What is tooluniverse?

A collection of scientific research tools and specialized skills covering biology, chemistry, medicine, and data science. It connects to databases such as PubMed, a database of biomedical papers, and UniProt, a protein-information database, through one interface.

Searching scientific databases, analyzing genomic and clinical data, researching proteins and variants, supporting drug discovery, and carrying out related biology, chemistry, medicine, and data-science work.

It brings many research databases and analysis tasks together, reducing the need to learn and connect each service separately.

tooluniverse — Plugin for Claude Code by mims-harvard

About the project

ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.

mims-harvard/ToolUniverse · 1,744 stars · on GitHub · aiscientist.tools

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/mims-harvard/ToolUniverse

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/mims-harvard/tooluniverse/plugin/github.svg)](https://agentmods.dev/plugins/mims-harvard/tooluniverse/plugin)

Your own site

<a href="https://agentmods.dev/plugins/mims-harvard/tooluniverse/plugin"><img src="https://agentmods.dev/badge/plugins/mims-harvard/tooluniverse/plugin/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/mims-harvard/tooluniverse/plugin"><img src="https://agentmods.dev/badge/plugins/mims-harvard/tooluniverse/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 162 skills, 8 commands, 1 agent, 1 hook, 1 MCP server cost 18,140 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

tooluniverse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugin/.claude-plugin/plugin.json · 32 lines

What it actually says

{
  "name": "tooluniverse",
  "description": "1000+ scientific research tools for biology, chemistry, medicine, and data science. Access PubMed, UniProt, PubChem, TCGA, NHANES, GWAS Catalog, and hundreds more databases through a unified MCP interface. Includes 120+ specialized research skills for genomics, drug discovery, clinical analysis, protein variant interpretation, and more.",
  "version": "1.5.8",
  "author": {
    "name": "Shanghua Gao",
    "url": "https://shgao.site"
  },
  "homepage": "https://aiscientist.tools",
  "repository": "https://github.com/mims-harvard/ToolUniverse",
  "license": "Apache-2.0",
  "keywords": [
    "science",
    "biology",
    "chemistry",
    "medicine",
    "genomics",
    "bioinformatics",
    "rna-seq",
    "deseq2",
    "phylogenetics",
    "drug-discovery",
    "clinical-trials",
    "pubmed",
    "uniprot",
    "pubchem",
    "tcga",
    "research",
    "mcp"
  ]
}

Contents

What it installs

The manifest is a name and a version. 162 skills, 8 commands, 1 agent, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 18,140 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago Changed 952e316cf485
9d ago Changed fa6c60428580
29d ago Changed f6522269135e
1mo ago First seen · 32 lines scan A 6efd3802df40

Subscribe to this mod's changes

tooluniverse is a plugin published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Research Scientific agents ai-agents ai-scientists reasoning-agent reasoning-language-models tool-use

tooluniverse

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

What it actually says

What it installs

What this file has done since we first saw it

Other plugins, from other repositories

full

results-to-slides

humanizer

nextjs

themes-example

claude-plugins-official marketplace