Add or update an autoload (singleton) in the project settings.
AI agents use add_autoload to create or update resources in Godot Mcp Pilot — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot Mcp Pilot environment.
This tool creates or modifies project-level configuration (autoloads/singletons) that affects all game scenes and runtime behavior. While not destructive (changes are reversible), it is a Write operation that alters persistent project state. Severity is high because a malicious autoload could inject arbitrary GDScript to execute on every scene load, affecting game behavior globally.
From the tool's definition Tool description states it can 'Add or update an autoload (singleton) in the project settings' — directly modifying project configuration that persists across sessions.
Attacks that exploit this kind of access
Add or update an autoload (singleton) in the project settings. It is categorised as a Write tool in the Godot Mcp Pilot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Godot Mcp Pilot MCP server in PolicyLayer and add a rule for add_autoload: 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 Mcp Pilot. Nothing to install.
add_autoload is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_autoload 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 add_autoload. 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.
add_autoload is provided by the Godot Mcp Pilot MCP server (pushks18/godot-mcp-pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →