Low Risk

sandbox_fs_stat

Get file or directory metadata (kind, size, mode, modified time) inside the sandbox.

How to control sandbox_fs_stat ↓

What sandbox_fs_stat does on Microsandbox

AI agents call sandbox_fs_stat to retrieve information from Microsandbox without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why sandbox_fs_stat needs a policy

This tool queries and returns metadata about files and directories without altering, executing, or deleting anything. It is purely informational, making it a Read category tool with low severity. The metadata returned (size, mode, timestamps) could inform decisions about other operations, but the tool itself has no side effects. Confidence is high because the description is clear and unambiguous.

From the tool's definition Tool description states it 'Get[s] file or directory metadata (kind, size, mode, modified time)' — a retrieval operation with no modification or execution capability.

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

How to control sandbox_fs_stat

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_fs_stat:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "sandbox_fs_stat": {}
  }
}

sandbox_fs_stat is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Microsandbox — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about sandbox_fs_stat

What does the sandbox_fs_stat tool do? +

Get file or directory metadata (kind, size, mode, modified time) inside the sandbox. It is categorised as a Read tool in the Microsandbox MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on sandbox_fs_stat? +

Register the Microsandbox MCP server in PolicyLayer and add a rule for sandbox_fs_stat: 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_fs_stat? +

sandbox_fs_stat is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit sandbox_fs_stat? +

Yes. Add a rate_limit block to the sandbox_fs_stat 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_fs_stat completely? +

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

sandbox_fs_stat 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.

Free to start. No card required.

19 Microsandbox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.