run_mssqlclient

What run_mssqlclient does on Pentester-MCP

AI agents invoke run_mssqlclient 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_mssqlclient is rated High

This tool executes an MSSQL client, which can run arbitrary SQL queries and administrative commands against databases. While not inherently destructive (depends on query arguments), execution tools are classified as Execute. Confidence slightly reduced due to empty tool description, but context as a penetration testing tool and the nature of 'run_' prefix strongly indicates command execution capability.

From the tool's definition Tool named 'run_mssqlclient' with no description, but MCP server is explicitly for executing penetration testing tools. MSSQL client execution permits arbitrary database queries and commands against SQL Server instances.

The rule that runs run_mssqlclient 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_mssqlclient, this is the rule to start with:

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

Questions about run_mssqlclient