ckg-nvidia-guardrails

NeMo Guardrails as a traversable knowledge graph.

50 nodes · MCP-native · free · Graphify.md

pip install ckg-nvidia-guardrails
uvx ckg-nvidia-guardrails

The problem this solves

NeMo Guardrails rails govern conversation flow — but the tool fleet executes entirely outside the railed channel. There is no mutual visibility between config.yml rails configuration and tool/action bindings.

This means:

• Auto-approved shell-capable tools bypass guardrails entirely
• Outgoing responses from tool calls leave un-railed
• Rails config and tool config exist as separate files with no declared relationship

This knowledge graph maps those relationships explicitly. Query the Tool Authorization Gap node to traverse what's railed vs what isn't:

query_ckg('Tool Authorization Gap', 'nvidia-guardrails', 3)

What's covered (50 nodes)

MCP tools

Add to Claude Desktop

{
  "mcpServers": {
    "nvidia-guardrails": {
      "command": "uvx",
      "args": ["ckg-nvidia-guardrails"]
    }
  }
}

Benchmark

11× fewer tokens than RAG · F1 0.471 vs RAG 0.123 · 269 tokens/query vs 2,982

Full paper: github.com/Yarmoluk/ckg-benchmark/blob/main/paper/main.pdf

EVAL

benchmark: ckg-benchmark v0.6.2
dataset: huggingface.co/datasets/danyarm/ckg-benchmark
benchmarked: false
rag_baseline_f1: 0.123
graphrag_baseline_f1: 0.120
mean_tokens: 269
paper: github.com/Yarmoluk/ckg-benchmark/blob/main/paper/main.pdf

Built by Graphify.md · MIT License · Patent pending