monty_run_transform

Run a named workspace transform from .cowork/transforms/<name>.monty. The input object is available as

SERVERCoWork OS SOURCECoWork-OS/CoWork-OS

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/cowork-os/monty-run-transform.md

WHAT IT DOES

What monty_run_transform does on CoWork OS

AI agents invoke monty_run_transform 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.

RISK

Why monty_run_transform is rated High

This tool triggers execution of transforms (likely scripts or programs) stored in the workspace configuration directory. Even though the transforms are pre-defined files rather than arbitrary user code, the tool still executes external operations whose effects depend on the transform's implementation and the provided input object.

From the tool's definition Tool name includes 'run' and description states it executes 'a named workspace transform from .cowork/transforms/<name>.monty' with input available to the transform, indicating code execution capability.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs monty_run_transform 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_run_transform, this is the rule to start with:

monty_run_transform Rate-limited

monty_run_transform stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every monty_run_transform call is checked against it from then on.

FAQ

Questions about monty_run_transform

What does the monty_run_transform tool do? +

Run a named workspace transform from .cowork/transforms/<name>.monty. The input object is available as. It is categorised as a Execute tool in the CoWork OS MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on monty_run_transform? +

Register the CoWork OS MCP server in PolicyLayer and add a rule for monty_run_transform: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches CoWork OS. Nothing to install.

What risk level is monty_run_transform? +

monty_run_transform is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit monty_run_transform? +

Yes. Add a rate_limit block to the monty_run_transform rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block monty_run_transform completely? +

Set action: deny in the PolicyLayer policy for monty_run_transform. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides monty_run_transform? +

monty_run_transform is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on CoWork OS, and thousands of servers like it.

This server

All 342 CoWork OS tools → High-risk tools on this server →

Across the catalogue

shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →