1. Conduid
  2. RAG
  3. LLM Blue Team Guardrail
MCP server · RAG

LLM Blue Team Guardrail

A layered LLM guardrail (fast heuristics + an LLM judge) against prompt injection, with a guarded RAG pipeline that quarantines poisoned documents and an MCP server for AI agents. FastAPI, React/TypeScript, pgvector, Docker. The blue-team counterpart to my Secure AI red-team coursework.

34Low

Scored 6 hours ago · breakdown

About LLM Blue Team Guardrail

LLM Blue Team Guardrail is an MCP server published by daniel-omari in the RAG category: a layered LLM guardrail (fast heuristics + an LLM judge) against prompt injection, with a guarded RAG pipeline that quarantines poisoned documents and an MCP server for AI agents. FastAPI, React/TypeScript, pgvector, Docker. The blue-team counterpart to my Secure AI red-team coursework.

Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/daniel-omari/llm-blue-team-guardrail

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 LLM Blue Team Guardrail

Powered by Claude · Grounded in docs

I know everything about LLM Blue Team Guardrail. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About LLM Blue Team Guardrail

How do I install LLM Blue Team Guardrail?

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

Is LLM Blue Team Guardrail 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 LLM Blue Team Guardrail still maintained?

Yes — the last commit was 2 days ago. The repository has 0 stars and 0 forks.