1. Conduid
  2. AI
  3. Safety Training
MCP server · AI

Safety Training

DPO/SafeDPO/OPAD training + eval for teaching tool-using LLMs to refuse falsely-benign MCP exploits

34Low

Scored a month ago · breakdown

About Safety Training

Safety Training is an MCP server published by johnhalloran321 in the AI category: dPO/SafeDPO/OPAD training + eval for teaching tool-using LLMs to refuse falsely-benign MCP exploits.

The repository has 4 stars and 0 forks, with the last commit 3 months ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/johnhalloran321/mcp_safety_training

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Safety Training

Powered by Claude · Grounded in docs

I know everything about Safety Training. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Releases

v0.1.0v0.1.0 — DPO, SafeDPO, OPAD, RAG-Pref, Vanilla RAG · 8 Jul 2026v0.1.0 — DPO, SafeDPO, OPAD, RAG-Pref Initial public release: training and evaluation code for teaching LLM agents to refuse falsely benign attacks (FBAs)** — CVE-derived Model Context Protocol (MCP) tool-use exploits phrased so ordinarily…
Questions

About Safety Training

How do I install Safety Training?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Safety Training safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Safety Training still maintained?

Yes — the latest release is v0.1.0 (8 Jul 2026), and the last commit was 3 months ago. The repository has 4 stars.