Godot AI
Connects MCP clients directly to a live Godot editor, enabling AI assistants to build scenes, edit nodes, and control the editor through over 120 operations.
README
<p align="center"> <img src="docs/hero.png" alt="Godot AI — The wait is over" width="700"> </p>
Godot AI
Connect MCP clients directly to a live Godot editor via the Model Context Protocol. Over 120 ops across ~39 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).
<img src="docs/images/assetlib.png" alt="Godot AI on the Godot Asset Library" width="312">
💬 Join the Discord — questions, showcases, and contributor chat.
<p align="center"> <img src="docs/images/huddemo.gif" alt="Cyberpunk HUD demo" width="800"><br> <em>UI demo built in ~2 hours with zero coding, zero image gen, all programmatically drawn by Godot AI — <a href="https://github.com/hi-godot/cyberpunk-hud-demo">source</a></em> </p>
Quick Start
Prerequisites
- Godot
4.3+(4.4+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" - Other options: uv install docs
- macOS / Linux:
- 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.
<details> <summary>Or via the Godot Asset Library</summary>
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.
</details>
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.
<p align="center"><img src="docs/images/dock.png" alt="Godot AI dock — Clients & Tools button highlighted" width="350"></p>
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
<details> <summary><strong>…and 16+ more clients</strong></summary>
Codex, Cursor, Windsurf, VS Code, VS Code Insiders, Zed, Gemini CLI, Cline, Kilo Code, Roo Code, Kiro, Trae, Cherry Studio, OpenCode, Qwen Code, Kimi Code.
</details>
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."
<p align="center"> <img src="docs/images/blockarena.gif" alt="Block-world game scene built from MCP tool calls — voxel terrain, player, and UI" width="640"> </p> <p align="center"><em>Demo gamelet with sophisticated save system built from a handful of Godot AI MCP prompts. Code and Godot project <a href="https://github.com/dsarno/save-system-godot-claude">available free here</a>.</em></p>
Tools and resources: see docs/TOOLS.md for the full list of 120+ MCP tools and resources, grouped by domain.
<details> <summary><strong>Manual Client Configuration</strong></summary>
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/antigravity/mcp_config.json)
{
"mcpServers": {
"godot-ai": {
"serverUrl": "http://127.0.0.1:8000/mcp",
"disabled": false
}
}
}
</details>
<details> <summary><strong>How It Works</strong></summary>
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.
</details>
<details> <summary><strong>Windows: <code>uvx mcp-proxy</code> won't start (<code>pywin32</code> install fails)</strong></summary>
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:
_stop_serverandforce_restart_serverboth callMcpUvCacheCleanup.purge_stale_builds()immediately after killing the server children, while the.pydis briefly unmapped. Seeplugin/addons/godot_ai/utils/uv_cache_cleanup.gd.- Auto-configure now writes
UV_LINK_MODE=copyinto the bridged entry'senvblock 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 spawnsuvx mcp-proxywhile 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.
</details>
<details> <summary><strong>Contributing</strong></summary>
See CONTRIBUTING.md for development setup, testing, and PR guidelines.
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.
</details>
<details> <summary><strong>Telemetry & Privacy</strong></summary>
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.
</details>
Star History
<a href="https://star-history.com/#hi-godot/godot-ai&Date"> <img src="https://api.star-history.com/svg?repos=hi-godot/godot-ai&type=Date" alt="Star History Chart" width="700"> </a>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。