Skip to main content
Glama

Run game

godot_run

Launch a Godot project as a child process with live debugging capabilities including scene tree inspection, expression evaluation, hot reload, and screenshots.

Instructions

Launch the project (or a specific scene) as a child process and return a handle. With live=true the godot_mcp bridge is enabled (auto-installed if needed) so you can inspect the scene tree, eval expressions, hot reload and screenshot the running game.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
liveNoEnable the godot_mcp bridge for live control.
sceneNoA specific scene to run (res:// path). Defaults to the project main scene.
versionNoGodot version to use, e.g. "4.7", "4.7-stable", "stable"/"latest". Defaults to the project's declared version, then the latest stable release.
headlessNoRun with the headless/dummy renderer (no window; screenshots unavailable).
positionNoWindow position as X,Y.
extra_argsNoAdditional engine arguments.
resolutionNoWindow size as WxH, e.g. "1280x720".
project_rootNoPath to the Godot project root (folder containing project.godot). Defaults to $GODOT_PROJECT_ROOT or an upward search from the working directory.
response_formatNoOutput format. "markdown" is human-readable; "json" is structured.markdown
Behavior3/5

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

Annotations only provide openWorldHint=true, which is vague. The description adds that the tool launches a child process, returns a handle, and auto-installs the bridge when live=true. However, it does not disclose process lifecycle (e.g., how to stop, resource usage) or potential side effects like multiple runs conflicting.

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?

Two sentences, no fluff. The first sentence states the core action, the second explains the key feature. Every word earns its place.

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

Completeness3/5

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

Given the richness (9 parameters, complex live mode) and no output schema, the description is adequate but incomplete. It mentions returning a handle but does not describe the handle format or how to use it with other tools like godot_stop. It also does not guide parameter selection for common scenarios.

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?

All 9 parameters are fully described in the schema (100% coverage), so the description carries less burden. It does add contextual meaning for the 'live' parameter by explaining what the bridge enables. However, for other parameters, the description adds no extra value beyond the schema.

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 it launches a project or scene as a child process and returns a handle, with a key feature of enabling the godot_mcp bridge for live control. However, it does not differentiate from the sibling tool run_project, which may have similar function.

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

Usage Guidelines2/5

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

No explicit guidance on when to use this tool versus alternatives. The description does not mention when-not to use it or suggest any sibling tools. The context signals list many sibling tools that could be alternatives for specific tasks (e.g., godot_stop, godot_screenshot), but these are not referenced.

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/Fulviuus/godot-mcp'

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