Skip to content
mcp/harbor
Grok

agent guard for Grok

io.github.ipezygj/agent-guard

Safety checks an agent runs before it acts: package malware, destructive command, secret leak.

client:Grok transport:stdio runtime:pypi

Install agent guard in Grok

.mcp.json (in your project root) 

{
  "mcpServers": {
    "agent-guard": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agent-tripwire"
      ]
    }
  }
}

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 guard in other clients

agent guard MCP server