Mediation analysis plays a crucial role in epidemiology, unraveling the intricate path- ways through which exposures exert influence on health outcomes. Recent advances in high-throughput sequencing techniques have generated growing interest in applying mediation analysis to explore the causal relationships between patient environmen- tal exposures, molecular features (such as omics data) and various health outcomes. Mediation analysis handling high-dimensional mediators raise a number of statistical challenges. Despite the emergence of numerous methods designed to tackle these challenges, the majority are limited to continuous outcomes. Furthermore, these ad- vanced statistical approaches have yet to find widespread adoption among epidemiol- ogists and health data scientists in their day-to-day practices. To address this gap, we introduce an R package specifically tailored for high-dimensional mediation analysis us- ing the max-squared method (HDMAX2). This tool aims to mitigate these obstacles by providing a practical solution for researchers and practitioners eager to explore intri- cate causal relationships in health data involving complex molecular features. Here we improve the HDMAX2 method, and expand its capabilities to accommodate multiple exposures and non-continuous variables. This improvement enables its application to a diverse array of mediation analysis scenarios, mirroring the complexity often encoun- tered in healthcare data. To enhance accessibility for users with varying expertise, we release an R package called hdmax2. This package allows users to estimate the indirect effects of mediators, calculate the overall indirect effect of mediators, and facilitates the execution of high-dimensional mediation analysis.