Developed a metadata collection and analysis pipeline for the egenomics/agb2025 repository, focusing on Group4’s MGnify data. The work centered on building a reproducible workflow that automates metadata export and analysis, supporting scalable data retrieval and study-specific context. Leveraging R programming, the solution integrated MGnifyR for API access, vegan for bioinformatics processing, and ggplot2 for visualization. The pipeline outputs a detailed CSV and an R Markdown script, enabling efficient data extraction and processing from the MGnify database. This approach provided a shareable, reproducible framework for Group4 analytics and reporting, emphasizing robust API integration and bioinformatics-aware data handling.