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-use-shared-computergit 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-use-shared-computer)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-use-shared-computer"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-use-shared-computer/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-use-shared-computer"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-use-shared-computer.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 | $0.00102 | $0.00591 |
| Opus 5.5 | $0.00041 | $0.00236 |
| Sonnet 5.5 | $0.00020 | $0.00118 |
| Haiku 4.5 | $0.00010 | $0.00059 |
Grade A, and why
tooluniverse-use-shared-computer 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use a colleague's computer or a published tool
Colleagues can share the tools on their computer, and scientists can publish single tools to ToolUniverse. The tools run on their computer; nothing runs on the user's. The person you are helping is usually a scientist: keep it plain.
1. Join with a share code (once per computer)
A colleague sends a code that starts with TU-SHARE- (sometimes inside an invitation message). The user redeems it once:
- Open https://connect.aiscientist.tools/dashboard (sign in if asked).
- Paste the code into Use a colleague's computer and click Join.
The code is the colleague's to give; do not post it anywhere else. If the page says the code is invalid or expired, ask the colleague for a new one.
If ToolUniverse runs locally on this computer instead of the hosted service, the same code works with tu connect TU-SHARE-....
2. Find the tools
With the hosted ToolUniverse connection:
- Call
list_remote_tools(optionally with words from the task, such as "protein" or the computer's name). It lists tools on the user's own computers, computers they joined, and published tools, each with an id, a description, its inputs and whether its computer is online. - Published tools can also be browsed at https://connect.aiscientist.tools/discover ("Shared by scientists").
Pick the tool that fits the task; tell the user which one and from whose computer.
3. Run them
Call run_remote_tool with the tool's id and arguments that match its input schema.
- A model can take minutes. Tell the user it is running on the colleague's computer.
- If the computer is offline, say so plainly: the colleague's computer must be on and sharing. Do not substitute a different tool silently.
- If a call reports that it may already have run, do not repeat it automatically; ask the user.
- Results come from the colleague's model or data; mention that when you report them.
Leaving
The user can leave a shared computer on https://connect.aiscientist.tools/remote-servers: its card has Stop using. The owner can also turn the code off at any time.
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 · 42 lines · 102 tokens per session scan A af3a6ec5991d
tooluniverse-use-shared-computer is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 102 tokens to every session and 591 once invoked, about $0.0004 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.