sandbox_execute · MCP Multi-Language Sandbox MCP

WHAT IT DOES

What sandbox_execute does on MCP Multi-Language Sandbox

AI agents invoke sandbox_execute 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_execute needs a policy

This tool directly executes arbitrary code in a sandboxed environment. While Docker isolation provides some containment, code execution is inherently an Execute category action whose effects depend entirely on the code supplied as arguments. An AI agent could execute malicious scripts, exfiltrate data, consume resources, or trigger unintended side effects.

From the tool's definition Tool description states 'Execute code in an isolated sandbox' across six programming languages (Python, TypeScript, JavaScript, Go, Rust, Bash).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sandbox_execute Rate-limited

sandbox_execute 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_execute": {
      "limits": [
        {
          "counter": "sandbox_execute_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_execute

What does the sandbox_execute tool do? +

Execute code in an isolated sandbox. Supports Python, TypeScript, JavaScript, Go, Rust, and Bash. 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_execute? +

Register the MCP Multi-Language Sandbox MCP server in PolicyLayer and add a rule for sandbox_execute: 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_execute? +

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

Can I rate-limit sandbox_execute? +

Yes. Add a rate_limit block to the sandbox_execute 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_execute completely? +

Set action: deny in the PolicyLayer policy for sandbox_execute. 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_execute? +

sandbox_execute 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.