monty_run

Run deterministic, sandboxed Python-subset code (Monty) for fast local computation and post-processing.

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.md

WHAT IT DOES

What monty_run does on CoWork OS

AI agents invoke monty_run 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 is rated High

Code execution tools are classified as Execute because they trigger external operations (code evaluation) whose side effects depend on the arguments provided. Although this tool has mitigations (sandboxing, Python subset), it still permits running code that could inadvertently access file systems, make network calls if permitted by the sandbox, or perform unwanted computations.

From the tool's definition 'Run deterministic, sandboxed Python-subset code' indicates the tool executes code. While sandboxing and the 'Python-subset' constraint limit scope, the capability to execute arbitrary code is fundamentally an Execute operation.

Attacks that exploit this kind of access

RECOMMENDED RULE

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

monty_run Rate-limited

monty_run 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": {
      "limits": [
        {
          "counter": "monty_run_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 call is checked against it from then on.

FAQ

Questions about monty_run

What does the monty_run tool do? +

Run deterministic, sandboxed Python-subset code (Monty) for fast local computation and post-processing. 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? +

Register the CoWork OS MCP server in PolicyLayer and add a rule for monty_run: 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? +

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

Can I rate-limit monty_run? +

Yes. Add a rate_limit block to the monty_run 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 completely? +

Set action: deny in the PolicyLayer policy for monty_run. 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? +

monty_run 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 →