run_editor_python

THE RISK

High Risk

Why run_editor_python needs a policy

The tool runs Python code in the editor, which can trigger external operations, modify engine state, and interact with the project and build system. While the description is empty (lowering confidence slightly), the name combined with the server's purpose (O3DE automation) and sibling tools clearly indicate this executes code whose effects depend on the Python arguments provided.

From the tool's definition Tool name 'run_editor_python' indicates execution of Python code within the O3DE editor context. The sibling tools include destructive operations (delete_entity, disable_gem) and create/modify operations (add_component, create_entity), suggesting this server…

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

POLICY

How to control run_editor_python

PolicyLayer is an MCP gateway — it sits between your AI agents and O3de, and nothing reaches the server without passing your rules. This is the rule we recommend for run_editor_python:

policy.json

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

run_editor_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 O3de — 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

Related tools and policies

More O3de tools

Destructive delete_entity Delete an entity from the current O3DE level. Execute build_project Build an O3DE project using CMake. Execute load_level Open a level in the O3DE Editor. Execute enter_game_mode Enter game mode (play-in-editor) in the O3DE Editor. Execute exit_game_mode Exit game mode and return to edit mode. Write add_component Add a component to an entity. Write create_entity Create a new entity in the current O3DE level. Write create_gem Create a new O3DE gem.

All 30 O3de tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in O3de → 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.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run_editor_python

What does the run_editor_python tool do? +

run_editor_python. It is categorised as a Execute tool in the O3de 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_editor_python? +

Register the O3de MCP server in PolicyLayer and add a rule for run_editor_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 O3de. Nothing to install.

What risk level is run_editor_python? +

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

Can I rate-limit run_editor_python? +

Yes. Add a rate_limit block to the run_editor_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_editor_python completely? +

Set action: deny in the PolicyLayer policy for run_editor_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_editor_python? +

run_editor_python is provided by the O3de MCP server (nickschuetz/o3de-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every O3de tool call.

Start from O3de, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →