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 devtu-auto-discover-apisgit 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/devtu-auto-discover-apis)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/devtu-auto-discover-apis"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/devtu-auto-discover-apis/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/devtu-auto-discover-apis"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/devtu-auto-discover-apis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00084 | $0.01038 |
| Opus 5.5 | $0.00034 | $0.00415 |
| Sonnet 5.5 | $0.00017 | $0.00208 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
devtu-auto-discover-apis 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 1mo 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automated Life Science API Discovery & Tool Creation
Discover, create, validate, and integrate life science APIs into ToolUniverse.
Four-Phase Workflow
Gap Analysis → API Discovery → Tool Creation → Validation → Integration
↓ ↓ ↓ ↓ ↓
Coverage Web Search devtu-create devtu-fix Git PR
Human approval gates after: discovery, creation, validation, and before PR.
Phase 1: Discovery & Gap Analysis
1.1 Analyze Current Coverage
Load ToolUniverse, categorize tools by domain (genomics, proteomics, drug discovery, clinical, omics, imaging, literature, pathways, systems biology). Count per category.
1.2 Identify Gap Domains
- Critical Gap: <5 tools in category
- Moderate Gap: 5-15 tools, missing key subcategories
- Emerging Gap: New technologies not represented
Common gaps: single-cell genomics, metabolomics, patient registries, microbial genomics, multi-omics integration, synthetic biology, toxicology.
1.3 Web Search for APIs
For each gap domain, run multiple queries:
"[domain] API REST JSON"— direct API search"[domain] public database"— database discovery"[domain] API 2025 OR 2026"— recent releases"[domain] database" site:nar.oxfordjournals.org— NAR Database Issue
Extract: base URL, endpoints, auth method, parameter schemas, rate limits.
1.4 Score and Prioritize
| Criterion | Max Points |
|---|---|
| Documentation Quality | 20 |
| API Stability | 15 |
| Authentication Simplicity | 15 |
| Coverage | 15 |
| Maintenance | 10 |
| Community | 10 |
| License | 10 |
| Rate Limits | 5 |
High priority (>=70), Medium (50-69), Low (<50).
1.5 Generate Discovery Report
Coverage analysis, prioritized candidates with scores, implementation roadmap.
Phase 2: Tool Creation
For each API, use Skill(skill="devtu-create-tool") or follow these patterns.
Architecture Decision
- Multiple endpoints → multi-operation tool (single class, multiple JSON wrappers)
- Single endpoint → single-operation acceptable
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 125 lines · 84 tokens per session scan A a7918983c368
devtu-auto-discover-apis is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,739 stars, last pushed today), licensed Apache-2.0. It adds 84 tokens to every session and 1,038 once invoked, about $0.0003 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 2026-09-03.
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.
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.
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.
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.
clinical-research-session
Start a structured clinical research session. Use when users describe research goals, want to analyze cohorts, investigate hypotheses, or need a rigorous research plan. Interviews the user, then produces a research protocol.