Skip to main content
Glama

Change project settings, input map or autoloads

godot_project_edit
Destructive

Safely change project.godot settings, input actions, and autoloads without opening the editor, touching only the target lines. Preview the diff first, then write and review errors.

Instructions

Change project.godot safely without the editor, touching only the lines of that entry. op and its fields: set (key, value; name and type checked against the Godot 4.7 reference), unset (key), input_add (action, events, deadzone), input_remove (action), autoload_add (name, file, global; the file must be a Node script or a scene, the name must not clash with a class), autoload_remove (name). Events: Key:Space, Key:Ctrl+S, Mouse:Left, JoyButton:A, JoyAxis:left_y-. Without write it returns the diff and warnings; with write: true it writes and reports the review errors before and after (an error result when there are more after). A missing field or a refused change (bad event, unknown action, name clash) is an error and writes nothing. Use it instead of editing project.godot by hand. For .tscn files use godot_scene_edit; to rename an action or autoload everywhere, godot_rename.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "op": "<op>"
    },
    "name": "godot_project_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
opYeswhat to change
keyNoset/unset: the setting path, e.g. display/window/size/viewport_width
fileNoautoload_add: res:// path of the script or scene
nameNoautoload_add/autoload_remove: the autoload name, e.g. Game
pathNoproject folder, or a file or folder inside it (relative to the server's folder; default: the current project)
valueNoset: the value, e.g. 1920, true, 1.5, a text, res://main.tscn or Vector2i(1920, 1080)
writeNowrite the change (default false: show the diff only)
actionNoinput_add/input_remove: the action name, e.g. jump
eventsNoinput_add: events such as Key:Space, Mouse:Left, JoyButton:0, JoyAxis:1-
globalNoautoload_add: make a global variable (default true)
deadzoneNoinput_add: deadzone of a new action (default 0.2)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.0
    • changedInput schema / properties / path / description
      Previous value: -"The project folder, or any file or folder inside it (Godotwright walks up to project.godot). Relative paths start at the server's folder. Default: the current project."New value: +"project folder, or a file or folder inside it (relative to the server's folder; default: the current project)"
  2. Changed1 schema field changedv0.1.1
    • changedInput schema / properties / path / description
      Previous value: -"Project directory or a path inside it (default: the current project)."New value: +"The project folder, or any file or folder inside it (Godotwright walks up to project.godot). Relative paths start at the server's folder. Default: the current project."
  3. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only flag it as a destructive, non-idempotent write; the description adds the crucial detail that it is dry-run by default ('Without `write` it returns the diff and warnings') and that `write: true` reports review errors before and after, erroring if errors increase. It also guarantees refused changes write nothing, which directly mitigates the destructiveHint risk.

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

Conciseness4/5

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

Front-loaded with the core action followed by a per-op field breakdown, then dry-run/write behavior, then sibling routing. Dense but every sentence carries information; only the long run-on op enumeration slightly reduces scannability.

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 an 11-parameter mutation tool with no output schema, the definition covers what each op touches, validation and failure modes, default dry-run behavior, and the exact conditions producing an error result. An agent has everything needed to call it correctly and safely.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds real semantics beyond it: it maps fields to each `op` (set/unset/input_add/input_remove/autoload_add/autoload_remove), documents event syntax examples (Key:Ctrl+S, JoyAxis:left_y-), and states validation rules (value type-checked against the Godot 4.7 reference; autoload file must be a Node script or scene; name must not clash with a class).

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

Purpose5/5

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

States a specific verb and resource ('Change project.godot safely without the editor') plus the key scoping constraint ('touching only the lines of that entry'), and explicitly distinguishes itself from godot_scene_edit and godot_rename.

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

Usage Guidelines5/5

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

Gives explicit routing: 'Use it instead of editing project.godot by hand', '.tscn files use godot_scene_edit', and 'to rename an action or autoload everywhere, godot_rename'. Use/no-use conditions are both covered.

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