sandbox_create · Promethean OS MCP: Risk & Policy

WHAT IT DOES

What sandbox_create does on Promethean OS MCP

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

WHY IT NEEDS A POLICY

Why sandbox_create needs a policy

This tool creates a new git worktree, which is a reversible modification to the repository state. It does not execute arbitrary code (Execute), delete data (Destructive), or move money (Financial). While worktrees can be used as a basis for further operations, the tool itself only creates the sandbox structure.

From the tool's definition Tool name 'sandbox_create' and description indicate it 'Create[s] a git worktree-based sandbox'. Creating a new worktree is a write operation that modifies the repository structure by adding a new working directory.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sandbox_create Rate-limited

sandbox_create 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": {
    "sandbox_create": {
      "limits": [
        {
          "counter": "sandbox_create_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 Promethean OS MCP, so you can run agents against it safely.

FAQ

Questions about sandbox_create

What does the sandbox_create tool do? +

Create a git worktree-based sandbox rooted under .sandboxes/<id>. It is categorised as a Write tool in the Promethean OS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sandbox_create? +

Register the Promethean OS MCP server in PolicyLayer and add a rule for sandbox_create: 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 Promethean OS MCP. Nothing to install.

What risk level is sandbox_create? +

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

Can I rate-limit sandbox_create? +

Yes. Add a rate_limit block to the sandbox_create 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_create completely? +

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

sandbox_create is provided by the Promethean OS MCP server (octave-commons/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.