Skip to content
Grok

agent guardrail for Grok

io.github.rudimentall1/agent-guardrail

Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.

client:Grok transport:stdio runtime:pypi

Install agent guardrail in Grok

.mcp.json (in your project root)

{
  "mcpServers": {
    "agent-guardrail": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "guardrail-mcp"
      ]
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

agent guardrail in other clients