executePython · SMART-E2B MCP: Risk & Policy

WHAT IT DOES

What executePython does on SMART-E2B

AI agents invoke executePython to trigger actions in SMART-E2B. 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 executePython needs a policy

This tool executes arbitrary Python code, which is inherently an Execute-category risk. Although the sandbox provides isolation (mitigating some risk), the tool can run any Python operations depending on provided arguments—including file operations, network calls, data processing, or side effects determined by the code content.

From the tool's definition Tool name 'executePython' combined with description 'Execute Python code in a secure cloud sandbox' directly indicates code execution capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

executePython Rate-limited

executePython 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": {
    "executePython": {
      "limits": [
        {
          "counter": "executepython_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 SMART-E2B, so you can run agents against it safely.

FAQ

Questions about executePython

What does the executePython tool do? +

Execute Python code in a secure cloud sandbox. It is categorised as a Execute tool in the SMART-E2B MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on executePython? +

Register the SMART-E2B MCP server in PolicyLayer and add a rule for executePython: 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 SMART-E2B. Nothing to install.

What risk level is executePython? +

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

Can I rate-limit executePython? +

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

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

executePython is provided by the SMART-E2B MCP server (leghis/smart-e2b). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.