run_python · Pymol Cursor MCP: Risk & Policy

WHAT IT DOES

What run_python does on Pymol Cursor

AI agents invoke run_python to trigger actions in Pymol Cursor. 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 needs a policy

This tool allows execution of arbitrary Python code within the PyMOL application environment. While PyMOL is a molecular visualization tool with limited scope for harm in isolation, the ability to execute arbitrary Python code is inherently high-risk: an AI agent could run malicious scripts, access the filesystem, modify molecular data structures irreversibly, or cause unexpected side effects.

From the tool's definition Tool description states 'Execute Python code inside PyMOL.' The name 'run_python' combined with the description explicitly indicates arbitrary code execution capabilities.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_python Rate-limited

run_python 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": {
      "limits": [
        {
          "counter": "run_python_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 Pymol Cursor, so you can run agents against it safely.

FAQ

Questions about run_python

What does the run_python tool do? +

Execute Python code inside PyMOL. Returns OK or ERROR: <message> directly. It is categorised as a Execute tool in the Pymol Cursor 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? +

Register the Pymol Cursor MCP server in PolicyLayer and add a rule for run_python: 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 Pymol Cursor. Nothing to install.

What risk level is run_python? +

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

Can I rate-limit run_python? +

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

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

run_python is provided by the Pymol Cursor MCP server (truong128/pymol-cursor-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.