sandbox_exec · Node Code Sandbox MCP: Risk & Policy

WHAT IT DOES

What sandbox_exec does on Node Code Sandbox MCP

AI agents invoke sandbox_exec to trigger actions in Node Code Sandbox MCP. 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_exec needs a policy

This tool allows arbitrary shell command execution within a sandbox. While the sandbox provides some containment, shell commands can perform a wide range of operations including reading sensitive files, modifying data, spawning processes, and accessing network resources. An AI agent with access to this tool could be misdirected to execute harmful commands.

From the tool's definition Tool description states it 'Execute[s] one or more shell commands inside a running sandbox container.' The word 'Execute' combined with 'shell commands' directly matches the Execute category definition: 'runs code, shell commands, browser actions, or triggers…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sandbox_exec Rate-limited

sandbox_exec 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_exec": {
      "limits": [
        {
          "counter": "sandbox_exec_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 Node Code Sandbox MCP, so you can run agents against it safely.

FAQ

Questions about sandbox_exec

What does the sandbox_exec tool do? +

Execute one or more shell commands inside a running sandbox container. Requires a sandbox initialized beforehand. It is categorised as a Execute tool in the Node Code Sandbox MCP 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_exec? +

Register the Node Code Sandbox MCP server in PolicyLayer and add a rule for sandbox_exec: 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 Node Code Sandbox MCP. Nothing to install.

What risk level is sandbox_exec? +

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

Can I rate-limit sandbox_exec? +

Yes. Add a rate_limit block to the sandbox_exec 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_exec completely? +

Set action: deny in the PolicyLayer policy for sandbox_exec. 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_exec? +

sandbox_exec is provided by the Node Code Sandbox MCP server (mozicim/node-code-sandbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.