start_dev_server · Npm Dev MCP: Risk & Policy

WHAT IT DOES

What start_dev_server does on Npm Dev

AI agents invoke start_dev_server to trigger actions in Npm Dev. 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 start_dev_server needs a policy

This tool executes npm scripts in the background, which is fundamentally an Execute operation. While not immediately destructive, npm dev scripts can have broad system effects (network calls, file writes, spawning processes). It has high severity because a compromised AI agent could execute malicious scripts if pointed at a malicious package.json.

From the tool's definition Tool description states 'npm run dev をバックグラウンドで開始' (start npm run dev in the background). npm run dev executes arbitrary scripts defined in package.json, which can perform code execution, file I/O, network operations, and other side effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_dev_server Rate-limited

start_dev_server 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": {
    "start_dev_server": {
      "limits": [
        {
          "counter": "start_dev_server_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 Dev, so you can run agents against it safely.

FAQ

Questions about start_dev_server

What does the start_dev_server tool do? +

指定ディレクトリでnpm run devをバックグラウンドで開始. It is categorised as a Execute tool in the Npm Dev MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_dev_server? +

Register the Npm Dev MCP server in PolicyLayer and add a rule for start_dev_server: 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 Dev. Nothing to install.

What risk level is start_dev_server? +

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

Can I rate-limit start_dev_server? +

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

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

start_dev_server is provided by the Npm Dev MCP server (masamunet/npm-dev-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.