AI agents invoke restart_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.
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). While reversible (unlike Destructive), it interrupts running services and can impact dependent systems.
From the tool's definition Tool performs 'npm run dev プロセス再起動' (npm run dev process restart), which restarts a development server—a background process execution that affects running services and their state.
Attacks that exploit this kind of access
npm run devプロセス再起動. 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.
Register the Npm Dev MCP server in PolicyLayer and add a rule for restart_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.
restart_dev_server is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the restart_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.
Set action: deny in the PolicyLayer policy for restart_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.
restart_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.
restart_dev_server is one line of Npm Dev's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →