Which integrations are available for this server?

Allows AI assistants to create and manage Godot projects, launch the editor, run projects, manipulate scenes and nodes, and read/write files.

How do I use Godot MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Godot MCP Server create a new 3D project called 'MyGame'" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Godot MCP Server

by matula

Overview Schema Related Servers Score Discussions

TypeScript

Local

Godot MCP Server (GMS)

A basic Model Context Protocol (MCP) server for the Godot game engine that enables AI assistants to interact with and manipulate Godot projects. This server, in general, uses the Godot command line to work with projects, so no Godot plugins are needed.

Related MCP server: Godot MCP

Overview

The GMS provides a bridge between AI assistants (like Claude) and the Godot game engine. It allows AI models to:

Create and manage Godot projects
Launch the Godot editor
Run Godot projects
Manipulate scenes and nodes
Read and write files

This server implements the Model Context Protocol (MCP), which standardizes how AI assistants interact with external tools and services.

Setup

Prerequisites

Node.js (v14 or higher)
Godot Engine (v4.x recommended)

Installation

Clone this repository:

git clone https://github.com/matula/godot-mcp-server.git
cd godot-mcp-server

Install dependencies:
```
npm install
```
Build the project:
```
npm run build
```

Configuration

The server will automatically try to locate your Godot command line executable. If it can't find it, you can set the GODOT_PATH environment variable to the path of your Godot executable:

export GODOT_PATH=/path/to/your/godot

On different platforms, the server looks for Godot in these default locations:

macOS:
- /Applications/Godot.app/Contents/MacOS/Godot
- /Applications/Godot_4.app/Contents/MacOS/Godot
- /Applications/Godot_4.2.app/Contents/MacOS/Godot
Linux:
- /usr/bin/godot
- /usr/local/bin/godot
Windows:
- C:\Program Files\Godot\Godot.exe
- C:\Program Files (x86)\Godot\Godot.exe

Usage

Starting the Server

npm start

Or in development mode:

npm run dev

Using with MCP Inspector

You can test the server with the MCP Inspector:

npm run inspector

Using with Claude Desktop

You can integrate the GMS with Claude Desktop by adding it to the Claude Desktop configuration:

Locate the Claude Desktop configuration file:
- Generally on macOS: /Users/{username}/Library/Application Support/Claude/claude_desktop_config.json
Add the following configuration to the file:

{
  "mcpServers": {
    "godot-mcp": {
      "command": "node",
      "args": ["{full path to mcp}/godot-mcp-server/build/index.js"],
      "env": {
        "MCP_TRANSPORT": "stdio"
      }
    }
  }
}

Notes:

If the configuration file already contains an mcpServers object, add the godot-mcp entry to the existing object.
Replace {full path to mcp} with the actual path to where you cloned the repository.
You may need to use the complete path to the node executable if it's not in your system PATH.

Available Tools

The GMS provides the following tools:

Godot Tools

godot_version: Get the installed Godot version
launch_editor: Launch the Godot editor for a project
list_projects: List Godot projects in a directory
create_project: Create a new Godot project (3D, 2D, or empty)
run_project: Run a Godot project
stop_project: Stop a running project
get_debug_output: Get debug output from a running project
get_scene_tree: Get the scene tree from a project
create_scene: Create a new scene in a project
add_node: Add a node to a scene

File Tools

write_file: Write content to a file
read_file: Read content from a file

Architecture

The GMS is built with a modular architecture:

MCP Server Core: Uses the @modelcontextprotocol/sdk to create a server that communicates with AI assistants.
Tools Registration: Tools are registered with the MCP server to expose functionality to AI assistants.
Godot Integration: The server interacts with Godot in three main ways:
- Commands: Direct execution of Godot commands via command-line interface
- Operations: Complex operations executed through GDScript
- Utilities: Helper functions for finding Godot, running commands, etc.
File Operations: Basic file I/O operations to read and write files.

How It Works

The server starts and registers all available tools with the MCP framework.
It connects to the standard input/output for communication with AI assistants.
When a tool is invoked:
- For simple commands, it executes Godot with appropriate command-line arguments
- For complex operations, it creates a temporary GDScript file and executes it with Godot
- The results are returned to the AI assistant in a structured format

Development

Project Structure

src/index.ts: Main entry point
src/godot/commands.ts: Basic Godot commands
src/godot/operations.ts: Complex Godot operations using GDScript
src/tools/godot-tools.ts: MCP tool definitions for Godot
src/tools/file-tools.ts: MCP tool definitions for file operations
src/utils/godot-utils.ts: Utility functions for Godot integration

Building

npm run build

Example using Claude Desktop - Mac

In the tools, you should see the active MCP:

Here's an example prompt:

If you're interested, here's the full code that was created with that prompt. I tried to run it and there were errors, but it looks fixable.

License

ISC License

Available Tools

12 tools

add_nodeD

ParametersJSON Schema

Name	Required	Description
`nodeName`	Yes	Name of the node to add
`nodeType`	Yes	Type of the node
`parentPath`	Yes	Path to the parent node
`projectPath`	Yes	Absolute path to the Godot project directory

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

create_projectD

ParametersJSON Schema

Name	Required	Description
`template`	No	Project template (3d, 2d, or empty)
`projectName`	Yes	Name of the project to create
`parentDirectory`	Yes	Directory to create the project in

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

create_sceneD

ParametersJSON Schema

Name	Required	Description
`nodeType`	No	Type of the root node (default: Node3D)
`sceneName`	Yes	Name of the scene to create
`projectPath`	Yes	Absolute path to the Godot project directory

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_debug_outputD

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_scene_treeD

ParametersJSON Schema

Name	Required	Description	Default
`projectPath`	Yes	Absolute path to the Godot project directory

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

godot_versionD

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

launch_editorD

ParametersJSON Schema

Name	Required	Description	Default
`projectPath`	Yes	Absolute path to the Godot project directory

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_projectsD

ParametersJSON Schema

Name	Required	Description	Default
`directoryPath`	Yes	Directory to search for Godot projects

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

read_fileD

ParametersJSON Schema

Name	Required	Description	Default
`filePath`	Yes	Absolute path to the file to read

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

run_projectD

ParametersJSON Schema

Name	Required	Description	Default
`projectPath`	Yes	Absolute path to the Godot project directory

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

stop_projectD

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

write_fileD

ParametersJSON Schema

Name	Required	Description	Default
`content`	Yes	Content to write to the file
`filePath`	Yes	Absolute path to the file to write

TDQS

D1/5.0

Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

12 tool updatesv1.0.0Jul 30, 2026
- First observedadd_node
- First observedcreate_project
- First observedcreate_scene
- First observedget_debug_output
- First observedget_scene_tree
- First observedgodot_version
- First observedlaunch_editor
- First observedlist_projects
- First observedread_file
- First observedrun_project
- First observedstop_project
- First observedwrite_file

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.1/5.0

Disambiguation5/5

Each tool targets a distinct action (e.g., project management, scene editing, file I/O) with unique names, making confusion unlikely despite missing descriptions.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern (e.g., list_projects, create_scene, write_file), ensuring predictability.

Tool Count5/5

12 tools cover a broad range of Godot interactions (project, editor, scene, debug, file) without being excessive or trivial.

Completeness4/5

Core workflows are covered, but missing operations like remove_node or update project limit some lifecycle completeness.

Maintenance

ActivityInactive

ResponsivenessSyncing

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

GitHubOAuth
io.github.github
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
Version Control Developer Tools CI/CD & DevOps
1232,723
ChiR24-unreal_mcpOAuth
ai.smithery
Control Unreal Engine to browse assets, import content, and manage levels and sequences. Automate…
Developer Tools App Automation Multimedia Processing
2856
ChiR24-unreal_mcp_serverOAuth
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E…
Developer Tools App Automation Software Architecture
2856
MorphedOAuth
app.morphed
Create AI images and videos, manage projects and credits, and use workspace campaign context.
AI & Machine Learning Image & Video Processing
1

Related MCP Servers

Godot MCP
Developer Tools Games & Gamification App Automation
LeeSinLiang
A
license
A
quality
F
maintenance
Enables AI assistants to interact with the Godot game engine by launching the editor, running projects, capturing debug output, managing scenes and nodes, and controlling project execution through a standardized interface.
Updated 9 months ago (2025-12-04 06:25 UTC)
18
248
11
MIT
Godot MCP
Developer Tools Games & Gamification App Automation
Zycroft
A
license
B
quality
Not graded
maintenance
Enables AI assistants to interact with the Godot game engine by launching the editor, running projects, capturing debug output, managing scenes and nodes, and controlling project execution through a standardized interface.
Updated 9 months ago (2025-12-21 00:33 UTC)
14
248
1
-
Godot MCP Server
Developer Tools Games & Gamification App Automation
koltyakov
A
license
Not graded
quality
B
maintenance
Enables LLMs to create and modify Godot game engine projects by managing scenes, generating GDScript code, creating animations, and controlling the Godot editor through natural language commands.
Updated 2 months ago (2026-07-11 21:06 UTC)
248
1
MIT
godot-mcp
Games & Gamification Developer Tools
ChanceFlow
A
license
B
quality
C
maintenance
Enables AI assistants to interact with the Godot game engine, including launching the editor, running projects, capturing debug output, and managing scenes.
Updated 7 months ago (2026-02-12 05:34 UTC)
84
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/matula/godot-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

Godot MCP Server (GMS)

Table of Contents

Overview

Setup

Prerequisites

Installation

Configuration

Usage

Starting the Server

Using with MCP Inspector

Using with Claude Desktop

Available Tools

Godot Tools

File Tools

Architecture

How It Works

Development

Project Structure

Building

Example using Claude Desktop - Mac

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API