run_fatcat

What run_fatcat does on Pentester-MCP

AI agents invoke run_fatcat to trigger actions in Pentester-MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Why run_fatcat is rated High

This tool executes an external penetration testing utility (fatcat), which performs reconnaissance and potentially exploitative operations against databases. Execution tools have high severity because their effects depend entirely on user-supplied arguments and attacker intent. While not immediately destructive like DELETE commands, unauthorized execution could enable reconnaissance leading to compromise.

From the tool's definition Tool named 'run_fatcat' on Pentester-MCP server which 'Enables AI assistants to autonomously execute over 200 open-source penetration testing tools'. The 'run_' prefix indicates execution of an external tool.

The rule that runs run_fatcat safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Pentester-MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_fatcat, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_fatcat": {
      "limits": [
        {
          "counter": "run_fatcat_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

Questions about run_fatcat