sandbox_stop · Node Code Sandbox MCP: Risk & Policy

WHAT IT DOES

What sandbox_stop does on Node Code Sandbox MCP

AI agents invoke sandbox_stop to trigger actions in Node Code Sandbox MCP. 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 sandbox_stop needs a policy

While the tool stops a sandbox rather than deleting persistent data, it halts an active execution environment and removes its container—actions with external side effects that cannot be trivially undone. This is Execute rather than Destructive because the sandbox is ephemeral infrastructure, not permanent data deletion.

From the tool's definition Tool terminates and removes a running sandbox container. 'Terminate and remove' indicates irreversible shutdown of an execution environment and cleanup of its state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sandbox_stop Rate-limited

sandbox_stop 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": {
    "sandbox_stop": {
      "limits": [
        {
          "counter": "sandbox_stop_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 Node Code Sandbox MCP, so you can run agents against it safely.

FAQ

Questions about sandbox_stop

What does the sandbox_stop tool do? +

Terminate and remove a running sandbox container. Should be called after finishing work in a sandbox initialized with sandbox_initialize. It is categorised as a Execute tool in the Node Code Sandbox MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sandbox_stop? +

Register the Node Code Sandbox MCP server in PolicyLayer and add a rule for sandbox_stop: 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 Node Code Sandbox MCP. Nothing to install.

What risk level is sandbox_stop? +

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

Can I rate-limit sandbox_stop? +

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

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

sandbox_stop is provided by the Node Code Sandbox MCP server (mozicim/node-code-sandbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.