replay_recording
🔴 Game must be running. Replay a previously recorded game session
This record as markdown: /tools/keeveeg-godot-mcp/replay-recording.md
What replay_recording does on Godot
AI agents invoke replay_recording 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 |
|---|---|---|---|
speed | number | — | Playback speed multiplier (default: 1.0) |
Parameters from the server's own tool schema.
Why replay_recording is rated High
This tool triggers external execution within a running game engine, replaying a recorded session. It executes operations in the context of a live game process, which qualifies as Execute. It doesn't read/write data in a reversible sense nor does it delete or have financial implications, but it does trigger active game-state changes by running a replay.
From the tool's definition 'Replay a previously recorded game session' and '🔴 Game must be running'
Attacks that exploit this kind of access
The rule that runs replay_recording 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 replay_recording, this is the rule to start with:
replay_recording 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 replay_recording call is checked against it from then on.
Questions about replay_recording
🔴 Game must be running. Replay a previously recorded game session. 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.
replay_recording accepts 1 parameter: speed. 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 replay_recording: 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.
replay_recording 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 replay_recording 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 replay_recording. 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.
replay_recording 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