cat

What cat does on Claude C2

AI agents call cat to retrieve information from Claude C2 without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why cat is rated Low

This tool retrieves and displays file contents without modifying, deleting, or executing anything. It has no side effects beyond querying data, fitting the 'Read' category. Severity is low as file reading alone presents minimal risk unless the system contains highly sensitive data, but the tool itself is non-destructive. The description is clear and directly indicates its purpose.

From the tool's definition Tool name is 'cat' with description 'Read file contents. Auto-selects client.' The verb 'Read' and lack of modification/deletion/execution semantics clearly indicate a read-only data retrieval operation.

The rule that runs cat safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Claude C2, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cat, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cat": {}
  }
}

Questions about cat