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 setup-boltz-remote-toolgit 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/setup-boltz-remote-tool)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/setup-boltz-remote-tool"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/setup-boltz-remote-tool/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/setup-boltz-remote-tool"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/setup-boltz-remote-tool.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 2 findings, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low MCP Rug Pull · line 35 pip install without ==version installs the latest release, which could include malicious changes.Fix: Pin the version: pip install package==1.2.3
- low MCP Rug Pull · line 117 pip install without ==version installs the latest release, which could include malicious changes.Fix: Pin the version: pip install package==1.2.3
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 | $0.00043 | $0.02312 |
| Opus 5.5 | $0.00017 | $0.00925 |
| Sonnet 5.5 | $0.00009 | $0.00462 |
| Haiku 4.5 | $0.00004 | $0.00231 |
Grade A, and why
setup-boltz-remote-tool scanned grade A with 1 finding 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> curl -fsSL -o ~/.tooluniverse/envs/boltz-tooluniverse.txt https://connect.aiscientist.tools/install-requirements.txt How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up Boltz-2 as a remote tool
Sharing this model for a user, not developing it? Follow the
tooluniverse-share-computerguide; no ToolUniverse source checkout is needed. The model runs in its own Python environment, with its dependencies:~/.local/bin/uv venv --python 3.12 ~/.tooluniverse/envs/boltz curl -fsSL -o ~/.tooluniverse/envs/boltz-tooluniverse.txt https://connect.aiscientist.tools/install-requirements.txt ~/.local/bin/uv pip install --python ~/.tooluniverse/envs/boltz/bin/python -r ~/.tooluniverse/envs/boltz-tooluniverse.txt # then this model's own dependencies, as in "Create an isolated environment" below ~/.local/bin/tu remote check boltz --python ~/.tooluniverse/envs/boltz/bin/python # lists anything still missing ~/.local/bin/tu serve --allow boltz --python ~/.tooluniverse/envs/boltz/bin/python --share --detach --name "<computer name>" --service https://tooluniverse-backend.onrender.comIf the check reports a missing environment variable (a data folder, a model cache, a provider key), set it in the same shell before
tu serve; "Obtain credentials, data, and model weights" below says what each one is. The model reads only the variables it declares.The rest of this guide is for developers working from the ToolUniverse source, and for diagnosing problems with this model.
Validation status (2026-08-16): Boltz 2.2.1 and the official checkpoints ran on the NVIDIA GB10 in one repaired direct MCP call and three authenticated Platform calls, each returning six finite affinity values in 63.6-66.5 seconds. The upstream MSA service timed out during validation, so those successful calls explicitly used bounded single-sequence mode. Missing, oversized, malformed, or non-finite affinity artifacts now fail closed. Public publication, cross-user isolation, broad concurrency, recovery, biological accuracy, and the live MSA path remain unvalidated; keep this deployment private.
Prerequisites
- Run from the ToolUniverse repository root on Linux with Python 3.12.3.
- CUDA GPU strongly recommended; CPU is not a practical production target.
- Keep provider data, weights, caches, and credentials outside Git.
- Bind to loopback. A non-loopback bind requires TOOLUNIVERSE_API_TOKEN; never put it in arguments or results.
What ships with it
1 file 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.
- 6d ago Changed · +15 lines 09a212a79ef3
- 1mo ago First seen · 174 lines · 43 tokens per session scan A 4168b47b8f22
setup-boltz-remote-tool is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,739 stars, last pushed today), licensed Apache-2.0. It adds 43 tokens to every session and 2,312 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
azure-resource-manager-durabletask-dotnet
Azure Resource Manager SDK for Durable Task Scheduler in .NET. Use for MANAGEMENT PLANE operations: creating/managing Durable Task Schedulers, Task Hubs, and retention policies via Azure Resource Manager. Triggers: "Durable Task Scheduler", "create scheduler", "task hub", "DurableTaskSchedulerResource", "provision…
manage-iacm
Manage Harness Infrastructure as Code Management (IaCM) via MCP. Configure Terraform workspaces with remote state and RBAC, set up continuous drift detection with auto-remediation, design multi-tier change approval workflows, and estimate infrastructure costs before deployment. Use when asked to manage Terraform…
check-referenced-statements
Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second. Use when a markdown proof cites statements from external papers.
observability-setup
Sett opp Prometheus-metrikker, OpenTelemetry-tracing og health check-endepunkter for Nais-applikasjoner.
cis-aws-foundations-5.13
Ensure route table changes are monitored.
cis-aws-compute-2.2.4
Ensure unused EBS volumes are removed.