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-database-loginsgit 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-database-logins)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-database-logins"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-database-logins/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-database-logins"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-database-logins.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 | $0.00127 | $0.01061 |
| Opus 5.5 | $0.00051 | $0.00424 |
| Sonnet 5.5 | $0.00025 | $0.00212 |
| Haiku 4.5 | $0.00013 | $0.00106 |
Grade A, and why
tooluniverse-database-logins 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 8d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add a database login for ToolUniverse
Most ToolUniverse tools need no login. A few databases require the user's own free or licensed account. The person you are helping is usually a scientist, not a programmer: explain in plain words, one step at a time.
Never ask the user to paste a key, token or password into the chat, and never put one in a file, command or message yourself. Keys are typed only into the ToolUniverse website (hosted use) or the user's own local settings (local use).
1. Find out which login is needed
- If a tool failed, its error names the missing or rejected setting (for example
OMIM_API_KEY). Use that exact name. - If the user asks in general, ask what they want to do, and suggest only the logins that unlock it. Do not push them to collect every key.
Common ones:
| Login | Unlocks | Where to get it | Cost / wait |
|---|---|---|---|
NCBI_API_KEY (+ NCBI_EMAIL) |
Faster PubMed, Gene, Protein and other NCBI tools (they work without it, slower) | https://account.ncbi.nlm.nih.gov/settings/ → API Key Management | Free, ~2 minutes |
OMIM_API_KEY |
OMIM genetic-disorder, gene and phenotype tools | https://www.omim.org/api | Free for research; approval can take days |
DISGENET_API_KEY |
DisGeNET gene–disease associations | https://disgenet.com/signup/ | Account; API access depends on plan |
UMLS_API_KEY |
UMLS terminology and concept lookup | https://uts.nlm.nih.gov/uts/profile | Free UTS account and license |
OPENALEX_API_KEY |
OpenAlex papers, authors, institutions | https://openalex.org/settings/api | Free account |
SEMANTIC_SCHOLAR_API_KEY |
Higher Semantic Scholar limits | https://www.semanticscholar.org/product/api | Free, by request |
HF_TOKEN |
Hugging Face–hosted models and datasets | https://huggingface.co/settings/tokens | Free account |
The full list, with steps for each, is on https://connect.aiscientist.tools/credentials (search box). Before the user signs up for anything paid, metered, or requiring a license or an institutional claim, say so and let them decide.
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.
- 8d ago First seen · 56 lines · 127 tokens per session scan A 786f73938d22
tooluniverse-database-logins is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 127 tokens to every session and 1,061 once invoked, about $0.0005 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 2026-10-09.
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.