Skip to main content
Glama

project_manage

Manage Godot project runs and settings: stop running projects, read/write project.godot keys, set main scene, apply display presets, and retrieve project metadata.

Instructions

Project run/stop and project.godot settings.

Resource form: godot://project/info and godot://project/settings — prefer for active-session reads.

Ops: • stop() Stop the running project (game). Takes no params — call as project_manage(op="stop") or with params={}. Idempotent: succeeds with was_running=false if the project isn't running. Do NOT pass extra fields like force or reason inside params — only the registered keys are accepted (here, none). For multi-editor setups, pass session_id as a sibling of op/params, not inside params. • settings_get(key) Read a ProjectSettings key (e.g. "application/config/name"). • settings_set(key, value) Write a ProjectSettings key and persist to project.godot. Refuses the startup-execution keys (autoload/*, editor_plugins/*, application/run/main_scene, editor/run/main_run_args, editor/script/templates_search_path); use set_main_scene / autoload_manage(op="add") for the two that have a validated route. • set_main_scene(path) Set the project's main scene — the scene project_run(mode="main") boots and the engine loads at startup. Writes application/run/main_scene and persists to project.godot. path must be a res:// scene inside the project that already exists and loads as a PackedScene, so a scaffolded project can be made runnable without opening the generic startup-execution surface. • apply_preset(preset="pixel_art_2d", viewport_width=None, viewport_height=None) Configure project display resolution, stretch modes, and texture filtering in one atomic operation. Presets: 'pixel_art_2d' (320x180 viewport stretch, nearest filter), 'hd_2d' (1920x1080 canvas_items stretch, linear filter), 'low_poly_3d' (1280x720 canvas_items expand, FXAA), 'cinematic_3d' (1920x1080 canvas_items expand, 4x MSAA, FXAA, TAA).

  • get_info() Retrieve comprehensive project metadata: Godot version, project name, project path, display settings, rendering settings, active scenes, and registered autoloads.

  • get_map(max_files=180) Compact, read-only map of scenes, scripts, assets, resources, autoloads, input actions and open scenes. Results are capped and mark truncation.

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
NameRequiredDescriptionDefault
opYes
paramsNo
session_idNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv5.0.36
    • changedInput schema / properties / op / enum
      Previous value: -[
      -  "apply_preset",
      -  "get_info",
      -  "set_main_scene",
      -  "settings_get",
      -  "settings_set",
      -  "stop"
      -]New value: +[
      +  "apply_preset",
      +  "get_info",
      +  "get_map",
      +  "set_main_scene",
      +  "settings_get",
      +  "settings_set",
      +  "stop"
      +]
  2. Changed1 schema field changedv5.0.28
    • changedInput schema / properties / op / enum
      Previous value: -[
      -  "set_main_scene",
      -  "settings_get",
      -  "settings_set",
      -  "stop"
      -]New value: +[
      +  "apply_preset",
      +  "get_info",
      +  "set_main_scene",
      +  "settings_get",
      +  "settings_set",
      +  "stop"
      +]
  3. First observedv4.1.0

TDQS

A5/5.0
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 it delivers: stop is declared idempotent with a was_running=false result, settings_set lists refused keys and persistence behavior, set_main_scene requires an existing res:// scene that loads as PackedScene, apply_preset is atomic, and get_map returns capped results with truncation marking. These behavioral details go well beyond what any annotation would convey.

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 because the tool is complex, but every sentence earns its place: key warnings are front-loaded (canonical call shape, idempotency, refusal list), each op is a scannable bullet, and no redundant phrasing exists. The structure groups related ops and highlights cross-references without bloat.

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 no annotations, the description covers all necessary context: prerequisites (set_main_scene path validation), side effects (persistence, atomicity), edge cases (was_running=false), and routing to siblings. The output schema exists, so return value details are not needed in the description. An agent can call any op correctly with only this text.

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?

Schema coverage is 0%, so the description must fully explain every parameter. It does: each op lists its parameters with types, defaults, and constraints (e.g., apply_preset's viewport_width/height, set_main_scene's path requirements). It also explicitly states that params={} is allowed for stop and that extra fields are rejected, making the semantics unambiguous despite the generic 'params' object in the schema.

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?

The description opens with a clear summary ('Project run/stop and project.godot settings') and then enumerates each operation with a specific verb and target resource (stop, settings_get, settings_set, set_main_scene, apply_preset, get_info, get_map). Each op is distinguished from relevant siblings (project_run, autoload_manage), so an agent can tell exactly what this tool does and what it doesn't.

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?

The description explicitly says when to prefer the resource form (godot://project/info and godot://project/settings) for active-session reads, and directs users to set_main_scene and autoload_manage for operations that settings_set refuses. It also provides canonical call shape, warns against extra params, and explains session_id placement for multi-editor setups. Nothing is left to inference.

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

Deploy Server

Other Tools