monty_transform_file

What monty_transform_file does on CoWork OS

AI agents invoke monty_transform_file to trigger actions in CoWork OS. 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 monty_transform_file is rated High

Although the tool reads input and writes output (which could suggest Write), the critical phrase is 'run a named workspace transform.' This indicates execution of user-defined or system-defined transforms whose actual behavior is opaque and argument-dependent. This meets the Execute category: code/operations triggered by arguments whose effects cannot be fully predicted without knowing the transform implementation.

From the tool's definition The tool 'run[s] a named workspace transform' on file content and 'write[s] the result to an output file.' This executes arbitrary transformations—which may include code execution, script processing, or other operations—whose side effects depend on what…

The rule that runs monty_transform_file safely

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

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

Questions about monty_transform_file