Get the debug output captured from the remote debugger connection
AI agents call get_remote_debug_output to retrieve information from Godot MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves debug output from an already-established remote debugger connection. It does not modify state, execute code, delete data, or move resources. It is purely observational—reading logs or diagnostic information that has already been captured. The lowest blast radius applies: misuse would only expose information the AI can already see through the debugger, not enable harmful actions.
From the tool's definition Tool description states 'Get the debug output' - a retrieval operation with no modification or execution. The verb 'Get' and the read-only nature of querying previously captured debug output confirm this is a data retrieval function.
Documented attack patterns abuse exactly the kind of access get_remote_debug_output gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Godot MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_remote_debug_output:
{
"version": "1",
"default": "deny",
"tools": {
"get_remote_debug_output": {}
}
} get_remote_debug_output 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.
Get the debug output captured from the remote debugger connection. It is categorised as a Read tool in the Godot MCP MCP Server, which means it retrieves data without modifying state.
Register the Godot MCP server in PolicyLayer and add a rule for get_remote_debug_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 Godot MCP. Nothing to install.
get_remote_debug_output 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_remote_debug_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 get_remote_debug_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.
get_remote_debug_output is provided by the Godot MCP server (leesinliang/godot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Godot MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
18 Godot MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.