write_input_action · Godot MCP: Risk & Policy

WHAT IT DOES

What write_input_action does on Godot

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

PARAMETERS

Parameter	Type	Required	Description
`action`	string	Yes	Input action name (e.g. "jump", "move_left")
`deadzone`	object	—	Deadzone for analog inputs (0-1)

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why write_input_action needs a policy

This tool creates new input action configurations in Godot, which modifies the project's input system reversibly. It is a Write-category operation (creates/modifies data) rather than Read (it actively changes state) or Execute (it does not run arbitrary code).

From the tool's definition Tool name 'write_input_action' and description 'Create a new input action' indicate creation of configuration data in Godot Engine. The verb 'write' and 'create' establish this as a modification operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

write_input_action Rate-limited

write_input_action 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": {
    "write_input_action": {
      "limits": [
        {
          "counter": "write_input_action_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, so you can run agents against it safely.

FAQ

Questions about write_input_action

What does the write_input_action tool do? +

Create a new input action. It is categorised as a Write tool in the Godot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does write_input_action accept? +

write_input_action accepts 2 parameters: action, deadzone. Required: action. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on write_input_action? +

Register the Godot MCP server in PolicyLayer and add a rule for write_input_action: 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.

What risk level is write_input_action? +

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

Can I rate-limit write_input_action? +

Yes. Add a rate_limit block to the write_input_action 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 write_input_action completely? +

Set action: deny in the PolicyLayer policy for write_input_action. 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 write_input_action? +

write_input_action 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.