blender_run_python

THE RISK

High Risk

blender_run_python triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

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

HOW TO CONTROL BLENDER_RUN_PYTHON

PolicyLayer is an MCP gateway — it sits between your AI agents and Gamedev All-in-One MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for blender_run_python:

policy.json

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

blender_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 Gamedev All-in-One MCP — 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 Gamedev All-in-One MCP tools

Destructive blender_delete_object Delete an object from the Blender scene by name. Destructive roblox_delete_instance Delete (Destroy) an instance at the given path in Roblox Studio. Destructive unity_delete_gameobject Delete a GameObject from the Unity scene by path. Destructive unreal_destroy_actor Destroy an actor in the current Unreal level by path. Execute doctor Run local prerequisite checks for the Roblox all-in-one MCP environment. Execute roblox_run_code Send a Luau code execution request through the Studio-side companion runtime boundary. Execute unity_execute_menu_item Execute a Unity Editor menu item by its path (e.g. Execute unreal_run_python Execute a Python script in the Unreal Editor Python environment.

All 78 Gamedev All-in-One MCP 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 Gamedev All-in-One MCP → 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 blender_run_python tool do? +

Execute arbitrary Python code in Blender. It is categorised as a Execute tool in the Gamedev All-in-One MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on blender_run_python? +

Register the Gamedev All-in-One MCP server in PolicyLayer and add a rule for blender_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 Gamedev All-in-One MCP. Nothing to install.

What risk level is blender_run_python? +

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

Can I rate-limit blender_run_python? +

Yes. Add a rate_limit block to the blender_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 blender_run_python completely? +

Set action: deny in the PolicyLayer policy for blender_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 blender_run_python? +

blender_run_python is provided by the Gamedev All-in-One MCP server (sansaks-jpg/gamedev-all-in-one-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Gamedev All-in-One MCP tool call.

Deterministic rules across all 78 Gamedev All-in-One MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN GAMEDEV ALL-IN-ONE →

Free to start. No card required.

78 Gamedev All-in-One MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT BLENDER_RUN_PYTHON ON GAMEDEV ALL-IN-ONE MCP DOES

// THE RISK

// HOW TO CONTROL BLENDER_RUN_PYTHON

// EXPLORE