mims-harvardOfficial·150 Agent Skills Included

ToolUniverse

Give AI agents 1000+ scientific databases and research workflows

Connects AI agents to over 1000 scientific databases, ML models, and APIs covering genomics, drug discovery, proteomics, clinical trials, and literature search. Eliminates manual querying of PubMed, ChEMBL, GWAS Catalog, PDB, and dozens of other research sources through one standardized interface. Includes 68 pre-built research workflows for variant interpretation, ADMET profiling, single-cell analysis, and meta-analysis so agents complete studies faster.

1,668|254

↗

npx skills add mims-harvard/ToolUniverse --all -g -y

All Skills in This Repository (150)

Pure Emerald Level Indicators

📦 In Repo

mims-harvard

tooluniverse-gwas-study-explorer

Compare GWAS studies, meta-analyze loci, and assess replication across cohorts.

tooluniverse-microbiome-research

Analyze microbiome studies, taxonomic profiles, and genome quality using MGnify, GTDB, ENA, and EuropePMC.

tooluniverse-metabolomics-analysis

Analyze metabolomics data from identification through pathway enrichment and multi-omics integration.

tooluniverse-data-wrangling

Download and parse scientific data from APIs and file formats using Python code.

tooluniverse-immune-repertoire-analysis

Analyzes TCR and BCR repertoire sequencing data for clonality, diversity, and antigen specificity.

tooluniverse-single-cell

Analyze single-cell RNA-seq data with scanpy from QC gating through clustering and annotation.

tooluniverse-admet-prediction

Profiles ADMET properties and toxicity of drug candidates from SMILES or compound names.

tooluniverse-variant-to-mechanism

Trace genetic variants through regulatory context, target genes, and pathways to disease mechanisms.

tooluniverse-proteomics-data-retrieval

Search and retrieve proteomics dataset metadata from MassIVE and ProteomeXchange repositories.

tooluniverse-gpcr-structural-pharmacology

Analyzes GPCR ligands, structures, mutations, and antibody interfaces via GPCRdb, SAbDab, and PDBePISA.

tooluniverse-meta-analysis

Pool effect sizes across multiple studies with fixed- or random-effects meta-analysis and heterogeneity statistics.

tooluniverse-dataset-discovery

Find and evaluate research datasets across scientific repositories for any research question.

Official

Advanced

Frequently Asked Questions

FAQPage Schema

How to install ToolUniverse?▼

Run `npx skills add mims-harvard/ToolUniverse --all -g -y` in your terminal to install all skills in this suite globally.

What is ToolUniverse used for?▼

It lets AI agents query 1000+ scientific databases and tools (PubMed, UniProt, ChEMBL, GWAS Catalog, AlphaFold) through one standard protocol, powering research workflows like drug discovery, variant interpretation, and literature review.

Does ToolUniverse work with Claude and other AI agents?▼

Yes. It runs as an MCP server compatible with Claude Code, Cursor, VS Code, Windsurf, and other MCP clients, and also offers a CLI and Python SDK.

What research workflows are included?▼

Pre-built skills cover GWAS analysis, single-cell RNA-seq, metabolomics, ADMET prediction, ACMG variant classification, drug repurposing, meta-analysis, and epidemiological modeling.

Do I need coding experience to use ToolUniverse?▼

No. In chat mode you simply ask your AI assistant questions in plain English, and it selects and runs the right scientific tools for you.