play_scene
Start playing the current or specified scene. Required before using any runtime tools (get_game_*, capture_frames, etc.)
This record as markdown: /tools/keeveeg-godot-mcp/play-scene.md
What play_scene does on Godot
AI agents invoke play_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 |
|---|---|---|---|
mode | string | — | Play mode: 'main' (main scene), 'current' (open scene), or 'custom' (specified by scene_path) |
scene_path | string | — | Scene to play when mode is 'custom' |
Parameters from the server's own tool schema.
Why play_scene is rated High
This tool executes code within the Godot game engine by launching a scene. While not a direct shell command, it runs game logic and initializes runtime state, making it an Execute category tool. Severity is high because a malicious actor could execute arbitrary game logic or scripts embedded in scenes, potentially affecting the game state, performing unexpected computations, or triggering side effects.
From the tool's definition Tool description explicitly states 'Start playing the current or specified scene' and notes it is 'Required before using any runtime tools'. This triggers external operations (scene execution) whose effects depend on which scene is specified as an argument.
Attacks that exploit this kind of access
The rule that runs play_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 play_scene, this is the rule to start with:
play_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 play_scene call is checked against it from then on.
Questions about play_scene
Start playing the current or specified scene. Required before using any runtime tools (get_game_*, capture_frames, etc.). 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.
play_scene accepts 2 parameters: mode, scene_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 play_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.
play_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 play_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 play_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.
play_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