sandbox_teardown

THE RISK

Critical Risk

Why sandbox_teardown needs a policy

While stopping a sandbox is reversible (Execute category), the tool's ability to remove/delete Docker containers crosses into Destructive territory because deletion cannot be undone. An AI agent with misuse could permanently destroy computational environments, data volumes, and research results stored within those sandboxes.

From the tool's definition Tool description explicitly states it can "remove a Docker sandbox" and "delete" when remove parameter is set to true. The term 'delete' combined with the capability to permanently remove containers indicates irreversible data loss potential.

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

POLICY

How to control sandbox_teardown

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

policy.json

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

sandbox_teardown 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 MedSci Agent — 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 MedSci Agent tools

Execute differential_expression Run differential expression analysis between cell groups. Identifies genes that are signif Execute sandbox_run_job Execute a command in an existing Docker sandbox and capture stdout, stderr, exit code, dur Execute cluster_cells Cluster cells in a preprocessed single-cell dataset using Leiden or Louvain community dete Execute preprocess_omics Preprocess a single-cell RNA-seq dataset: filter cells/genes, normalize, log-transform, an Execute sandbox_prepare Create or verify an isolated Docker sandbox for the workspace. Optionally apply a containe Read parse_fasta Parse a FASTA file and return sequence metadata: IDs, names, descriptions, lengths, and se Read acquire_documents Acquire policy-compliant scientific document text from DOI/PMID/PMCID/URL targets with pro Read analyze_medical_image Analyze a medical image (X-ray, CT, pathology slide, dermatology photo) using MedGemma

All 28 MedSci Agent 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 MedSci Agent → 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_teardown

What does the sandbox_teardown tool do? +

Stop or remove a Docker sandbox. By default only stops; set remove to true to also delete. It is categorised as a Destructive tool in the MedSci Agent 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_teardown? +

Register the MedSci Agent MCP server in PolicyLayer and add a rule for sandbox_teardown: 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 MedSci Agent. Nothing to install.

What risk level is sandbox_teardown? +

sandbox_teardown 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_teardown? +

Yes. Add a rate_limit block to the sandbox_teardown 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_teardown completely? +

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

sandbox_teardown is provided by the MedSci Agent MCP server (omar-a-hassan/medsci-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MedSci Agent tool call.

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

CHECK YOUR STACK →