Godot AI

Connect MCP clients directly to a live Godot editor via the Model Context Protocol. Over 120 ops across ~41 MCP tools (full list) let AI assistants (Claude Code, Codex, Antigravity, etc.) build scenes, edit nodes and scripts, wire signals, and configure UI, materials, animations, particles, cameras, and environments.

🎉 Now on the Godot Asset Library and the new Godot Asset Store — one-click install from Godot's AssetLib tab. You'll still need uv for the Python server (see Quick Start).

💬 Join the Discord — questions, showcases, and contributor chat.

Quick Start

Prerequisites

• Godot 4.5+ (4.7+ recommended)

• uv (for the Python server):

  • macOS / Linux: curl -LsSf https://astral.sh/uv/install.sh | sh

  • Windows (PowerShell): powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

  • Prefer your package manager? uv is a popular open-source tool packaged in most distro repos, so you don't have to pipe a script from the web:

    • Arch: sudo pacman -S uv

    • Debian / Ubuntu: sudo apt install uv (older releases: pipx install uv or the script above)

    • Fedora: sudo dnf install uv

    • macOS (Homebrew): brew install uv

  • Other options: uv install docs

• An MCP client (Claude Code | Codex | Antigravity)

1. Install the plugin

Recommended — install from source (always the latest):

git clone https://github.com/hi-godot/godot-ai.git
cp -r godot-ai/plugin/addons/godot_ai your-project/addons/

Or download the latest release ZIP and extract addons/godot_ai into your project's addons/ folder.

In Godot, open the AssetLib tab, search for Godot AI, click Download, then Install. Note: Asset Library updates lag behind GitHub, so this version may not be the most recent.

🚨 If installing from the Asset Library, most issues can be resolved by disabling and re-enabling the plugin in Project > Project Settings > Plugins.

2. Enable the plugin

In Godot: Project > Project Settings > Plugins — enable Godot AI.

The plugin will automatically start the MCP server, connect over WebSocket, and show status in the Godot AI dock.

3. Connect your MCP client

The dock lists every supported client with a status dot and per-row Configure / Remove buttons, or press Configure all. Auto-configure covers:

• Claude Code, Claude Desktop, Antigravity

Codex, Cursor, Devin Desktop (formerly Windsurf), VS Code, VS Code Insiders, Zed, Gemini CLI, Cline, Kilo Code, Roo Code, Kiro, Trae, Cherry Studio, OpenCode, Qwen Code, Kimi Code.

Server URL is always http://127.0.0.1:8000/mcp. If auto-configure can't find a CLI, each dock row exposes a Run this manually panel with a copyable snippet.

4. Try it

• "Show me the current scene hierarchy."

• "Create a Camera3D named MainCamera under /Main."

• "Search the project for PackedScene files in ui/."

• "Run the scene test suite."

• "Build a voxel block-world game with a player, blocks to place and destroy, and save slots."

Tools and resources: see docs/TOOLS.md for the full list of 120+ MCP tools and resources, grouped by domain.

Claude Code

claude mcp add --scope user --transport http godot-ai http://127.0.0.1:8000/mcp

Codex (~/.codex/config.toml)

[mcp_servers."godot-ai"]
url = "http://127.0.0.1:8000/mcp"
enabled = true

Antigravity (~/.gemini/config/mcp_config.json)

{
  "mcpServers": {
    "godot-ai": {
      "serverUrl": "http://127.0.0.1:8000/mcp",
      "disabled": false
    }
  }
}

MCP Client
   | HTTP (/mcp)
   v
Python Server (FastMCP)      port 8000
   | WebSocket               port 9500
   v
Godot Editor Plugin
   | EditorInterface + SceneTree APIs
   v
Godot Editor

The plugin starts or reuses the Python server, connects over WebSocket, and exposes editor capabilities as MCP tools and resources over HTTP.

The MCP server binds to 127.0.0.1 by default. To reach it from another machine on your network (e.g. a remote coding agent), pass --allow-host with one or more CIDRs or bare IPs (repeat the flag or comma-separate values) when launching the server:

godot-ai --allow-host 192.168.1.0/24

This binds the HTTP transport off loopback and gates every request on the real (unforgeable) socket peer address, so only hosts inside the named range(s) get in — DNS-rebinding defenses (Origin / Host / Sec-Fetch-Site checks) stay active. The plugin's WebSocket bridge to the editor always stays loopback-only since it's unauthenticated. Only name ranges you trust; prefer an SSH tunnel or Tailscale on untrusted networks.

Symptom (in your MCP client's server log):

error: Failed to install: pywin32-311-cp313-cp313-win_amd64.whl (pywin32==311)
  Caused by: failed to remove directory `C:\Users\<you>\AppData\Local\uv\cache\builds-v0\.tmpXXXXXX\Lib\site-packages\pywin32-311.data`: ... os error 32

Cause: uv hard-links shared .pyd files (notably pydantic_core/_pydantic_core.cp313-win_amd64.pyd) from archive-v0\ into each new builds-v0\.tmpXXXXXX\ build venv. The running godot-ai Python process has the same .pyd mapped via LoadLibrary — and because hard links share the inode, Windows refuses to delete it under any path until every process unmaps it. uv's post-install cleanup of the build venv then dies on a stale lock; the misleading pywin32 mention is just the last package in the resolution order, not the actual lock holder.

Mitigation in this plugin:

1. _stop_server and force_restart_server both call McpUvCacheCleanup.purge_stale_builds() immediately after killing the server children, while the .pyd is briefly unmapped. See plugin/addons/godot_ai/utils/uv_cache_cleanup.gd.

2. Auto-configure now writes UV_LINK_MODE=copy into the bridged entry's env block for every uvx-bridge client (Claude Desktop, Zed), telling uv to copy shared C extensions instead of hard-linking them. That removes the reverse race where an MCP client spawns uvx mcp-proxy while a server child still holds the .pyd. Existing entries written by older plugin versions surface in the dock as drift (amber banner) so a single Configure click rewrites them with the env pin.

The shape client_configure writes for Claude Desktop is now:

{
  "mcpServers": {
    "godot-ai": {
      "command": "uvx",
      "args": ["mcp-proxy==0.11.0", "--transport", "streamablehttp", "http://127.0.0.1:8000/mcp"],
      "env": { "UV_LINK_MODE": "copy" }
    }
  }
}

If you've already hit the lock on an older config, click Configure on the affected uvx-bridge client (Claude Desktop or Zed) in the godot-ai dock to rewrite the entry with the env pin, then quit and reopen that client. If the lock persists (rare — pre-existing orphans the cache sweeper couldn't reach), kill stray python.exe children whose command line contains spawn_main(parent_pid=...) and delete %LOCALAPPDATA%\uv\cache\builds-v0\.tmp* manually before retrying.

See CONTRIBUTING.md for development setup, testing, and PR guidelines. AI assistants should also read AGENTS.md.

Windows contributors: run .\script\setup-dev.ps1 in PowerShell. It builds test_project\addons\godot_ai as a directory junction — no admin rights and no Windows Developer Mode required.

Godot AI ships anonymous, privacy-focused telemetry (no code, no scene contents, no project or file names, no personal data). Project-directory slugs are sha256-hashed before any event leaves your machine; only an anonymous installation UUID, the tool/event name, success/duration, and platform/version fields are sent.

Opt out by setting either environment variable to true:

export GODOT_AI_DISABLE_TELEMETRY=true
# or the cross-tool convention
export DISABLE_TELEMETRY=true

Opt-out is fully side-effect-free — no UUID generated, no worker thread, no files written.

Full details (what's collected, where data lives, how to self-host the endpoint): docs/TELEMETRY.md.

Related MCP server: AI-godot-mcp

Star History

License: MIT | Issues: GitHub