---
title: "microbe"
description: "16S/ITS downstream microbiome analysis via local Rscript (alpha/beta diversity, composition, differential abundance, co-occurrence, random forest)."
canonical: https://agentpluginsdirectory.com/plugins/microbe
last-updated: 2026-10-08
---

# microbe
16S/ITS downstream microbiome analysis via local Rscript (alpha/beta diversity, composition, differential abundance, co-occurrence, random forest).
- Slug: microbe
- Publisher: Presisitence
- Repository: https://github.com/MiniMax-AI/MiniMax-Code-Plugins
- Manifest: plugins/Presisitence/microbe/plugin.json
- Version: 0.1.0
- License: MIT
- Category (editorial): other
- Skills: 1 (microbe)
- MCP servers: 1 (microbe)
- Stars: 18
- Repository created: 2026-08-17
- Repository last pushed: 2026-09-21
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/microbe
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What microbe does, in the publisher's words

Downstream 16S / ITS microbiome analysis for MiniMax Code. vegan, DESeq2, edgeR, igraph, Hmisc, randomForest, and ggtree scripts are wrapped as MCP tools and rendered by local Rscript.

Figure types follow two public papers for layout (the Plugin does not include their data):

- Liu et al. 2023, Nature Microbiology
- Zhou et al. 2022, Nature Communications

Does not run DADA2/QIIME2. Start from a feature table.

- Python 3.10+ and uv on PATH.
- R with Rscript on PATH, or set MICROBE_RSCRIPT.
- R packages such as vegan, ggplot2, igraph; DESeq2/edgeR optional (tools degrade with install hints).
- Windows, macOS, and Linux.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/MiniMax-AI/MiniMax-Code-Plugins/HEAD/plugins/Presisitence/microbe/README.md

## Skills

- microbe: Use when the user has a 16S or ITS feature table plus taxonomy and metadata and needs alpha/beta diversity, composition bars, differential abundance, co-occurrence networks, random-forest biomarkers, or a taxonomy tree. Drive the microbe MCP tools with local Rscript.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- microbe: transport: stdio; command: uv run server.py

Read from the plugin's own mcp.json. Environment variable names only, never values.