npm_run_script · NPM MCP Server MCP: Risk & Policy

WHAT IT DOES

What npm_run_script does on NPM MCP Server

AI agents invoke npm_run_script to trigger actions in NPM 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 npm_run_script needs a policy

This tool triggers execution of user-defined scripts from package.json, which can run arbitrary shell commands and external processes. While the scripts themselves are pre-defined in the project, an AI agent with access to this tool could execute malicious scripts or scripts with unintended side effects.

From the tool's definition Tool name 'npm_run_script' combined with description 'Ejecutar un script definido en package.json' (Execute a script defined in package.json) directly indicates execution of arbitrary scripts.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

npm_run_script Rate-limited

npm_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": {
    "npm_run_script": {
      "limits": [
        {
          "counter": "npm_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 NPM MCP Server, so you can run agents against it safely.

FAQ

Questions about npm_run_script

What does the npm_run_script tool do? +

Ejecutar un script definido en package.json. It is categorised as a Execute tool in the NPM 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 npm_run_script? +

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

What risk level is npm_run_script? +

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

Can I rate-limit npm_run_script? +

Yes. Add a rate_limit block to the npm_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 npm_run_script completely? +

Set action: deny in the PolicyLayer policy for npm_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 npm_run_script? +

npm_run_script is provided by the NPM MCP Server MCP server (kpangaa/npm-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.