exit_container

THE RISK

Critical Risk

Why exit_container needs a policy

Exiting and cleaning up a container terminates the running environment and disposes of its state. This action cannot be undone; any unsaved data or state within the container is lost. The blast radius is high because an AI agent misusing this tool could destroy an active development environment and all in-memory work, though persistent volumes may survive depending on implementation.

From the tool's definition 'closes a container to cleanup environment when finished' — closing/cleaning up a container is an irreversible teardown of the running environment

Documented attack patterns abuse exactly the kind of access exit_container gives an agent:

POLICY

How to control exit_container

PolicyLayer is an MCP gateway — it sits between your AI agents and Sandbox MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for exit_container:

policy.json

{
  "version": "1",
  "default": "deny",
  "hide": [
    "exit_container"
  ]
}

exit_container disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

Create a free account and register Sandbox MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RESTRICT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Sandbox MCP Server tools

Execute execute_command_in_container Runs commands in a container Execute create_container_environment Creates a new Docker container with specified image Write create_file_in_container Creates a file in a container Write export_dockerfile exports a docker file to create a persistant environment Write save_container_state Saves the container state to a persistent container

All 6 Sandbox MCP Server tools →

Destructive tools on other servers

Android Forensics ADB MCP Server create_full_backup 0xarchive web3_revoke_key Frida Game Hacking MCP clear_scan cPanel MCP Server clear_spam_box

Go deeper

Critical-risk tools in Sandbox MCP Server → Every critical-risk tool this server exposes, in one view.
All critical-risk MCP tools → Every critical-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Blast radius → How much damage one compromised or confused agent can do — and how to bound it.
Tool call approval → Approval gates on individual tool calls: auto-allow, prompt, or deny.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about exit_container

What does the exit_container tool do? +

closes a container to cleanup environment when finished. It is categorised as a Destructive tool in the Sandbox MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on exit_container? +

Register the Sandbox MCP Server MCP server in PolicyLayer and add a rule for exit_container: 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 Sandbox MCP Server. Nothing to install.

What risk level is exit_container? +

exit_container is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit exit_container? +

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

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

exit_container is provided by the Sandbox MCP Server MCP server (tsuchijo/sandbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Sandbox MCP Server tool call.

Start from Sandbox MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →