AI agents call get_dev_status to retrieve information from Npm Dev without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the current state of development processes without creating, modifying, deleting, or executing anything. It is a passive monitoring/diagnostic operation that returns information. Even in a dev server management context, status checking alone carries minimal risk - it cannot misconfigure systems or trigger unintended operations.
From the tool's definition Tool description translates to 'check the status of npm run dev process' - a purely informational query operation with no modifications or side effects.
Attacks that exploit this kind of access
npm run devプロセスの状態確認. It is categorised as a Read tool in the Npm Dev MCP Server, which means it retrieves data without modifying state.
Register the Npm Dev MCP server in PolicyLayer and add a rule for get_dev_status: 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.
get_dev_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_dev_status 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 get_dev_status. 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.
get_dev_status 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.
get_dev_status 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 →