run_corsy

What run_corsy does on Pentester-MCP

AI agents invoke run_corsy 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_corsy is rated High

CORSY actively scans and tests CORS configurations on target systems—this is an active web exploitation operation with external effects dependent on the target argument. It executes reconnaissance and exploitation logic rather than simply reading data. The empty description lowers confidence slightly, but the server context and tool naming convention are definitive.

From the tool's definition Tool name 'run_corsy' on a penetration testing server described as enabling 'autonomous execution' of 'open-source penetration testing tools' including 'web exploitation.' CORSY is a known CORS misconfiguration scanner that actively probes web services.

The rule that runs run_corsy 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_corsy, this is the rule to start with:

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

Questions about run_corsy