AI agents invoke run_project 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 |
|---|---|---|---|
debug | object | — | Run with debugger |
scene | object | — | Specific scene to run |
headless | object | — | Run in headless mode (no window) |
window_size | object | — | Window size (e.g. "1280x720", "1920x1080") |
project_path | object | — | Project path (default: current project root) |
Parameters from the server's own tool schema.
This tool executes the Godot project, which triggers arbitrary game logic, scripts, and external operations defined within the project. An AI agent could inadvertently run a project with malicious code, resource-intensive loops, network calls, or side effects.
From the tool's definition Tool name is 'run_project' and description states 'Run the Godot project.' The verb 'run' indicates execution of code/operations whose effects depend on project contents and configuration.
Attacks that exploit this kind of access
Run the Godot project. 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.
run_project accepts 5 parameters: debug, scene, headless, window_size, project_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 run_project: 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.
run_project 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 run_project 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 run_project. 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.
run_project 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.
run_project is one line of Godot's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →