// SCAN REPORT

Npm Dev

9 tools. 5 can modify or destroy data without limits.

5 write tools that can modify data. Rate limits recommended.

Last updated: 4 Jul 2026

5 can modify or destroy data

4 read-only

9 tools total

Community server · catalogue entry verified 04/07/2026

How to control Npm Dev ↓

TOOL MAP

What Npm Dev exposes to your agents

Read (4) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Npm Dev tools

Execute · High restart_dev_server Restarting a development server is an Execute-category action: it triggers an external operation (process restart) whose effects depend on the arguments (which project/port to restart). Execute · High start_dev_server This tool executes npm scripts in the background, which is fundamentally an Execute operation. Execute · High stop_dev_server Stopping a dev server is an executable action that halts an active background process. Execute · High auto_recover This tool executes a multi-step automated recovery workflow (health check → recovery → re-validation) which involves starting/stopping/restarting dev server processes.

5 of Npm Dev's 9 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Npm Dev

PolicyLayer is an MCP gateway — it sits between your AI agents and Npm Dev, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "get_dev_logs": {
    "limits": [
      {
        "counter": "get_dev_logs_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Npm Dev — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON NPM DEV →

Instant setup, no code required.

FULL CATALOGUE

All 9 Npm Dev tools

EXECUTE 5 tools

Execute auto_recover MCPサーバーの自動復旧を実行（ヘルスチェック→復旧→再検証） Execute recover_from_state 保存された状態から復旧を試行 Execute restart_dev_server npm run devプロセス再起動 Execute start_dev_server 指定ディレクトリでnpm run devをバックグラウンドで開始 Execute stop_dev_server npm run devプロセス停止

READ 4 tools

Read get_dev_logs npm run devのログ取得 Read get_dev_status npm run devプロセスの状態確認 Read get_health_status MCPサーバーのヘルス状態を取得 Read scan_project_dirs プロジェクト内のpackage.jsonとdevスクリプトを検索

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Npm Dev

Is the Npm Dev MCP server safe to use without restrictions? +

The Npm Dev server is primarily read-only with 4 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Npm Dev MCP server expose? +

9 tools across 2 categories: Execute, Read. 4 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Npm Dev? +

Register the Npm Dev MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Npm Dev tool call.

Deterministic rules across all 9 Npm Dev tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON NPM DEV →

Instant setup, no code required.

9 Npm Dev tools catalogued and risk-classified — across an index of 43,000+ MCP servers.