Server profile

Godot MCP

Godot MCP lets AI agents open the editor, run projects, and inspect debug output. It also supports scene and node operations, sprite loading, mesh-library export, and UID maintenance for supported Godot versions.

Server facts

Godot MCP

Project

License
MIT
Category
Games & 3D

Tech

Runtime / language
nodeTypeScript and GDScript
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
6,117
Last commit
Data as of

Tags

  • Debugging
  • Game Development
  • Gdscript
  • Godot
  • Scene Management

Overview

Godot MCP gives compatible AI agents a direct connection to the Godot game engine. It can launch the editor for a project, execute that project in debug mode, collect output and errors, and stop execution. Other tools discover projects, inspect their metadata, and report the installed engine version. These operations create a feedback loop in which an assistant can inspect what a project actually does rather than relying only on source text when helping with implementation or debugging.

The integration also handles scene work: creating scenes, inserting nodes with properties, loading sprites into Sprite2D nodes, saving changes, and exporting scenes as MeshLibrary resources for GridMap. UID lookup and reference updates are listed for Godot 4.4 and later. Simple operations use Godot's command-line capabilities, while more complex changes are routed through a bundled GDScript operations file that accepts JSON parameters. The README requires an installed Godot engine, Node.js 18 or newer with npm, and an MCP-capable agent. Client examples run the npm package with npx, and GODOT_PATH can override executable discovery when automatic detection fails. Project paths must identify directories containing project.godot. Source builds are also documented. This is engine-connected tooling, so it complements a local Godot installation rather than providing an independent game runtime or editor.

Install & configure

Requirements

  • Godot Engine installed locally
  • Node.js 18.0.0 or newer and npm
  • An MCP-compatible agent
  • Godot 4.4 or newer for UID operations
Documented launch / install command
npx @coding-solo/godot-mcp

GODOT_PATH overrides automatic executable detection and can be omitted when discovery works. DEBUG=true enables detailed server logging. Ensure project paths contain project.godot.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "godot-mcp": {
      "command": "npx",
      "args": [
        "@coding-solo/godot-mcp"
      ],
      "env": {
        "GODOT_PATH": "<Path to the Godot executable; optional discovery override>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "godot-mcp": {
      "command": "npx",
      "args": [
        "@coding-solo/godot-mcp"
      ],
      "env": {
        "GODOT_PATH": "<Path to the Godot executable; optional discovery override>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "godot-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "@coding-solo/godot-mcp"
      ],
      "env": {
        "GODOT_PATH": "<Path to the Godot executable; optional discovery override>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "godot-mcp": {
      "command": "npx",
      "args": [
        "@coding-solo/godot-mcp"
      ],
      "env": {
        "GODOT_PATH": "<Path to the Godot executable; optional discovery override>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "godot-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "@coding-solo/godot-mcp"
      ],
      "env": {
        "GODOT_PATH": "<Path to the Godot executable; optional discovery override>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository tool metadata. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
launch_editorOpen the Godot editor for a selected project.
run_projectExecute a project and collect its output.
get_debug_outputRead the current runtime logs and error output.
stop_projectEnd the project execution currently controlled by the server.
get_godot_versionReport the installed engine version.
list_projectsDiscover Godot projects beneath a directory.
get_project_infoInspect a project’s metadata.
create_sceneGenerate a Godot scene file.
add_nodeInsert a node into an existing scene.
load_spriteAssign sprite content to a Sprite2D node.
export_mesh_libraryExport scene content as a MeshLibrary resource.
save_scenePersist scene changes to a file.
get_uidRead a file’s resource UID on Godot 4.4 or newer.
update_project_uidsResave resources to refresh project UID references on Godot 4.4 or newer.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Run a game project and inspect errors from an AI assistant.
  • Create scenes and add configured nodes.
  • Load sprites or export MeshLibrary resources for GridMap.
  • Maintain project resource UID references on Godot 4.4 or newer.

Strengths

  • Combines execution control and debug output with scene editing.
  • Uses a bundled GDScript file for complex operations.
  • Allows an explicit Godot executable path when discovery fails.

Limitations

  • Requires an installed Godot engine and Node.js 18 or newer.
  • UID operations require Godot 4.4 or newer.
  • Project paths must point to directories containing project.godot.

Frequently asked questions

Yes. The documented tools start and stop projects and retrieve debug output and error messages.

Yes. It can create scenes, add nodes, load sprites, export MeshLibrary resources, and save scenes.

Set GODOT_PATH to the Godot executable, overriding automatic detection.

No. The README identifies UID management as requiring Godot 4.4 or newer.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

BlenderMCP

Games & 3D

BlenderMCP links AI assistants to Blender for scene inspection, object and material changes, and Python execution. Optional asset integrations add Poly Haven downloads, Sketchfab models, and generated 3D assets.

MCP for Unity

Games & 3D

MCP for Unity links AI assistants to the Unity Editor for scene work, asset management, script editing, testing, and builds. It targets game developers who want to direct editor workflows through natural language.

Unreal MCP

Games & 3D

Unreal MCP links assistant requests to Unreal Editor through a Python server and C++ plugin. It covers scene objects, Blueprint construction, and viewport adjustments, but the project explicitly remains experimental.

MCP Unity Editor

Games & 3D

Connect AI assistants to Unity Editor through a Unity package and Node.js MCP bridge. Manage scenes, GameObjects, materials, packages, tests, and console logs, with resources and guided workflow prompts.

Unreal Engine Generative AI Support Plugin

Games & 3D

This Unreal Engine plugin combines generative AI API integrations with MCP-based editor control. Assistants can manipulate scene objects, work with some Blueprint features, and run editor scripts, although MCP development is inactive.

Minecraft MCP Server

Games & 3D

Minecraft MCP Server lets an AI assistant control a Minecraft character through Mineflayer. Tools cover movement, blocks, inventory, smelting, entities, and chat, with a documented local LAN-world setup.