Get the current debug output and errors
AI agents call get_debug_output to retrieve information from Godot MCP Unified without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing debug output and error logs from the Godot Engine. It performs no modifications, deletions, code execution, or financial operations. The blast radius of misuse is minimal—an AI agent retrieving debug information cannot cause damage to the game project or its assets.
From the tool's definition Tool name is 'get_debug_output' and description states it 'Get the current debug output and errors' — this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the current debug output and errors. It is categorised as a Read tool in the Godot MCP Unified MCP Server, which means it retrieves data without modifying state.
Register the Godot MCP Unified MCP server in PolicyLayer and add a rule for get_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 Unified. Nothing to install.
get_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_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_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_debug_output is provided by the Godot MCP Unified MCP server (pierrealexandreguillemin-a11y/godot-mcp-unified). 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 →