terminate_sandbox · MCP4Modal Sandbox MCP: Risk & Policy

WHAT IT DOES

What terminate_sandbox does on MCP4Modal Sandbox

AI agents use terminate_sandbox to create or update resources in MCP4Modal Sandbox — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP4Modal Sandbox environment.

WHY IT NEEDS A POLICY

Why terminate_sandbox needs a policy

An AI agent can call terminate_sandbox faster than any human can review — one bad instruction and it creates or modifies resources in MCP4Modal Sandbox by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

terminate_sandbox Rate-limited

terminate_sandbox stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "terminate_sandbox": {
      "limits": [
        {
          "counter": "terminate_sandbox_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP4Modal Sandbox, so you can run agents against it safely.

FAQ

Questions about terminate_sandbox

What does the terminate_sandbox tool do? +

terminate_sandbox. It is categorised as a Write tool in the MCP4Modal Sandbox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on terminate_sandbox? +

Register the MCP4Modal Sandbox MCP server in PolicyLayer and add a rule for terminate_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 MCP4Modal Sandbox. Nothing to install.

What risk level is terminate_sandbox? +

terminate_sandbox is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit terminate_sandbox? +

Yes. Add a rate_limit block to the terminate_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 terminate_sandbox completely? +

Set action: deny in the PolicyLayer policy for terminate_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 terminate_sandbox? +

terminate_sandbox is provided by the MCP4Modal Sandbox MCP server (milkymap/mcp4modal_sandbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.