mims-harvard/ToolUniverse

Democratizing AI scientists with ToolUniverse

1.7kStars on the repository
60Mods indexed here, across every type
2d agoLast push, which is what freshness is scored on
Apache-2.0Licence, which decides whether bodies are shown

compare

01

mims-harvard/ToolUniverse

Command

Side-by-side comparison of N items (drugs, targets, diseases, variants, trials, etc.) with a domain-appropriate column set, structured tabular output, and per-cell source citation. Use when the user wants to evaluate alternatives, not when they want a profile of a single item. Enforces the comparison structure that…

1.7k 2d ago A 74 tokens original Apache-2.0

cross-validate

02

mims-harvard/ToolUniverse

Command

Take a specific scientific claim and confirm or refute it across 3+ independent databases, then report concordance. Use before publishing, citing, or acting on a fact when you want to know how strongly it's supported. Forces multi-source verification that the agent doesn't naturally enforce.

1.7k 2d ago A 59 tokens original Apache-2.0

literature-sweep

03

mims-harvard/ToolUniverse

Command

Run a graded mini-review on a topic across many literature sources, adaptively chosen by domain — a core multi-field set (PubMed, EuropePMC, OpenAlex, Semantic Scholar) plus domain-specific indexes (ArXiv/DBLP for CS, InspireHEP for physics, PubTator/PMC/clinical guidelines for biomedical, Crossref/CORE/DOAJ/Fatcat…

1.7k 2d ago A 144 tokens original Apache-2.0

research

04

mims-harvard/ToolUniverse

Command

Conduct a multi-database scientific research investigation inline in the current chat. Same operating discipline as the /tooluniverse:researcher agent (look up specific claims, cross-validate, honest INDETERMINATE) — but runs in this conversation so you can watch each step, follow up, and refine, instead of receiving…

1.7k 2d ago A 99 tokens original Apache-2.0

self-review

05

mims-harvard/ToolUniverse

Command

Review current or supplied work against the user's actual goal, report evidence-backed strengths, gaps, risks, and fixes, and give a plain-language completion verdict. Qualitative by default; only score or grade when explicitly requested.

1.7k 2d ago A 47 tokens original Apache-2.0

setup-keys

06

mims-harvard/ToolUniverse

Command

Set up ToolUniverse API keys. Opens a graphical setup page (or guides you in chat) listing every key tools can use, with registration links, and saves them permanently to a .env that the MCP server, CLI, and SDK all read. Use when a tool reports a missing API key or when first configuring ToolUniverse.

1.7k 2d ago A 70 tokens original Apache-2.0

translate-id

07

mims-harvard/ToolUniverse

Command

Resolve an identifier across all relevant namespaces (HGNC symbol, Ensembl, UniProt, NCBI Gene ID, RefSeq, MGI, OMIM, ChEMBL, PubChem, etc.). Detects the input namespace automatically, picks the right resolver tool, and returns a complete cross-reference table. Use when you have an ID in one namespace and need it in…

1.7k 2d ago A 85 tokens original Apache-2.0

verify-references

08

mims-harvard/ToolUniverse

Command

Check whether cited references are real and accurately described — confirms each citation actually exists and that its title/authors/year/journal/DOI match what's claimed, using independent databases (Crossref, DataCite, PubMed, OpenAlex, Semantic Scholar, EuropePMC, plus domain-specific sources like…

1.7k 2d ago A 167 tokens original Apache-2.0