehensive understanding of uncertainty and produce reliable segmentation results. Experimental results on five polyp segmentation datasets demonstrate that our proposed method remains competitive and generates effective uncertainty estimations compared to existing representative methods. Specifically, our method has reached the mean Dice coefficient of 0.905 and 0.923 on the Kvasir and CVC-ClinicDB datasets, 0.791 and 0.788 on the challenging CVC-ColonDB and ETIS datasets.