manage_input_actions · Godot MCP Unified MCP: Risk & Policy

WHAT IT DOES

What manage_input_actions does on Godot MCP Unified

AI agents use manage_input_actions to create or update resources in Godot MCP Unified — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Godot MCP Unified environment.

WHY IT NEEDS A POLICY

Why manage_input_actions needs a policy

This tool modifies the project.godot configuration file by adding or removing input action bindings. While 'list' is a read operation, the tool's primary capability includes reversible write operations ('add', 'remove'). The modifications are reversible (can be undone by adding back or removing again), so it is classified as Write rather than Destructive.

From the tool's definition The tool description explicitly states it can "add, remove, or list input actions in project.godot". The 'add' and 'remove' operations are write/modify operations that alter the project configuration file.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

manage_input_actions Rate-limited

manage_input_actions stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "manage_input_actions": {
      "limits": [
        {
          "counter": "manage_input_actions_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Godot MCP Unified, so you can run agents against it safely.

FAQ

Questions about manage_input_actions

What does the manage_input_actions tool do? +

Add, remove, or list input actions in project.godot. It is categorised as a Write tool in the Godot MCP Unified MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on manage_input_actions? +

Register the Godot MCP Unified MCP server in PolicyLayer and add a rule for manage_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 Unified. Nothing to install.

What risk level is manage_input_actions? +

manage_input_actions is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit manage_input_actions? +

Yes. Add a rate_limit block to the manage_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.

How do I block manage_input_actions completely? +

Set action: deny in the PolicyLayer policy for manage_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.

What MCP server provides manage_input_actions? +

manage_input_actions 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.