This record as markdown: /tools/keeveeg-godot-mcp/open-scene.md
What open_scene does on Godot
AI agents invoke open_scene 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 |
|---|---|---|---|
path | string | Yes | Scene file path to open |
Parameters from the server's own tool schema.
Why open_scene is rated High
Opening a scene in a Godot editor triggers an external operation in the running editor environment. It's not a pure read (it changes editor state) and not a write to data files, so Execute best fits — it invokes an editor action whose side effects depend on which scene is specified.
From the tool's definition "Open a scene file in the editor" — triggers an editor action/operation rather than just reading data
Risk signalsAccepts file system path (path)
Attacks that exploit this kind of access
The rule that runs open_scene 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 open_scene, this is the rule to start with:
open_scene 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 open_scene call is checked against it from then on.
Questions about open_scene
Open a scene file in the editor. 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.
open_scene accepts 1 parameter: path. Required: path. 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 open_scene: 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.
open_scene 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 open_scene 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 open_scene. 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.
open_scene is provided by the Godot MCP server (@keeveeg/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