godot_export
Headless export using an export preset. Runs to completion and returns exit code + logs. Can be slow — exposed as an MCP task, so task-aware clients can poll, await, or cancel it (tasks/get, tasks/result, tasks/cancel).
This record as markdown: /tools/breakpoint-mcp/godot-export.md
What godot_export does on Breakpoint
AI agents invoke godot_export to trigger actions in Breakpoint. 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 |
|---|---|---|---|
debug | boolean | — | Export a debug build instead of release (default false) |
preset | string | Yes | Export preset name as defined in export_presets.cfg |
timeout_ms | integer | — | Max run time (default 600000) |
output_path | string | Yes | Output file path for the exported build |
Parameters from the server's own tool schema.
Why godot_export is rated High
This tool executes a Godot engine export process headlessly, running an external operation whose effects depend on the export preset arguments. It produces build artifacts and runs to completion, making it an Execute-category tool. Severity is high because a misconfigured export could overwrite build outputs, consume significant resources, or expose sensitive project data through unintended export configurations.
From the tool's definition 'Headless export using an export preset. Runs to completion and returns exit code + logs.' — triggers an external build/export process that runs to completion.
Attacks that exploit this kind of access
The rule that runs godot_export safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Breakpoint, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For godot_export, this is the rule to start with:
godot_export 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 Breakpoint, apply this rule, and every godot_export call is checked against it from then on.
Questions about godot_export
Headless export using an export preset. Runs to completion and returns exit code + logs. Can be slow — exposed as an MCP task, so task-aware clients can poll, await, or cancel it (tasks/get, tasks/result, tasks/cancel). It is categorised as a Execute tool in the Breakpoint MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
godot_export accepts 4 parameters: debug, preset, timeout_ms, output_path. Required: preset, output_path. The full parameter table on this page comes from the server's own tool schema.
Register the Breakpoint MCP server in PolicyLayer and add a rule for godot_export: 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 Breakpoint. Nothing to install.
godot_export 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 godot_export 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 godot_export. 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.
godot_export is provided by the Breakpoint MCP server (breakpoint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Breakpoint, and thousands of servers like it.
Across the catalogue