exec_code · Code Box MCP: Risk & Policy

WHAT IT DOES

What exec_code does on Code Box

AI agents invoke exec_code to trigger actions in Code Box. 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 exec_code needs a policy

The tool name 'exec_code' strongly implies arbitrary code execution (Python/JavaScript per server description). The server is explicitly described as a 'stateful code execution' environment. Arbitrary code execution carries critical blast radius as a misused agent could run destructive, data-exfiltrating, or system-compromising code.

From the tool's definition Tool name 'exec_code' on a server described as 'providing stateful code execution (Python/JavaScript)'; sibling tools include 'exec_sql', 'upload_file', 'destroy_session' confirming execution context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

exec_code Rate-limited

exec_code 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": {
    "exec_code": {
      "limits": [
        {
          "counter": "exec_code_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 Code Box, so you can run agents against it safely.

FAQ

Questions about exec_code

What does the exec_code tool do? +

exec_code. It is categorised as a Execute tool in the Code Box MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on exec_code? +

Register the Code Box MCP server in PolicyLayer and add a rule for exec_code: 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 Code Box. Nothing to install.

What risk level is exec_code? +

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

Can I rate-limit exec_code? +

Yes. Add a rate_limit block to the exec_code 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 exec_code completely? +

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

exec_code is provided by the Code Box MCP server (madhanmohanreddy2301/codeboxmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.