sandbox_session · MCP Multi-Language Sandbox MCP

WHAT IT DOES

What sandbox_session does on MCP Multi-Language Sandbox

AI agents invoke sandbox_session to trigger actions in MCP Multi-Language Sandbox. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why sandbox_session needs a policy

This tool controls persistent sandbox session lifecycle. While 'list' is a Read operation and 'pause/resume' are Execute-level, 'destroy' is potentially Destructive (terminates sessions and any associated state). However, since sessions are containers that can be recreated and the primary purpose is session management rather than permanent data deletion, Execute is the most appropriate category.

From the tool's definition 'Create, list, pause, resume, or destroy persistent sandbox sessions' — manages lifecycle of Docker-isolated execution environments

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sandbox_session Rate-limited

sandbox_session stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_session": {
      "limits": [
        {
          "counter": "sandbox_session_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Multi-Language Sandbox, so you can run agents against it safely.

FAQ

Questions about sandbox_session

What does the sandbox_session tool do? +

Create, list, pause, resume, or destroy persistent sandbox sessions. It is categorised as a Execute tool in the MCP Multi-Language Sandbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on sandbox_session? +

Register the MCP Multi-Language Sandbox MCP server in PolicyLayer and add a rule for sandbox_session: 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 MCP Multi-Language Sandbox. Nothing to install.

What risk level is sandbox_session? +

sandbox_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit sandbox_session? +

Yes. Add a rate_limit block to the sandbox_session 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_session completely? +

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

sandbox_session is provided by the MCP Multi-Language Sandbox MCP server (pit-cl/mcp-multilang-sandbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.