recover_from_state · Npm Dev MCP: Risk & Policy

WHAT IT DOES

What recover_from_state does on Npm Dev

AI agents invoke recover_from_state 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 recover_from_state needs a policy

Recovery from saved state implies restarting or re-launching dev server processes based on persisted state, which constitutes triggering external operations (process execution). It doesn't merely read data nor does it irreversibly destroy anything, placing it in Execute. Severity is medium because it can spin up background processes and affect running services, but blast radius is limited to local dev servers.

From the tool's definition recover_from_state — '保存された状態から復旧を試行' (attempt recovery from saved state); sibling tool 'auto_recover' confirms automated recovery/restart operations are performed

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

recover_from_state Rate-limited

recover_from_state 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": {
    "recover_from_state": {
      "limits": [
        {
          "counter": "recover_from_state_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 recover_from_state

What does the recover_from_state tool do? +

保存された状態から復旧を試行. 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 recover_from_state? +

Register the Npm Dev MCP server in PolicyLayer and add a rule for recover_from_state: 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 recover_from_state? +

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

Can I rate-limit recover_from_state? +

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

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

recover_from_state 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.