stop_sandbox · MCP Docker Sandbox Interpreter MCP

WHAT IT DOES

What stop_sandbox does on MCP Docker Sandbox Interpreter

AI agents invoke stop_sandbox to trigger actions in MCP Docker Sandbox Interpreter. 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 stop_sandbox needs a policy

stop_sandbox triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_sandbox Rate-limited

stop_sandbox 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": {
    "stop_sandbox": {
      "limits": [
        {
          "counter": "stop_sandbox_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 MCP Docker Sandbox Interpreter, so you can run agents against it safely.

FAQ

Questions about stop_sandbox

What does the stop_sandbox tool do? +

Stops and removes the currently active Docker container sandbox. It is categorised as a Execute tool in the MCP Docker Sandbox Interpreter MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_sandbox? +

Register the MCP Docker Sandbox Interpreter MCP server in PolicyLayer and add a rule for stop_sandbox: 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 MCP Docker Sandbox Interpreter. Nothing to install.

What risk level is stop_sandbox? +

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

Can I rate-limit stop_sandbox? +

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

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

stop_sandbox is provided by the MCP Docker Sandbox Interpreter MCP server (svngoku/mcp-docker-code-interpreter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.