Skillget

toxmcp

mcp
Security Audit
Pass
Health Pass
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 15 GitHub stars
Code Pass
  • Code scan — Scanned 1 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This umbrella project delivers guardrailed, auditable agentic workflows for computational toxicology. It acts as a central hub connecting to multiple external scientific APIs and databases, such as the EPA CompTox API and ADMETlab.

Security Assessment
The overall risk is Low. The code scan did not find any dangerous patterns, hardcoded secrets, or requests for dangerous local permissions. The tool does not natively execute arbitrary shell commands. However, it does rely heavily on making network requests to third-party scientific databases and requires an external API key (CTX_API_KEY) for certain modules. As an umbrella repository, it links out to separate, distinct modules, meaning your overall security also depends on the individual code within those specific sub-repositories.

Quality Assessment
The project appears to be actively maintained, with repository activity as recent as today. It is well-documented, includes a clear architectural outline, and has an academic preprint available. The repository uses the standard Apache-2.0 license and shows early but positive signs of community trust with 15 GitHub stars.

Verdict
Safe to use, though developers should audit the individual sub-module repositories and be mindful of securing their required API keys.
SUMMARY

Umbrella repo for the ToxMCP Suite (docs, links, quickstart).

README.md

Release
DOI
License
MCP

ToxMCP Suite

ToxMCP is a suite of guardrailed, auditable agentic workflows for computational toxicology delivered through the Model Context Protocol (MCP).

Architecture

ToxMCP architecture

Getting started

  1. Pick a module below (CompTox is the recommended first run today).
  2. Follow that repo’s Quickstart TL;DR.
  3. Verify with the Verification (smoke test) curl snippet.

Default ports (examples)

What is MCP?

MCP (Model Context Protocol) is a standard way for LLM clients/orchestrators to call external tools over a structured interface.
See the official MCP docs/spec: https://modelcontextprotocol.io/

Modules

Module What it covers Upstream dependency Requirements Status Repo
CompTox MCP Identity, hazard, exposure EPA CompTox API API key required (CTX_API_KEY) Available now Repo
ADMETlab MCP Rapid ADMET prediction + utilities ADMETlab 3.0 API No key by default (upstream may rate-limit) Available now Repo
AOP MCP Mechanistic pathways + authoring workflows AOP-Wiki / AOP-DB / federation Internet access recommended Available now Repo
O-QT MCP OECD QSAR Toolbox workflows + reports OECD QSAR Toolbox WebAPI Requires QSAR Toolbox WebAPI access Available now Repo
PBPK MCP PBPK simulation control + PK analytics Open Systems Pharmacology Suite Local engine setup (see repo) Available now Repo
Direct-Use Exposure MCP Coming soon Coming soon Coming soon Coming soon Repo
Dietary Exposure MCP Coming soon Coming soon Coming soon Coming soon Repo
Environmental Fate MCP Coming soon Coming soon Coming soon Coming soon Repo
Bioactivity-PoD MCP Coming soon Coming soon Coming soon Coming soon Repo

Which one should I try first?

  • Start with CompTox MCP if you want the best first-run experience and the most
    recognizable toxicology dataset integration today.
  • Then add AOP MCP, O-QT MCP, or PBPK MCP depending on whether you want
    mechanistic context, QSAR Toolbox automation, or PK workflows next.

Exposure-side stack expansion is in progress. The new module repos are linked above early so
you can follow them, while setup details for the Coming soon entries will land in those
repos directly as each module is published.

Docs

Start here: docs/README.md

Notes

  • Each MCP server is versioned and released independently.
  • Some modules depend on proprietary or rate-limited upstream services—check each module README for exact setup.

Acknowledgements / Origins

ToxMCP was developed in the context of the VHP4Safety project (see: https://github.com/VHP4Safety) and related research/engineering efforts.

Funding: Dutch Research Council (NWO) — NWA.1292.19.272 (NWA programme)

This suite integrates with third-party data sources and services (e.g., EPA CompTox, ADMETlab, AOP resources, OECD QSAR Toolbox, Open Systems Pharmacology). Those upstream resources are owned and governed by their respective providers; users are responsible for meeting any access, API key, rate limit, and license/EULA requirements described in each module.

License

Apache-2.0

✅ Citation

Djidrovski, I. ToxMCP: Guardrailed, Auditable Agentic Workflows for Computational Toxicology via the Model Context Protocol. bioRxiv (2026). https://doi.org/10.64898/2026.02.06.703989

@article{djidrovski2026toxmcp,
  title   = {ToxMCP: Guardrailed, Auditable Agentic Workflows for Computational Toxicology via the Model Context Protocol},
  author  = {Djidrovski, Ivo},
  journal = {bioRxiv},
  year    = {2026},
  doi     = {10.64898/2026.02.06.703989},
  url     = {https://doi.org/10.64898/2026.02.06.703989}
}

Citation metadata: CITATION.cff

Contributing

Please see CONTRIBUTING.md. If you’re not sure which repository to use, open an issue here: https://github.com/ToxMCP/toxmcp/issues

Support

See SUPPORT.md.

Reviews (0)

No results found