AI agents call editor_get_input_map to retrieve information from Godot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the Input Map configuration from the Godot editor API. It retrieves data about input bindings and mappings without modifying, executing, or deleting anything. This is a read-only operation with no destructive potential and minimal risk to the game project.
From the tool's definition The tool description explicitly states 'Read the Input Map' and uses the verb 'Read', indicating data retrieval with no side effects. The name 'editor_get_input_map' with the 'get' prefix further confirms a retrieval operation.
Attacks that exploit this kind of access
Read the Input Map via editor API. It is categorised as a Read tool in the Godot MCP Server, which means it retrieves data without modifying state.
Register the Godot MCP server in PolicyLayer and add a rule for editor_get_input_map: 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. Nothing to install.
editor_get_input_map 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 editor_get_input_map 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 editor_get_input_map. 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.
editor_get_input_map is provided by the Godot MCP server (@yanhuifair/godot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
editor_get_input_map is one line of Godot's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →