run_python_code · MCP Python Interpreter MCP: Risk & Policy

WHAT IT DOES

What run_python_code does on MCP Python Interpreter

AI agents invoke run_python_code to trigger actions in MCP Python Interpreter. 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 run_python_code needs a policy

Executing arbitrary Python code is a high-impact operation that can read/modify/delete files, make network requests, spawn processes, access system resources, or interact with external services. The blast radius is critical because code execution is fundamentally unrestricted unless sandboxed. Tool description is empty, but the name and server context make the function unambiguous.

From the tool's definition Tool name 'run_python_code' and server description states it 'Enables LLMs to interact with Python environments, execute code'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_python_code Rate-limited

run_python_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": {
    "run_python_code": {
      "limits": [
        {
          "counter": "run_python_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 MCP Python Interpreter, so you can run agents against it safely.

FAQ

Questions about run_python_code

What does the run_python_code tool do? +

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

How do I enforce a policy on run_python_code? +

Register the MCP Python Interpreter MCP server in PolicyLayer and add a rule for run_python_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 MCP Python Interpreter. Nothing to install.

What risk level is run_python_code? +

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

Can I rate-limit run_python_code? +

Yes. Add a rate_limit block to the run_python_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 run_python_code completely? +

Set action: deny in the PolicyLayer policy for run_python_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 run_python_code? +

run_python_code is provided by the MCP Python Interpreter MCP server (luutuankiet/mcp-python-interpreter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.