AI agents call resource_load to retrieve information from Godot Devtool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from the Godot project (loading a resource file) with no side effects, no code execution, no data modification, and no destructive capability. It is a read-only operation analogous to 'get' or 'fetch'. The low severity reflects minimal risk from misuse: reading project resources does not directly compromise system integrity or cause irreversible changes.
From the tool's definition Tool name 'resource_load' and description 'Load a text-based Godot resource from the project' indicate retrieval of resource data without modification or execution. The verb 'load' in this context means to read/fetch an existing resource.
Documented attack patterns abuse exactly the kind of access resource_load gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Godot Devtool, and nothing reaches the server without passing your rules. This is the rule we recommend for resource_load:
{
"version": "1",
"default": "deny",
"tools": {
"resource_load": {}
}
}resource_load is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Load a text-based Godot resource from the project. It is categorised as a Read tool in the Godot Devtool MCP Server, which means it retrieves data without modifying state.
Register the Godot Devtool MCP server in PolicyLayer and add a rule for resource_load: 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 Devtool. Nothing to install.
resource_load 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 resource_load 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 resource_load. 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.
resource_load is provided by the Godot Devtool MCP server (wangdiandao/godot-devtool). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 101 Godot Devtool tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
101 Godot Devtool tools catalogued and risk-classified — across an index of 42,500+ MCP servers.