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.
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.
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-lab-protocolsgit clone --depth 1 https://github.com/mims-harvard/ToolUniverseWrote 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.
[](https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-lab-protocols)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-lab-protocols"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-lab-protocols/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.
<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-lab-protocols"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-lab-protocols.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01090 |
| Opus 5.5 | $0.00000 | $0.00436 |
| Sonnet 5.5 | $0.00000 | $0.00218 |
| Haiku 4.5 | $0.00000 | $0.00109 |
Grade A, and why
tooluniverse-lab-protocols 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lab Protocol Discovery (protocols.io)
Find a published, step-by-step lab protocol before designing your own from scratch, or pull the exact steps/materials for a protocol someone already pointed you to.
Honesty contract (read first)
- This requires a real API key. protocols.io's API requires
Authorization: Bearer <token>on every endpoint, including protocol search — there is no anonymous tier. IfPROTOCOLS_IO_API_KEYis not set, the tools return a clean error naming the missing key rather than a raw HTTP failure. Tell the user plainly that a key is needed and point them to https://www.protocols.io/api-clients to register an API client and obtain one. - Never fabricate a protocol. If the key is missing or a lookup fails, say so — do not describe a plausible-sounding protocol from memory and present it as if it came from protocols.io.
- Tokens expire (~1 year). A previously-working key that starts failing with an auth error may simply need refreshing, not re-registering from scratch.
When to Use This Skill
Apply when users:
- Want to find a published protocol for a specific technique before running it themselves (e.g., "is there a protocols.io method for lentiviral titering?")
- Already have a protocols.io ID, URI slug, or DOI and want its full description, materials list, or step-by-step instructions
- Want to compare how different labs perform the same technique
NOT for (route elsewhere):
- Designing a novel Gibson/Golden Gate assembly strategy ->
tooluniverse-molecular-cloning - PCR primer design ->
tooluniverse-primer-design - General plasmid/reagent sourcing (Addgene) -> already covered by
Addgene_*tools
Workflow
1. Search for a protocol by technique/keyword
ProtocolsIO_search_protocols {"query": "<technique or keyword>", "limit": <1-50, default 10>, "order_field": "relevance"|"activity"|"date"|"name"|"id"}
Returns candidate protocols with id, title, doi, authors, published_on. Pick the most relevant hit — do not assume the first result is the best match; check the title against what the user actually wants.
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.
- 10d ago First seen · 60 lines · 0 tokens per session scan A ecb8cf488472
tooluniverse-lab-protocols is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,090 tokens. 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 2026-10-07.
Other skills, from other repositories
ai-agent-tool-routing
Use when designing or reviewing an AI agent tool registry or MCP router: document parameter schemas, caller authorization, execution limits, replay-safe retries and verification evidence.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
construct-toy-examples
Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain intuition.
obtain-immediate-conclusions
Derive immediate mathematical consequences from a theorem statement or subgoal. Use when starting a new problem, branch, or subgoal, or when cheap progress or a cleaner reformulation is needed before deeper proof search.
clinical-research-analysis-framework
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
apache-iv-score
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.