Loading...
Godot MCP enables AI assistants to interact with the Godot game engine, automating tasks such as launching the editor, running projects, and managing scenes.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
Godot MCP enables AI assistants to interact with the Godot game engine, automating tasks such as launching the editor, running projects, and managing scenes.
Godot MCP offers powerful automation capabilities but requires careful configuration and monitoring. It is relatively safe when used with trusted projects and with user oversight. However, running untrusted projects or granting excessive permissions can lead to security risks.
Performance depends on the complexity of the Godot project and the operations being performed. Complex scene modifications or project analysis can be resource-intensive.
There are no direct monetary costs associated with using Godot MCP. However, running resource-intensive operations can consume CPU and memory resources.
npm install
npm{
"mcpServers": {
"godot": {
"command": "node",
"args": ["/absolute/path/to/godot-mcp/build/index.js"],
"env": {
"DEBUG": "true" // Optional: Enable detailed logging
},
"disabled": false,
"autoApprove": [
"launch_editor",
"run_project",
"get_debug_output",
"stop_project",
"get_godot_version",
"list_projects",
"get_project_info",
"create_scene",
"add_node",
"load_sprite",
"export_mesh_library",
"save_scene",
"get_uid",
"update_project_uids"
]
}
}
}launch_editorLaunches the Godot editor for a specific project.
Only opens the editor; no modification of files.
run_projectExecutes a Godot project in debug mode.
Executes project code, which could have unintended consequences.
get_debug_outputRetrieves console output and error messages from a running project.
Read-only operation; does not modify any files.
stop_projectStops a running Godot project.
Terminates the project execution, potentially interrupting processes.
get_godot_versionRetrieves the installed Godot version.
Read-only operation; no side effects.
list_projectsFinds Godot projects in a specified directory.
Read-only operation; only lists files.
get_project_infoGets detailed information about project structure.
Read-only operation; no modification of files.
create_sceneCreates a new scene with specified root node types.
Creates a new file, but the content is controlled.
add_nodeAdds nodes to existing scenes with customizable properties.
Modifies existing scene files.
load_spriteLoads sprites and textures into Sprite2D nodes.
Modifies scene files to include sprite data.
export_mesh_libraryExports 3D scenes as MeshLibrary resources for GridMap.
Creates a new resource file based on scene data.
save_sceneSaves scenes with options for creating variants.
Overwrites existing scene files.
get_uidGets UID for specific files (Godot 4.4+).
Read-only operation; retrieves file metadata.
update_project_uidsUpdates UID references by resaving resources.
Modifies multiple project files, potentially causing data loss if interrupted.
None
cloud
Godot MCP offers powerful automation capabilities but requires careful configuration and monitoring. It is relatively safe when used with trusted projects and with user oversight. However, running untrusted projects or granting excessive permissions can lead to security risks.
Autonomy is limited by the AI assistant's configuration and the approved MCP tools. Users should carefully review the actions performed by the AI assistant to avoid unintended consequences.
Production Tip
Enable detailed logging during development and testing, but disable it in production to reduce overhead and potential security risks.
Godot MCP is a Model Context Protocol server that allows AI assistants to interact with the Godot game engine.
You can automate tasks such as launching the editor, running projects, managing scenes, and debugging code.
Clone the repository, install dependencies with `npm install`, and build the server with `npm run build`.
Add the server configuration to your AI assistant's MCP settings file, specifying the command and arguments to run the server.
Potential risks include arbitrary code execution, file modification, and exposure of sensitive information if not configured properly.
Approve only necessary tools, use trusted projects, and monitor the actions performed by the AI assistant.
You can use GODOT_PATH to specify the path to the Godot executable and DEBUG to enable detailed logging.