editor_run_gdscript
Execute arbitrary GDScript code in editor context.
This record as markdown: /tools/yanhuifair-godot-mcp/editor-run-gdscript.md
What editor_run_gdscript does on Godot
AI agents invoke editor_run_gdscript to trigger actions in Godot. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
code | string | Yes | GDScript code to execute in editor context |
Parameters from the server's own tool schema.
Why editor_run_gdscript is rated High
This tool allows unrestricted execution of GDScript (Godot's scripting language) within the editor context. While GDScript execution in Godot is generally constrained by the engine's sandbox, 'arbitrary' code execution in an editor context can access scene graphs, project files, and editor state.
From the tool's definition 'Execute arbitrary GDScript code in editor context' — the tool explicitly permits running arbitrary code in the editor's runtime environment.
Risk signalsAccepts freeform code/query input (code)
Attacks that exploit this kind of access
The rule that runs editor_run_gdscript safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Godot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For editor_run_gdscript, this is the rule to start with:
editor_run_gdscript 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Godot, apply this rule, and every editor_run_gdscript call is checked against it from then on.
Questions about editor_run_gdscript
Execute arbitrary GDScript code in editor context. It is categorised as a Execute tool in the Godot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
editor_run_gdscript accepts 1 parameter: code. Required: code. The full parameter table on this page comes from the server's own tool schema.
Register the Godot MCP server in PolicyLayer and add a rule for editor_run_gdscript: 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 Godot. Nothing to install.
editor_run_gdscript is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the editor_run_gdscript 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.
Set action: deny in the PolicyLayer policy for editor_run_gdscript. 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.
editor_run_gdscript is provided by the Godot MCP server (@yanhuifair/godot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Godot, and thousands of servers like it.
Across the catalogue