Godot MCP is an AI-powered game development assistant for the Godot Editor. Connect Claude, Cursor, Copilot, or any MCP-aware agent to Godot and let it inspect and drive your project — create nodes, edit scenes, manage resources and scripts, capture screenshots, and more.

Godot-MCP is the Godot counterpart of Unity-MCP: a C# editor addon that exposes Godot Editor operations as AI Tools and connects them to an MCP server through the same hosted cloud backend (ai-game.dev) that powers Unity-MCP — or your own self-hosted server. The MCP / reflection stack is not forked: it is shared with Unity-MCP and consumed from nuget.org as PackageReferences.

💬 Join our Discord Server — Ask questions, showcase your work, and connect with other developers!

• ✔️ AI agents — Use the best agents from Anthropic, OpenAI, Google, or any other provider with no vendor lock-in
• ✔️ 39 built-in Tools — A wide range of MCP Tools across 11 families for operating the Godot Editor
• ✔️ C# & GDScript — Read, create, and update both .cs and .gd scripts, and attach them to nodes
• ✔️ Scene & Node control — Build and edit the scene tree, open/save .tscn scenes, mutate .tres/.res resources
• ✔️ Visual feedback — Capture viewport, camera, and isolated-node screenshots the LLM can inspect
• ✔️ Reflection escape hatch — Find and call any C# method across loaded assemblies via ReflectorNet
• ✔️ Cloud or self-hosted — Connect to ai-game.dev out of the box, or point at your own server
• ✔️ Natural conversation — Chat with AI like you would with a human

Quick Start

Get up and running from a terminal using the godot-cli (the Godot analog of unity-mcp-cli) — no manual file copying or csproj editing required:

# 1. Install godot-cli
npm install -g godot-cli

# 2. (Optional) Scaffold a fresh Godot C# project — skip if you already have one
godot-cli create-project --dotnet ./MyGodotProject

# 3. Install the godot_mcp addon: downloads addons/godot_mcp/ from the matching
#    GitHub release, adds the required NuGet packages + the extension-catalog
#    EmbeddedResource to your .csproj, and enables the plugin in project.godot —
#    all idempotently
godot-cli install-plugin ./MyGodotProject

# 4. Pick an AI agent (Claude Code, Cursor, Copilot, …) and write its MCP config
godot-cli setup-mcp claude-code ./MyGodotProject

# 5. Open the Godot editor — builds the C# assembly first (so the addon loads on
#    the very first open) then auto-connects with the right GODOT_MCP_* env vars
godot-cli open ./MyGodotProject

# 6. Wait until the plugin answers the readiness probe
godot-cli wait-for-ready ./MyGodotProject

That's it. Ask your AI "Create 3 cubes in a circle with radius 2" and watch it happen. ✨

Offline / dev install: install-plugin --source <path-to>/addons/godot_mcp copies the addon from a local directory instead of downloading it. Prefer the matching release version with install-plugin --version <x.y.z> if you need a specific addon build. The manual route (copy the addon + add the NuGet packages yourself) is still documented under Installation Steps 1–2 for the Asset Library / hand-managed flows.

See the full CLI documentation for every command, editor-resolution order, and connection env vars.

Contents

• Quick Start
• Tools Reference
• Requirements
• Installation
  • Step 1: Add the addon
    • Option A — Godot Asset Library (recommended)
    • Option B — GitHub Release zip
    • Option C — copy from source
  • Step 2: Add the NuGet packages
  • Step 3: Install an AI agent
• Connect
  • Cloud mode (default) — ai-game.dev
  • Custom mode — your own server
• Godot MCP Server setup
  • Local server — let the addon download & run it for you
  • Build & run the server manually (advanced)
• Customize Tools
• Runtime usage (in-game)
  • Capturing in-game runtime errors
  • Sample: a live game-state tool
  • Where the server URL and token come from
  • Security: opt-in only, default OFF
• [How Godot MCP Architecture Works](#how-godot-mcp-archi