pnpm_run_script · Promethean OS MCP: Risk & Policy

WHAT IT DOES

What pnpm_run_script does on Promethean OS MCP

AI agents invoke pnpm_run_script to trigger actions in Promethean OS 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 IT NEEDS A POLICY

Why pnpm_run_script needs a policy

This is an Execute tool because it triggers external operations (pnpm scripts) whose effects depend entirely on what those scripts contain. While pnpm scripts are typically defined by the project maintainer, an AI agent with access to this tool could invoke scripts with unpredictable side effects—including file modifications, network calls, or system commands.

From the tool's definition Tool name contains 'run' and description states 'Execute a pnpm script'. The pnpm package manager runs arbitrary scripts defined in package.json, which can execute shell commands, install dependencies, build code, or trigger any operation the script author…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pnpm_run_script Rate-limited

pnpm_run_script 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": {
    "pnpm_run_script": {
      "limits": [
        {
          "counter": "pnpm_run_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Promethean OS MCP, so you can run agents against it safely.

FAQ

Questions about pnpm_run_script

What does the pnpm_run_script tool do? +

Execute a pnpm script, optionally filtered to specific workspace packages. It is categorised as a Execute tool in the Promethean OS MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pnpm_run_script? +

Register the Promethean OS MCP server in PolicyLayer and add a rule for pnpm_run_script: 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 Promethean OS MCP. Nothing to install.

What risk level is pnpm_run_script? +

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

Can I rate-limit pnpm_run_script? +

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

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

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