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 routergit 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/router)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/router"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/router/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/router"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/router.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 | $0.00137 | $0.00682 |
| Opus 5 | $0.00068 | $0.00341 |
| Sonnet 5 | $0.00027 | $0.00136 |
| Haiku 4.5 | $0.00014 | $0.00068 |
Grade A, and why
tooluniverse-research 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 7d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ToolUniverse Research
Brings ToolUniverse's 2500+ scientific tools and 133 structured research workflows into Claude Science. The tooluniverse PyPI package supplies the tools; this skill bundles the workflows and a kernel sidecar that wires them up.
Setup
Run all cells in the tooluniverse conda environment. Loading this skill auto-defines these helpers in the kernel:
get_tu()→ a loadedToolUniverseinstance (cache redirected to the workspace, since~/.tooluniverseis read-only here).tu_workflows()→ list all 133 workflows (name+description).find_tu_workflow(query)→ rank workflows by relevance to a question.tu_workflow(name)→ the full step-by-step procedure for one workflow.tu_tool_info(tu, name)→ a tool's JSON spec, including its argument schema.
Answering a research question
- Route to a workflow:
find_tu_workflow("tell me about metformin")returns ranked names. (Or browsetu_workflows().) - Load its procedure:
print(tu_workflow("tooluniverse-drug-research"))and follow the steps. - Execute the tools the workflow names. Every
ToolName(args)reference maps to:tu = get_tu() tu.run({"name": "PubChem_get_CID_by_compound_name", "arguments": {"name": "metformin"}}) - Confirm argument names before a call if unsure —
tu_tool_info(tu, "PubChem_get_CID_by_compound_name")shows the exact schema. Workflow prose abbreviates arguments; the schema is authoritative. - Discover tools at runtime when no workflow fits:
tu.run({"name": "Tool_Finder_Keyword", "arguments": {"description": "drug adverse events", "limit": 10}})
Notes
- Most tools work without API keys. A few (NCBI, OncoKB, NVIDIA, …) unlock enhanced access when keys are set in the env — add under Customize → Credentials, then expose them in the
tooluniverseenv. - Workflows are self-contained: report templates, checklists, and tool references are appended to each as appendices.
- These workflows emphasize looking things up over recalling them — when a workflow says query a database, run the tool rather than answering from memory.
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.
- 7d ago First seen · 42 lines · 137 tokens per session scan A dbaecff09929
tooluniverse-research is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed yesterday), licensed Apache-2.0. It adds 137 tokens to every session and 682 once invoked, about $0.0007 per session on Opus 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
llm-integration
LLM integration patterns for function calling, streaming responses, local inference with Ollama, and fine-tuning customization. Use when implementing tool use, SSE streaming, local model deployment, LoRA/QLoRA fine-tuning, or multi-provider LLM APIs.
agent-engineering-expert
Build LLM agents that use tools safely: tool design, the agent loop, memory, MCP servers, multi-agent orchestration, sandboxing and prompt-injection defence. Use when the user mentions AI agents, tool use or function calling, MCP or Model Context Protocol, autonomous workflows, multi-agent systems, LangChain or…
external-repo-setup
Protocol for GPU agents to clone external GitHub repos, install their dependencies, download pretrained weights, and integrate them as featurizers or models inside a focus-area train.py. Use this when a proposal references a GitHub repo or pretrained checkpoint that is not already present in the focus-area workspace.
multi-agent-focus
Generic skill for self-organizing multi-agent teams that collaborate on an optimization problem. Agents discuss dimensions, form teams, run experiments, and adapt when stagnating. Uses AnonAPI posts for discussion and workspaces for shared state.
agentic-patterns
Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent"…
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.