editor_run_python

THE RISK

High Risk

This tool allows execution of arbitrary Python code within the Unreal Editor, giving an AI agent the ability to run any script, modify engine state, invoke editor commands, and perform complex operations. The unconstrained nature ('any python') and the context of running within Unreal Editor—which has deep access to project assets, scene manipulation, and external system calls—makes this critically severe.

From the tool's definition Tool is named 'editor_run_python' and the description explicitly states 'Execute any python within the Unreal Editor.' This enables arbitrary code execution in a powerful game engine environment.

Documented attack patterns abuse exactly the kind of access editor_run_python gives an agent:

HOW TO CONTROL EDITOR_RUN_PYTHON

PolicyLayer is an MCP gateway — it sits between your AI agents and Unreal, and nothing reaches the server without passing your rules. This is the rule we recommend for editor_run_python:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "editor_run_python": {
      "limits": [
        {
          "counter": "editor_run_python_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

editor_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.

Create a free account and register Unreal — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

More Unreal tools

Destructive editor_delete_object Delete an object/actor from the world\n\nExample output: { Execute editor_console_command Run a console command in Unreal\n\nExample output: (No output for most commands, executed Execute editor_move_camera Move the viewport camera to a specific location and rotation for positioning screenshots Write editor_create_object Create a new object/actor in the world\n\nExample output: { Write editor_update_object Update an existing object/actor in the world\n\nExample output: { Write set_unreal_engine_path Set the Unreal Engine path Write set_unreal_project_path Set the Project path Read editor_get_asset_info Get information about an asset, including LOD levels for StaticMesh and SkeletalMesh asset

All 20 Unreal tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in Unreal → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the editor_run_python tool do? +

Execute any python within the Unreal Editor. All python must have. It is categorised as a Execute tool in the Unreal MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on editor_run_python? +

Register the Unreal MCP server in PolicyLayer and add a rule for editor_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 Unreal. Nothing to install.

What risk level is editor_run_python? +

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

Can I rate-limit editor_run_python? +

Yes. Add a rate_limit block to the editor_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 editor_run_python completely? +

Set action: deny in the PolicyLayer policy for editor_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 editor_run_python? +

editor_run_python is provided by the Unreal MCP server (runreal/unreal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Unreal tool call.

Deterministic rules across all 20 Unreal tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN UNREAL →

Free to start. No card required.

20 Unreal tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT EDITOR_RUN_PYTHON ON UNREAL DOES

// THE RISK

// HOW TO CONTROL EDITOR_RUN_PYTHON

// EXPLORE