List all custom input actions defined in the project (Project > Project Settings > Input Map).
AI agents call list_input_actions to retrieve information from Godot Mcp Pilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about input actions from project settings without altering, executing, or destructing any data. It is a read-only informational query with minimal security impact. The blast radius of misuse is negligible since listing configuration poses no direct harm to the project or its assets.
From the tool's definition Tool name 'list_input_actions' and description 'List all custom input actions defined in the project' indicate a querying/retrieval operation with no modification of data.
Attacks that exploit this kind of access
List all custom input actions defined in the project (Project > Project Settings > Input Map). It is categorised as a Read tool in the Godot Mcp Pilot MCP Server, which means it retrieves data without modifying state.
Register the Godot Mcp Pilot MCP server in PolicyLayer and add a rule for list_input_actions: 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 Pilot. Nothing to install.
list_input_actions 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 list_input_actions 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 list_input_actions. 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.
list_input_actions is provided by the Godot Mcp Pilot MCP server (pushks18/godot-mcp-pilot). 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 →