sandbox_remove

THE RISK

Critical Risk

Why sandbox_remove needs a policy

This tool permanently deletes a sandbox environment. Even though the sandbox itself is ephemeral/temporary infrastructure, the removal action is irreversible and represents data destruction. The force parameter indicates the ability to bypass safety checks (requiring the sandbox to be stopped first), increasing blast radius if misused by an agent.

From the tool's definition 'Remove a sandbox' – the tool deletes a sandbox instance, which is an irreversible operation that destroys the sandbox and any associated state.

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

POLICY

How to control sandbox_remove

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

policy.json

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

sandbox_remove 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 Microsandbox — 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 Microsandbox tools

Destructive sandbox_fs_remove Remove a file or directory inside the sandbox. Destructive volume_remove Remove a named volume. Execute sandbox_run Create an ephemeral sandbox, run a shell command, return the output, and destroy the sandb Execute sandbox_exec Execute a command inside a running sandbox and return stdout/stderr/exit code. Execute sandbox_shell Execute a shell command or script string inside a running sandbox. Execute sandbox_stop Stop a running sandbox. Use force to kill with SIGKILL instead of graceful SIGTERM. Execute sandbox_create Create and boot a persistent named sandbox with full configuration. Write sandbox_fs_mkdir Create a directory with parent directories inside the sandbox.

All 19 Microsandbox 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 Microsandbox → 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 sandbox_remove

What does the sandbox_remove tool do? +

Remove a sandbox. Must be stopped unless force is true. It is categorised as a Destructive tool in the Microsandbox 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 sandbox_remove? +

Register the Microsandbox MCP server in PolicyLayer and add a rule for sandbox_remove: 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 Microsandbox. Nothing to install.

What risk level is sandbox_remove? +

sandbox_remove 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 sandbox_remove? +

Yes. Add a rate_limit block to the sandbox_remove 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_remove completely? +

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

sandbox_remove is provided by the Microsandbox MCP server (superradcompany/microsandbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Microsandbox tool call.

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

CHECK YOUR STACK →