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.
git 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/commands/mims-harvard/tooluniverse/translate-id)<a href="https://agentmods.dev/commands/mims-harvard/tooluniverse/translate-id"><img src="https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/translate-id/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/commands/mims-harvard/tooluniverse/translate-id"><img src="https://agentmods.dev/badge/commands/mims-harvard/tooluniverse/translate-id.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 | $0.00085 | $0.01533 |
| Opus 5 | $0.00043 | $0.00766 |
| Sonnet 5 | $0.00017 | $0.00307 |
| Haiku 4.5 | $0.00009 | $0.00153 |
Grade A, and why
translate-id 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 9d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Translate this identifier across namespaces: $ARGUMENTS
Direct ID lookup is brittle: each tool expects its own namespace, and silently returns nothing if you pass the wrong one. Detect, route, and report.
Process
1. Detect input namespace
Inspect the identifier shape:
| Pattern | Namespace |
|---|---|
^ENS[GTPR]\d+(\.\d+)?$ |
Ensembl gene/transcript/protein/RefSeq |
^[OPQ][0-9][A-Z0-9]{3}[0-9]$ or ^[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}$ |
UniProt accession |
^NM_\d+(\.\d+)?$, ^NP_, ^XM_ |
RefSeq |
^\d+$ (numeric only) |
likely NCBI Gene ID — confirm via metadata |
^OMIM:\d+$ or ^\d{6}$ (6-digit) |
OMIM |
^MGI:\d+$ |
MGI |
^CHEMBL\d+$ |
ChEMBL |
^CID\d+$ or ^\d+$ in chemistry context |
PubChem CID |
^DB\d{5}$ |
DrugBank |
^MONDO:\d+$, ^DOID:\d+$, ^EFO:\d+$ |
ontology disease IDs |
^rs\d+$ |
dbSNP |
| All-caps, 1-10 chars, no digits | likely HGNC gene symbol |
| Free-form name | drug name / disease name — fuzzy lookup |
If ambiguous (e.g., "BRAF" could be gene OR drug target context), ASK the user or pick gene by default and note the assumption.
2. Pick the resolver
For genes/proteins:
- HGNC symbol → all →
tu run MyGene_query_genes '{"query":"<symbol>","species":"human"}'(returns Ensembl, UniProt, RefSeq, NCBI Gene, MGI in one call) - Ensembl ID → all →
tu run ensembl_lookup_gene '{"gene_id":"<id>"}' - UniProt → gene/Ensembl →
tu run UniProt_search '{"query":"<accession>","limit":1}' - NCBI Gene ID → all →
tu run NCBIGene_get_summary '{"id":"<id>"}'then chain
For chemicals:
- Drug name → all →
tu run ChEMBL_search_molecules '{"query":"<name>","limit":1}'thentu run PubChem_get_CID_by_namefor cross-ref - ChEMBL ID → all →
get_tool_infoto find the right cross-ref tool
For diseases:
- Disease name → MONDO/DOID/EFO/OMIM →
tu run ols_search_terms '{"query":"<name>","ontologies":["mondo","doid","efo"]}' - OMIM → MONDO →
tu run MONDO_search(if available) orols_search_terms
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.
- 9d ago First seen · 112 lines · 85 tokens per session scan A c80621d234cb
translate-id is a command published in the GitHub repository mims-harvard/ToolUniverse (1,676 stars, last pushed yesterday), licensed Apache-2.0. It adds 85 tokens to every session and 1,533 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other commands, from other repositories
writing
You are the Writing Agent for NanoResearch. Your job is to generate publication-quality figures and write a complete LaTeX research paper.
experiment
You are the Experiment Agent for NanoResearch. This command combines the Setup, Coding, and Execution stages. You will generate runnable experiment code and execute it.
astro-dso-doc
Generate pixinsight project information for a deep-sky object astrophotography session.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.