node_run · NVM MCP Server MCP: Risk & Policy

WHAT IT DOES

What node_run does on NVM MCP Server

AI agents invoke node_run to trigger actions in NVM MCP Server. 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 node_run needs a policy

This tool executes Node.js code/binaries, which is an Execute operation whose effects depend entirely on what code is passed to it. While not inherently destructive, a compromised agent could use this to run malicious scripts, access file systems, make network requests, or compromise the system. The blast radius is high because node can do nearly anything an AI agent instructs it to do.

From the tool's definition Tool description states it will 'Run the `node` binary' with specified NVM versions. Running arbitrary node code can execute user-supplied scripts, require external modules, and trigger side effects depending on the arguments passed.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

node_run Rate-limited

node_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": {
    "node_run": {
      "limits": [
        {
          "counter": "node_run_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 NVM MCP Server, so you can run agents against it safely.

FAQ

Questions about node_run

What does the node_run tool do? +

Run the node binary with the session-active (or a specified) NVM version. It is categorised as a Execute tool in the NVM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on node_run? +

Register the NVM MCP Server MCP server in PolicyLayer and add a rule for node_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 NVM MCP Server. Nothing to install.

What risk level is node_run? +

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

Can I rate-limit node_run? +

Yes. Add a rate_limit block to the node_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 node_run completely? +

Set action: deny in the PolicyLayer policy for node_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 node_run? +

node_run is provided by the NVM MCP Server MCP server (realjacoblinder/nvm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.