Skip to main content
Glama

godot_start_project

Launch Godot editor for an existing project to begin development work, with option to open specific scenes directly.

Instructions

Start Godot's editor for an existing project, optionally opening a specific scene in the editor.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
project_pathYesPath to the Godot project directory or its project.godot file.
scene_pathNoOptional .tscn path to open in the editor.
godot_executableNoOptional explicit path to the Godot executable or .app bundle.

Implementation Reference

  • The logic to start a Godot project, implemented in the GodotController class.
    def start_project(
        self,
        project_path: str,
        godot_executable: str | None = None,
        scene_path: str | None = None,
    ) -> dict[str, Any]:
        project_dir = ensure_project_path(project_path)
        executable, version = resolve_godot_executable(godot_executable)
    
        command = [str(executable), "--path", str(project_dir), "-e"]
        opened_scene = None
        if scene_path:
            absolute_scene_path, resource_scene_path = resolve_scene_path(project_dir, scene_path)
            command.append(str(absolute_scene_path))
            opened_scene = resource_scene_path
    
        launched = _launch_process(command, cwd=project_dir, log_name="start-project")
        return {
            "project_path": str(project_dir),
            "pid": launched.pid,
            "command": launched.command,
            "log_path": launched.log_path,
            "godot_version": version,
            "opened_scene": opened_scene,
        }
  • Registration of the godot_start_project tool in the server's tool definitions list.
        name="godot_start_project",
        description="Start Godot's editor for an existing project, optionally opening a specific scene in the editor.",
        input_schema={
            "type": "object",
            "properties": {
                "project_path": {
                    "type": "string",
                    "description": "Path to the Godot project directory or its project.godot file.",
                },
                "scene_path": {
                    "type": "string",
                    "description": "Optional .tscn path to open in the editor.",
                },
                "godot_executable": {
                    "type": "string",
                    "description": "Optional explicit path to the Godot executable or .app bundle.",
                },
            },
            "required": ["project_path"],
            "additionalProperties": False,
        },
        handler=lambda args: self.controller.start_project(
            project_path=args["project_path"],
            scene_path=args.get("scene_path"),
            godot_executable=args.get("godot_executable"),
        ),
    ),
Behavior2/5

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

No annotations are provided, so the description carries full burden. It mentions starting the editor and optionally opening a scene, but omits critical behavioral details: whether this launches a GUI process, requires specific permissions, has side effects (like locking files), or how errors are handled (e.g., invalid paths). This is inadequate for a tool that likely interacts with external applications.

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 a single, efficient sentence that front-loads the core purpose ('Start Godot's editor for an existing project') and adds optional detail without redundancy. Every word earns its place, making it easy to parse quickly.

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

Completeness2/5

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

Given no annotations, no output schema, and a tool that likely launches an external application (complex behavior), the description is incomplete. It lacks information on expected outcomes (e.g., does it return a process ID?), error conditions, or dependencies (e.g., Godot installation). This leaves significant gaps for an agent to use it correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so parameters are well-documented in the schema. The description adds minimal value beyond the schema—it implies 'scene_path' is for opening scenes and contextually relates to the editor, but doesn't explain parameter interactions or provide additional semantic context. Baseline 3 is appropriate given high schema coverage.

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 states the action ('Start Godot's editor') and target ('for an existing project'), with an optional extension ('opening a specific scene'). It distinguishes from siblings like 'godot_create_project' (creation vs. starting) and 'godot_run_project' (editor vs. runtime), but doesn't explicitly contrast with all siblings like 'godot_edit_scene'.

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

Usage Guidelines3/5

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

Usage is implied by 'for an existing project' (vs. 'godot_create_project' for new ones) and 'optionally opening a specific scene' (vs. default editor launch). However, it lacks explicit when-not-to-use guidance or alternatives (e.g., when to use 'godot_edit_scene' instead for scene editing without starting the full editor).

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/MhrnMhrn/godot-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server