Godot MCP

                       (((((((             (((((((
                    (((((((((((           (((((((((((
                    (((((((((((((       (((((((((((((
                    (((((((((((((((((((((((((((((((((
     (((((      (((((((((((((((((((((((((((((((((((((((((      (((((
   (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
  ((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
    (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
      (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
       (((((((((@@@@@@@(((((((((((((((((((((((((@@@@@@@@((((((((((
       ((((((@@@@,,,,,@@@((((((((((((((((((((@@@,,,,,@@@@(((((((((
       (((((@@,,,,,,,,,@@(((((((@@@@@(((((((@@,,,,,,,,,@@@((((((((
       ((((((@@,,,,,,,@@(((((((@@@@@((((((((@@,,,,,,,@@@(((((((((
       (((((((((@@@@@@(((((((((@@@@@(((((((((((@@@@@@((((((((((((
       (((((((((((((((((((((((((((((((((((((((((((((((((((((((((((
       @@@@@@@@@@@@@(((((((((((@@@@@@@@@@@@@@(((((((((((@@@@@@@@@@@@@@
       (((((((( @@@(((((((((((@@(((((((((((@@(((((((((((@@@ ((((((((
       ((((((((( @@(((((((((@@@(((((((((((@@@((((((((((@@ (((((((((
        ((((((((((@@@@@@@@@@@@@@(((((((((((@@@@@@@@@@@@@@((((((((((
         ((((((((((((((((((((((((((((((((((((((((((((((((((((((((
            (((((((((((((((((((((((((((((((((((((((((((((((((
                    (((((((((((((((((((((((((((((((((

          G O D O T    x    M O D E L   C O N T E X T   P R O T O C O L

An MCP server that gives AI assistants full control over the Godot game engine. Build scenes, write scripts, run games, send input, capture screenshots, and query game state -- all through natural language.

Fork of Coding-Solo/godot-mcp, extended with interactive game control, persistent TCP communication, script authoring, and more.

How It Works

MCP (Model Context Protocol) is a standard that lets AI assistants use external tools. Think of it like a USB port -- your AI plugs into this server and gains the ability to control Godot.

You (natural language) --> AI Assistant --> MCP Server --> Godot Engine
    "Add a player to           |              |              |
     the scene"            interprets     calls tool     creates node
                           your request   add_node()     in .tscn file

You talk to your AI assistant normally. When it needs to do something in Godot, it calls one of the 75 tools this server provides. You don't write any code yourself -- the AI handles that.

Related MCP server: godot-mcp-pilot

Quickstart

Prerequisites

Before you start, make sure you have these installed:

1. Godot Engine 4.x -- Download here. Install it and note the full path to the executable.

   • Windows: e.g., C:/Program Files (x86)/Godot/Godot_v4.7-stable_win64.exe

   • macOS: e.g., /Applications/Godot.app/Contents/MacOS/Godot

   • Linux: e.g., /usr/local/bin/godot4

2. Node.js 18+ -- Download here. This runs the MCP server.

3. pnpm -- Install with npm install -g pnpm (or corepack enable if using Node 18+).

4. An MCP-compatible AI assistant -- See Supported Clients below.

Step 1: Clone and Build

git clone https://github.com/Vollkorn-Games/godot-mcp.git
cd godot-mcp
pnpm install
pnpm run build

After building, note the full path to build/index.js inside the cloned folder. You'll need it in the next step.

Step 2: Configure Your AI Assistant

Add the MCP server to your AI assistant's config. Every config needs two things:

1. The command to start the server (node + path to build/index.js)

2. The GODOT_PATH environment variable pointing to your Godot executable

Pick your assistant below and copy the config.

Run this command in your terminal:

claude mcp add godot -- node /absolute/path/to/godot-mcp/build/index.js

Or add to your MCP settings JSON (~/.claude/settings.json or project-level .mcp.json):

{
  "mcpServers": {
    "godot": {
      "command": "node",
      "args": ["/absolute/path/to/godot-mcp/build/index.js"],
      "env": {
        "GODOT_PATH": "/absolute/path/to/godot/executable"
      }
    }
  }
}

Open the Cline MCP settings (Cline sidebar > MCP Servers > Configure) and add:

{
  "mcpServers": {
    "godot": {
      "command": "node",
      "args": ["/absolute/path/to/godot-mcp/build/index.js"],
      "env": {
        "GODOT_PATH": "/absolute/path/to/godot/executable"
      },
      "disabled": false
    }
  }
}

Go to Settings > Features > MCP > + Add New MCP Server:

• Name: godot

• Type: command

• Command: node /absolute/path/to/godot-mcp/build/index.js

Then set the environment variable GODOT_PATH in your system or shell profile.

Any application that supports MCP can use this server. The connection always works the same way:

• Transport: stdio (the AI launches the server as a subprocess)

• Command: node /absolute/path/to/godot-mcp/build/index.js

• Environment variables: GODOT_PATH=/absolute/path/to/godot/executable

Check your client's documentation for where to add MCP server configs. Look for terms like "MCP", "tools", or "tool servers".

Windows paths example (replace with your actual paths):

{
  "godot": {
    "command": "node",
    "args": ["C:/Users/you/godot-mcp/build/index.js"],
    "env": {
      "GODOT_PATH": "C:/Program Files (x86)/Godot/Godot_v4.7-stable_win64.exe"
    }
  }
}

Use forward slashes / even on Windows -- JSON doesn't handle backslashes well.

Step 3: Test It

Open your AI assistant and try:

"Use the get_godot_version tool to check if the MCP server is connected."

If it returns a version number, everything is working. Now try:

"Create a new Godot project at C:/Users/you/my-game with a Node2D main scene."

Supported Clients

MCP is an open standard. Any AI assistant that supports MCP can use this server:

Using with Local LLMs (LlamaCPP, Ollama, etc.)

You don't connect the LLM to the MCP server directly. Instead, you need an MCP client (an app that speaks the MCP protocol) sitting between your LLM and the MCP server:

Your local LLM (LlamaCPP)  -->  MCP Client (e.g., Cline)  -->  Godot MCP Server
   runs on localhost:8080        handles tool calls               controls Godot

Here's how to set it up with LlamaCPP + Cline (the easiest path):

1. Start LlamaCPP with a tool-capable model

llama-server -m your-model.gguf --port 8080

Use a model that supports function/tool calling (e.g., Qwen 2.5, Mistral, Llama 3.1+). Smaller models may struggle with complex tool use.

2. Install Cline in VS Code

Install the Cline extension from the VS Code marketplace.

3. Point Cline to your local LLM

In Cline settings, configure the API provider:

• API Provider: OpenAI Compatible

• Base URL: http://localhost:8080/v1

• API Key: not-needed (any non-empty string)

• Model ID: the model name your server reports

4. Add the Godot MCP server to Cline

Open the Cline sidebar > MCP Servers > Configure, and add:

{
  "mcpServers": {
    "godot": {
      "command": "node",
      "args": ["/absolute/path/to/godot-mcp/build/index.js"],
      "env": {
        "GODOT_PATH": "/absolute/path/to/godot/executable"
      },
      "disabled": false
    }
  }
}

5. Test it

Ask Cline: "Use the get_godot_version tool" -- if it returns a version, the full chain is working.

Other local LLM setups:

• Ollama: Same as above, but base URL is http://localhost:11434/v1

• LM Studio: Has built-in MCP support via plugins -- check their docs

• Custom client: Implement the MCP client spec yourself -- the server uses stdio transport and doesn't care what LLM is behind the client

What Can It Do?

This isn't just "launch editor and read logs". The MCP server can build an entire game from scratch -- create scenes, add and configure nodes, write GDScript files, wire up signals, set up tilemaps, then run the game, play it via input commands, and observe the results through screenshots and state queries.

75 Tools Across 10 Categories

Project & Editor

Scene Management

Scripting

Assets & Resources

Animation & Physics

Project Configuration

Interactive Game Control

Static Analysis

Testing

Asset Library

Interactive Mode

The standout feature. run_interactive injects a TCP server into the running game as a temporary autoload. The AI can then:

1. Send inputs -- send_input(action: "move_right") for named actions, send_key(key: "space") for keyboard, send_mouse_click(x: 100, y: 200) for mouse, send_joypad_button(button: "a") and send_joypad_motion(axis: "left_x", value: 0.75) for gamepad

2. Batch input sequences -- send_key_sequence(keys: ["1", {"action": "move_right", "hold_ms": 300}, {"state": true}, "o", {"wait": 2000}, {"screenshot": "mid.png"}, "s"], collectSignals: [{nodePath: "/root/EventBus", signals: ["task_completed"]}]) sends keys and InputMap actions with inline checkpoints — waits, screenshots, state snapshots, and signal collection all in one round-trip

3. Query state -- game_state() returns health, score, turn, level, player position, game over status

4. Set properties -- set_property(nodePath: "/root/GameManager", property: "score", value: 9999) modifies live node properties

5. Call methods -- call_method(nodePath: "Player", method: "take_damage", args: [10]) invokes any method on a live node

6. Find nodes -- find_nodes(pattern: "Enemy*", typeFilter: "CharacterBody2D") searches the runtime scene tree

7. Evaluate expressions -- evaluate_expression(expression: "get_tree().current_scene.name") runs arbitrary GDScript at runtime

8. Execute scripts -- execute_script(code: "var p = $Player\nreturn p.position") runs multi-line GDScript blocks with autoload access

9. Wait for events -- wait_for_signal(nodePath: "Player", signal: "died") or wait_for_node(nodePath: "Player/Sword") for sequencing

10. Monitor signals -- subscribe_signals(nodePath: "/root/EventBus", signals: ["score_changed"]) then get_signal_events() to read buffered emissions

11. Monitor performance -- get_performance_metrics() returns FPS, draw calls, memory, node count, physics stats

12. Pause/unpause -- pause_game(paused: true) freezes game time while keeping MCP receiver active for inspection

13. Take screenshots -- game_screenshot() captures the live viewport with all runtime rendering

14. Reset and replay -- reset_scene() reloads the current scene, chain with inputs to test game loops

The TCP connection is persistent (single socket reused across commands). Everything is cleaned up automatically when the game stops -- the injected autoload is removed and project.godot is restored.

Efficient Testing Patterns

send_key_sequence is the primary tool for gameplay testing. It bundles keys, InputMap actions, waits, state snapshots, screenshots, and signal collection into a single round-trip — much faster than calling individual tools in a loop.

Fast gameplay test (1 round-trip):

send_key_sequence({
  keys: ["1", {"action": "move_right", "hold_ms": 300}, {"state": true}, "o", {"wait": 2000}, {"screenshot": "mid.png"}, "s"],
  collectSignals: [{nodePath: "/root/EventBus", signals: ["task_completed", "score_changed"]}]
})
// Response includes:
//   keys_sent: 4
//   states: [{state: {scene: "Desktop", score: 100}, index: 2}]
//   screenshots: [{path: "mid.png", size: "1024x768", index: 3}]
//   events: [{signal: "score_changed", node: "/root/EventBus", args: [200]}]

Avoid these slower patterns:

// BAD: 3 round-trips for the same result
subscribe_signals({nodePath: "/root/EventBus", signals: ["task_completed"]})
send_key_sequence({keys: ["1", "a", "o", "s"]})
get_signal_events()

// BAD: N round-trips instead of 1
send_key({key: "a"})
game_state()
send_key({key: "b"})
game_screenshot()

// BAD: shell sleeps between inputs — use {"wait": ms} checkpoints instead
send_input({action: "move_right"})
Bash("sleep 2")
send_input({action: "jump"})
game_screenshot()

Prefer structured checks over screenshots. game_state, evaluate_expression, and get_runtime_errors return text in milliseconds; a screenshot costs a viewport capture, a PNG write, and an image read. Reach for game_screenshot only when the visual result itself is what needs verifying (rendering, layout, animation).

When to use subscribe_signals instead: Only when you need to monitor signals across multiple separate commands (e.g., subscribe once, then issue several unrelated tool calls and check accumulated events later).

Environment Variables

The server tries to auto-detect Godot in common install locations. If it can't find it, set GODOT_PATH explicitly.

Tool Filtering

Reduce token overhead and add safety by controlling which tools are exposed. All three filters can be combined.

Toolset filtering

Only expose specific categories of tools:

{
  "godot": {
    "command": "node",
    "args": ["/path/to/godot-mcp/build/index.js"],
    "env": {
      "GODOT_PATH": "/path/to/godot",
      "MCP_TOOLSETS": "scene,node,script,analysis"
    }
  }
}

Available categories: process, project, scene, node, animation, tilemap, resource, script, signal_group, uid, settings, interactive, screenshot, analysis, testing.

Read-only mode

Block all tools that create, modify, or delete files and game state:

{
  "env": {
    "MCP_READ_ONLY": "true"
  }
}

This exposes only tools like get_scene_tree, read_script, get_project_info, validate_scene, run_tests, game_state, find_nodes, get_performance_metrics, etc.

Tool exclusion

Remove specific tools by name:

{
  "env": {
    "MCP_EXCLUDE_TOOLS": "export_project,manage_autoloads"
  }
}

Architecture

The server uses three execution strategies:

1. Direct CLI -- Simple operations (launch editor, get version, read files) call Godot CLI commands or manipulate files directly from TypeScript.

2. Bundled GDScript -- Complex scene operations use godot_operations.gd, a comprehensive script that runs via godot --headless --script to manipulate scene trees, nodes, and resources through the Godot API.

3. TCP Input Receiver -- Interactive mode injects input_receiver.gd as a temporary autoload that listens on port 9876 for JSON commands (input injection, state queries, viewport capture).

Troubleshooting

Contributing

pnpm install
pnpm run build
pnpm test           # run all tests
pnpm lint           # eslint
pnpm format:check   # prettier
pnpm typecheck      # tsc --noEmit

License

MIT -- see LICENSE.