2,700+ scientific tools for AI scientists: life science, research, literature, and more.
io.github.mims-harvard/tooluniverse MCP Server
ToolUniverse is an MCP server that provides access to 2,500+ scientific tools aimed at AI scientists. Its scope covers areas such as life science, research, and literature, as reflected in its description. The server is listed as an MCP Registry entry and has accompanying documentation links in its readme excerpt.
🛠️ Key Features
2,500+ scientific tools
Focus areas include life science, research, and literature
Exposes capabilities for tool use via MCP
🚀 Use Cases
Building AI agents for scientific workflows
Supporting automated science and “co-scientist” style interactions
Enabling research and literature-oriented tool access
⚡ Developer Benefits
Topics indicate support for agents, tool-use, and MCP server integration
Relevant for LLM-based agent applications (including reasoning-oriented setups)
⚠️ Limitations
The provided source data does not specify tool count beyond “2,500+,” nor does it describe specific tools, schemas, or endpoints.
Claude Desktop extension showing "Failed — Server disconnected"? The copy of ToolUniverse in
Claude Desktop's built-in Extensions directory is an old build that cannot start. Remove it, then
use either option below — both install a working version.
Details and status: #585
AI agent (recommended) — open your AI agent and run:
code
Read https://aiscientist.tools/setup.md and set up ToolUniverse for me.
The agent will walk you through MCP configuration, API keys, skill installation, and validation.
--refresh checks PyPI for the newest release on every launch. Drop it
("args": ["tooluniverse"]) to start faster from uv's cache — then upgrade
with uv cache clean tooluniverse.
Install agent skills:
bash
npx skills add mims-harvard/ToolUniverse
Claude Code users — one line, no config file:
bash
claude plugin marketplace add mims-harvard/ToolUniverse
claude plugin install tooluniverse@tooluniverse
Python developers — install the SDK. Install uv first and do not use system pip: on a current Mac, pip install tooluniverse fails with externally-managed-environment (PEP 668) and python3 -m venv can fail at ensurepip. uv manages its own Python and avoids both.
bash
curl -LsSf https://astral.sh/uv/install.sh | sh # if you don't have uv
uv venv --python 3.12 && source .venv/bin/activate
uv pip install tooluniverse
Needs Python 3.10 or newer. On an Apple Silicon Mac it also needs macOS 14 or newer: faiss-cpu, which backs the vector-search tools, publishes no arm64 wheel older than macosx_14_0, so macOS 13 and earlier would have to compile it. Intel Macs, Windows and Linux have no such floor.
The base install covers the API and database tools. Local ML, cheminformatics, and plotting tools need extras — uv pip install 'tooluniverse[all]', or a single group such as [ml], [visualization], [bioinformatics]. Note [all] excludes pdf, singlecell, smolagents, client, and build, which install by name. Run tooluniverse-doctor to see which groups are missing.
tu CLI — discover, inspect, run, and test tools from the terminal.
Python SDK — programmatic access for building AI scientist systems.
ToolUniverse is an ecosystem for creating AI scientist systems from any large language model. Powered by the AI-Tool Interaction Protocol, it standardizes how LLMs identify and call tools, integrating more than 2,700 machine learning models, datasets, APIs, and scientific packages for data analysis, knowledge retrieval, and experimental design.
Key features:
AI-Tool Interaction Protocol: Standardized interface governing how AI scientists issue tool requests and receive results
CLI (tu): Discover, inspect, run, and test tools directly from the terminal — 14 subcommands for interactive and scripted workflows
Agent Skills: 153 pre-built research skills for drug discovery, precision oncology, rare disease diagnosis, pharmacovigilance, and more, plus 63 that install a GPU-backed model locally
Literature Search: Unified search across PubMed, Semantic Scholar, ArXiv, BioRxiv, Europe PMC, and more
Two-Tier Result Caching: In-memory LRU + SQLite persistence with per-tool fingerprinting for 10x speedup, offline support, and reproducibility
Continuous Expansion: Register new tools locally or remotely without additional configuration
image
AI Scientists Powered by ToolUniverse
Building your project with ToolUniverse? Submit via GitHub Pull Request or contact us.
Medea integrates ToolUniverse tools for multi-omics analysis to identify therapeutic targets and predict drug responses across cancer, autoimmune, and other diseases.
Materials from the October 8, 2026 workshop in the Core for Computational Biomedicine (CCB) AI Seminar & Workshop Series at Harvard Medical School. Includes the ToolUniverse workshop slides, CCB introduction slides, and a follow-along Markdown guide for using ToolUniverse live with clinical and genetics examples.
ToolUniverse runs locally and collects nothing: no telemetry, no analytics, no
conversation data. When you run a tool, that tool's arguments are sent to that
tool's data provider (UniProt, openFDA, Open Targets and so on) so it can
answer, and nothing else leaves your machine. API keys stay local and are sent
only to the service they belong to. Full policy:
https://github.com/mims-harvard/ToolUniverse/blob/main/PRIVACY.md
Citation
code
@article{gao2025democratizingaiscientistsusing,
title={Democratizing AI scientists using ToolUniverse},
author={Shanghua Gao and Richard Zhu and Pengwei Sui and Zhenglun Kong and Sufian Aldogom and Yepeng Huang and Ayush Noori and Reza Shamji and Krishna Parvataneni and Theodoros Tsiligkaridis and Marinka Zitnik},
year={2025},
eprint={2509.23426},
archivePrefix={arXiv},
primaryClass={cs.AI},
url={https://arxiv.org/abs/2509.23426},
}
Install
Configuration
Environment variables
OPENAI_API_KEYsecret
OpenAI API key for LLM-based tool finding and embedding features
ANTHROPIC_API_KEYsecret
Anthropic API key for Claude-based features
GEMINI_API_KEYsecret
Google Gemini API key for Gemini-based features
OPENROUTER_API_KEYsecret
OpenRouter API key for accessing 100+ LLM models
AZURE_OPENAI_API_KEYsecret
Azure OpenAI API key (alternative to OpenAI)
HF_TOKENsecret
HuggingFace token for accessing models and datasets
NCBI_API_KEYsecret
NCBI/PubMed API key for higher rate limits (10 req/sec vs 3 req/sec). Register at https://www.ncbi.nlm.nih.gov/account/
SEMANTIC_SCHOLAR_API_KEYsecret
Semantic Scholar API key for higher rate limits (100 req/sec vs 1 req/sec). Register at https://www.semanticscholar.org/product/api
BIOGRID_API_KEYsecret
BioGRID API key for protein-protein interaction queries. Register free at https://webservice.thebiogrid.org/
DISGENET_API_KEYsecret
DisGeNET API key for gene-disease association data. Register free at https://www.disgenet.org/
OMIM_API_KEYsecret
OMIM API key for Mendelian disease data. Register at https://omim.org/api
ONCOKB_API_TOKENsecret
OncoKB API token for precision oncology annotations. Register at https://www.oncokb.org/apiAccess
NVIDIA_API_KEYsecret
NVIDIA NIM API key for AlphaFold2 structure prediction, molecular docking, and genomics tools. Get key at https://build.nvidia.com
USPTO_API_KEYsecret
USPTO API key for patent data access. Register at https://developer.uspto.gov/
UMLS_API_KEYsecret
UMLS API key for medical terminology and concept mapping. Register at https://uts.nlm.nih.gov/uts/
BRENDA_EMAIL
BRENDA enzyme database login email. Register at https://www.brenda-enzymes.org/