AI agents call clear_console_output to permanently remove resources in Minimal Godot MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Clearing the console output buffer is an irreversible action: once cleared, the previous output is lost and cannot be recovered. While the blast radius is low (it's only console/log data, not user files or system state), the action is non-reversible, placing it in the Destructive category. Severity is low because only transient diagnostic/log data is lost.
From the tool's definition 'Clear the console output buffer' — clearing a buffer irreversibly removes the accumulated console output data
Documented attack patterns abuse exactly the kind of access clear_console_output gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Minimal Godot MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for clear_console_output:
{
"version": "1",
"default": "deny",
"hide": [
"clear_console_output"
]
}clear_console_output disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Clear the console output buffer. It is categorised as a Destructive tool in the Minimal Godot MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Minimal Godot MCP server in PolicyLayer and add a rule for clear_console_output: 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 Minimal Godot MCP. Nothing to install.
clear_console_output is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the clear_console_output 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 clear_console_output. 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.
clear_console_output is provided by the Minimal Godot MCP server (ryanmazzolini/minimal-godot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Minimal Godot MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Minimal Godot MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.