Godot AI

by hi-godot

Overview Schema Source Related Servers Discussions Admin

Local

Input Map Manage

input_map_manage

Manage Godot input actions and bindings (keyboard, mouse, gamepad) and persist them to project.godot.

Instructions

InputMap actions and bindings (keyboard, mouse, gamepad). Persisted to project.godot.

Resource form: godot://input_map — prefer for active-session reads.

Ops: • list(include_builtin=False) List input actions and their bound events. By default only user-authored actions (those persisted in project.godot under input/<name>) are returned; pass include_builtin=True to also surface Godot's ui_* and editor-runtime actions (spatial_editor/*, etc.). The is_builtin field on each entry is true for any action not authored by the user. • add_action(action, deadzone=0.5) Create a new empty input action. deadzone must be in [0.0, 1.0] — Godot uses it as the analog-stick dead-zone threshold; values outside this range are rejected with VALUE_OUT_OF_RANGE. Typical values are 0.2-0.5; leave the default 0.5 unless you have a reason. Not a key-repeat delay. • ensure_action(action, deadzone=0.5) Idempotently create or persist an input action. If the action exists in live InputMap or in project.godot, the existing state is preserved. • remove_action(action) Remove an action and all its event bindings. Also removes actions persisted in project.godot but not loaded in the live InputMap (loaded_in_input_map: false in list), e.g. actions created by a previous editor session. • bind_event(action, event_type, keycode="", ctrl=False, alt=False, shift=False, meta=False, button=None, axis=None, axis_value=1.0) Bind a key/mouse/gamepad event to an action. The action must already exist (call add_action first). event_type is "key" | "mouse_button" | "joy_button" | "joy_axis". - key: keycode is a Godot keycode name string like "A", "Space", "Enter", "Escape", "F1", "Left" — not an integer and not KEY_*. Modifier booleans ctrl / alt / shift / meta optional. - mouse_button: button is an int — 1=left, 2=right, 3=middle, 4=wheel up, 5=wheel down. - joy_button: button is the JoyButton index (e.g. 0=A/Cross, 1=B/Circle). - joy_axis: axis is the JoyAxis index and axis_value is the direction/value, usually -1.0 or 1.0. • ensure_binding(action, event_type, ...) Idempotently ensure the action exists and has the requested binding.

Canonical call shape: {"op": "<verb>", "params": {...}}. Flat op parameters are accepted as a compatibility alias when the client transmits them; op and session_id remain top-level.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`op`	Yes
`params`	No
`session_id`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.9.1Jul 11, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so thoroughly: persistence side effects, builtin-vs-user actions, deadzone validation and rejection error, removal of unloaded persisted actions, and event-type-specific value mappings are all disclosed. This gives an agent a reliable model of what each operation changes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but earned: each operation has a compact bullet with parameter details and constraints, and the canonical call shape is stated at the end. The structure is scannable and front-loaded with the overall domain before diving into operations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a multi-operation tool with high complexity and a schema that covers none of the operation-specific parameters, the description is remarkably complete. It covers all ops, their parameters, constraints, side effects, and the call envelope; an output schema exists, so not detailing return values is acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides only a top-level op enum and an opaque params object, so parameter documentation is entirely the description's job. It delivers per-operation parameter lists, types, defaults, allowed ranges, and concrete examples (e.g., keycode name strings, mouse button indices, JoyButton/JoyAxis values), far exceeding what the schema offers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource ('InputMap actions and bindings (keyboard, mouse, gamepad)') and its persistence target ('project.godot'), and enumerates six concrete operations. It does not explicitly contrast itself with sibling tools like resource_manage, but the InputMap domain is distinct enough that an agent can tell what this tool is for.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives clear operational context: it recommends the godot://input_map resource form for active-session reads, instructs that bind_event requires the action to already exist, and highlights idempotent alternatives (ensure_action, ensure_binding). It stops short of explicitly saying when not to use this tool or naming a specific preferred sibling alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.