PlayCanvas Editor

v1.0.0Developer Toolsstable

An MCP Server that enables LLMs to build real-time 3D web applications in the PlayCanvas Editor.

javascriptmcpmcp-serverplaycanvastypescript
Share:
110
Stars
0
Downloads
0
Weekly
0/5

What is PlayCanvas Editor?

PlayCanvas Editor is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that enables llms to build real-time 3d web applications in the playcanvas editor.

An MCP Server that enables LLMs to build real-time 3D web applications in the PlayCanvas Editor.

This server falls under the Developer Tools category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • An MCP Server that enables LLMs to build real-time 3D web ap

Use Cases

Build real-time 3D web applications in PlayCanvas Editor through Claude.
Develop WebGL/WebGPU content with natural language instructions.
playcanvas

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx playcanvas-editor-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use PlayCanvas Editor

The PlayCanvas Editor MCP Server connects AI assistants directly to the PlayCanvas web-based 3D editor, enabling LLMs to create, modify, and manage entities, assets, and scenes in real-time WebGL and WebGPU applications through natural language. It works by combining a local MCP server (running via Node.js/tsx) with a Chrome extension that bridges the AI assistant to the open PlayCanvas Editor tab. Developers use it to accelerate 3D content creation, prototype WebXR experiences, and perform editor tasks through conversational commands instead of manual UI interaction.

Prerequisites

  • Node.js 18 or higher with npm
  • Google Chrome browser (the bridge extension requires Chrome)
  • A PlayCanvas account with at least one project open in the PlayCanvas Editor (playcanvas.com)
  • Claude Pro subscription recommended — the free tier's context window is too small for reliable 3D scene operations
  • An MCP-compatible client such as Claude Desktop
1

Clone the repository and install dependencies

Clone the PlayCanvas Editor MCP Server repository and install the required Node.js packages.

git clone https://github.com/playcanvas/editor-mcp-server.git
cd editor-mcp-server
npm install
2

Load the Chrome extension

Open Chrome and navigate to chrome://extensions/. Enable 'Developer mode' in the top-right corner, then click 'Load unpacked' and select the 'extension' folder inside the cloned repository.

3

Add the MCP server to Claude Desktop

Register the server in claude_desktop_config.json. The server runs via npx tsx and listens on a configurable port (default 52000).

{
  "mcpServers": {
    "playcanvas": {
      "command": "npx",
      "args": ["tsx", "/absolute/path/to/editor-mcp-server/src/server.ts"],
      "env": {
        "PORT": "52000"
      }
    }
  }
}
4

Open PlayCanvas Editor and connect the extension

Navigate to the PlayCanvas Editor in Chrome and open your project. Click the Chrome extension icon in the toolbar, then select 'CONNECT' and choose the port matching your server configuration (52000 by default).

5

Restart Claude Desktop and start building

Restart Claude Desktop so the MCP server is picked up. With the Chrome extension connected to the PlayCanvas Editor tab, you can now ask Claude to create entities, modify materials, manage assets, and capture viewport screenshots.

PlayCanvas Editor Examples

Client configuration

Claude Desktop config registering the PlayCanvas Editor MCP server. Update the path to match your local clone.

{
  "mcpServers": {
    "playcanvas": {
      "command": "npx",
      "args": ["tsx", "/Users/you/editor-mcp-server/src/server.ts"],
      "env": {
        "PORT": "52000"
      }
    }
  }
}

Prompts to try

These prompts demonstrate entity creation, asset management, and scene control through the PlayCanvas Editor MCP server.

- "Create a new entity called 'Player' with a collision box and rigidbody component"
- "List all entities in the current scene"
- "Set the material on entity 'Ground' to use color #4a7c59"
- "Take a screenshot of the current viewport"
- "Search the PlayCanvas Store for a free tree asset and add it to the scene"
- "Create a directional light entity pointing at 45 degrees and set its intensity to 2"

Troubleshooting PlayCanvas Editor

The Chrome extension shows 'disconnected' and cannot reach the MCP server

Verify that the MCP server is running and listening on the expected port (default 52000). Check that the PORT environment variable in your Claude Desktop config matches the port you selected in the Chrome extension popup. Also ensure no firewall is blocking localhost connections on that port.

Claude gives incomplete or truncated responses when editing 3D scenes

The free tier of Claude does not provide a large enough context window for complex PlayCanvas scenes. Upgrade to a Claude Pro subscription, which provides the extended context needed for reliable scene editing operations.

Tools return 'no active PlayCanvas Editor tab found'

The Chrome extension must be connected to an active PlayCanvas Editor tab. Open playcanvas.com, load a project in the editor, click the extension icon, and press CONNECT. Make sure the tab remains open and focused during tool calls.

Frequently Asked Questions about PlayCanvas Editor

What is PlayCanvas Editor?

PlayCanvas Editor is a Model Context Protocol (MCP) server that mcp server that enables llms to build real-time 3d web applications in the playcanvas editor. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install PlayCanvas Editor?

Follow the installation instructions on the PlayCanvas Editor GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with PlayCanvas Editor?

PlayCanvas Editor works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is PlayCanvas Editor free to use?

Yes, PlayCanvas Editor is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Developer Tools MCP Servers

Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "playcanvas-editor-mcp-server": { "command": "npx", "args": ["-y", "playcanvas-editor-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use PlayCanvas Editor?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides