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-antigravity-plugingit 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-antigravity-plugin)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-antigravity-plugin"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-antigravity-plugin/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-antigravity-plugin"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-antigravity-plugin.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 | $0.00230 | $0.01024 |
| Opus 5 | $0.00115 | $0.00512 |
| Sonnet 5 | $0.00046 | $0.00205 |
| Haiku 4.5 | $0.00023 | $0.00102 |
Grade D, and why
tooluniverse-antigravity-plugin scanned grade D with 3 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 11d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
uv --version # provides `uvx`; if missing: curl -LsSf https://astral.sh/uv/install.sh | sh Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Most tools work without keys. For higher rate limits or gated databases, set the keys you care about in `~/.gemini/config/plugins/tooluniverse/mcp_config.json` or pass them in environment variables: Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
uv --version # provides `uvx`; if missing: curl -LsSf https://astral.sh/uv/install.sh | sh How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install the ToolUniverse Plugin for Google Antigravity (AGY)
One-step install on Google Antigravity (AGY / Antigravity IDE / Antigravity 2.0): an MCP server exposing 1000+ scientific tools plus 120+ research skills — all auto-configured.
Prerequisites (check once)
uv --version # provides `uvx`; if missing: curl -LsSf https://astral.sh/uv/install.sh | sh
agy --version # Antigravity CLI; if missing: https://antigravity.google
Install
In Antigravity, plugins can be installed using the agy CLI:
Option 1: Direct path / imported plugin install (recommended)
# If installed via Claude Code / Codex marketplace cache or cloned repo:
agy plugin install /path/to/ToolUniverse/plugin
Option 2: Clone + install
git clone https://github.com/mims-harvard/ToolUniverse.git
cd ToolUniverse
agy plugin install ./plugin
Restart Antigravity. The MCP server auto-starts via uvx tooluniverse on first use (~30 s cold start while the package downloads, instant after).
Verify it worked
agy plugin list
Expect output showing tooluniverse under imports:
{
"imports": [
{
"name": "tooluniverse",
"source": "claude-code",
"components": [
"skills",
"agents",
"mcpServers",
"hooks",
"commands"
]
}
]
}
Inside Antigravity, just ask naturally:
What are the top mutated genes in breast cancer?
Research the drug metformin.
The research skills auto-activate on matching questions, and the MCP tools are discovered and run via find_tools → execute_tool — no command prefix needed.
What you get
| Component | What it does | How it's used |
|---|---|---|
| MCP server | 1000+ tools via find_tools, get_tool_info, execute_tool |
Auto-loaded; no action needed |
| 120+ skills | Structured research workflows (drug discovery, variant interpretation, pharmacovigilance, phylogenetics, statistical modeling, etc.) | Auto-activate on matching questions |
| Research agent | Autonomous multi-database research subagent | Auto-routed on complex research tasks |
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.
- 11d ago First seen · 110 lines · 230 tokens per session scan D 9342c2bae15e
tooluniverse-antigravity-plugin is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,680 stars, last pushed yesterday), licensed Apache-2.0. It adds 230 tokens to every session and 1,024 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it D with 3 findings (downloads and executes remote code, reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.