Get the project
AI agents call get_main_scene to retrieve information from Godot Mcp Pilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about the main scene/project without altering any data or triggering side effects. While it operates within a game development context (Godot), the action itself is a simple query operation. Severity is low because retrieving project metadata poses minimal risk even if misused by an AI agent—it cannot corrupt, delete, or execute arbitrary code.
From the tool's definition Tool name 'get_main_scene' and description 'Get the project' indicate data retrieval with no modification. The verb 'get' is a classic read operation that queries the current project state.
Attacks that exploit this kind of access
Get the project. It is categorised as a Read tool in the Godot Mcp Pilot MCP Server, which means it retrieves data without modifying state.
Register the Godot Mcp Pilot MCP server in PolicyLayer and add a rule for get_main_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 Mcp Pilot. Nothing to install.
get_main_scene is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_main_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 get_main_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.
get_main_scene 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 →