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-glycobiologygit 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-glycobiology)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-glycobiology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-glycobiology/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-glycobiology"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-glycobiology.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 | $0.00226 | $0.01868 |
| Opus 5.5 | $0.00090 | $0.00747 |
| Sonnet 5.5 | $0.00045 | $0.00374 |
| Haiku 4.5 | $0.00023 | $0.00187 |
Grade A, and why
tooluniverse-glycobiology 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glycobiology and Glycomics (GlyGen)
Glycan structure and protein-glycosylation research using GlyGen's 5 ToolUniverse
tools: GlyGen_get_glycan, GlyGen_search_glycans, GlyGen_get_glycoprotein,
GlyGen_search_glycoproteins, GlyGen_get_site.
LOOK UP, DON'T GUESS: Glycan composition, mass, and site-level glycosylation data are highly specific and not reliably recalled from memory — always resolve through these tools rather than asserting a glycan's structure or a protein's glycosylation status from general knowledge.
When to Use This Skill
Apply when users ask about:
- A specific glycan's structure, mass, monosaccharide composition, or species
distribution (given a GlyTouCan accession, e.g.
G17689DH) - Finding glycans that match a mass range, monosaccharide-count range, or glycan type (N-linked / O-linked)
- A protein's overall glycosylation profile (site count, site positions, attached glycans, associated diseases/pathways) given a UniProt accession
- Finding glycosylated proteins in an organism, by gene name, or by glycosylation-evidence level
- Detailed information about one specific glycosylation site: exact position, flanking amino-acid sequence, the glycan attached there, and any SNVs co-located at that position
NOT for (route elsewhere):
- Resolving a gene/protein name to its UniProt accession in the first place ->
tooluniverse-sequence-retrievalortooluniverse-protein-structure-retrieval(GlyGen tools require a UniProt accession as input, not a gene symbol, exceptGlyGen_search_glycoproteins'sgene_namefilter) - 3D protein structure ->
tooluniverse-protein-structure-retrieval - Non-glycan post-translational modifications (phosphorylation as a topic in
its own right, ubiquitination, etc.) ->
tooluniverse-protein-modification-analysis - General small-molecule/chemical compound lookup ->
tooluniverse-chemical-compound-retrieval
Tool Chains for Common Questions
"What glycans are attached to protein X?"
- If you only have a gene symbol, resolve it to a UniProt accession first
(
tooluniverse-sequence-retrieval/tooluniverse-protein-structure-retrieval, or pass the gene name straight intoGlyGen_search_glycoproteins'sgene_namefilter if you just need to confirm the protein is glycosylated at all). GlyGen_get_glycoprotein(uniprot_ac=...)— returnsglycosylation_countand aglycosylation_siteslist, each entry givingposition,residue,type(N-linked/O-linked), and theglytoucan_acof the attached glycan.- For full structural detail on any glycan found in step 2, call
GlyGen_get_glycan(glytoucan_ac=...). - For full detail on one specific site (flanking sequence, co-located SNVs),
build a
site_idas<uniprot_ac>.<start_pos>.<end_pos>(the canonical isoform accession from step 2's response usually needs a-1suffix, e.g.P14210-1.294.294— confirm the exact accession format from the glycoprotein response rather than assuming) and callGlyGen_get_site.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 116 lines · 226 tokens per session scan A fede0d0b546d
tooluniverse-glycobiology is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 226 tokens to every session and 1,868 once invoked, about $0.0009 per session on Opus 5.5. 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.