██████╗ ██╗ █████╗ ██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗ █████╗ ███████╗
██╔══██╗██║ ██╔══██╗╚██╗ ██╔╝██╔════╝██╔══██╗████╗ ██║██║ ██║██╔══██╗██╔════╝
██████╔╝██║ ███████║ ╚████╔╝ ██║ ███████║██╔██╗ ██║██║ ██║███████║███████╗
██╔═══╝ ██║ ██╔══██║ ╚██╔╝ ██║ ██╔══██║██║╚██╗██║╚██╗ ██╔╝██╔══██║╚════██║
██║ ███████╗██║ ██║ ██║ ╚██████╗██║ ██║██║ ╚████║ ╚████╔╝ ██║ ██║███████║
╚═╝ ╚══════╝╚═╝ ╚═╝ ╚═╝ ╚═════╝╚═╝ ╚═╝╚═╝ ╚═══╝ ╚═══╝ ╚═╝ ╚═╝╚══════╝
███╗ ███╗ ██████╗██████╗ ███████╗███████╗██████╗ ██╗ ██╗███████╗██████╗
████╗ ████║██╔════╝██╔══██╗ ██╔════╝██╔════╝██╔══██╗██║ ██║██╔════╝██╔══██╗
██╔████╔██║██║ ██████╔╝ ███████╗█████╗ ██████╔╝██║ ██║█████╗ ██████╔╝
██║╚██╔╝██║██║ ██╔═══╝ ╚════██║██╔══╝ ██╔══██╗╚██╗ ██╔╝██╔══╝ ██╔══██╗
██║ ╚═╝ ██║╚██████╗██║ ███████║███████╗██║ ██║ ╚████╔╝ ███████╗██║ ██║
╚═╝ ╚═╝ ╚═════╝╚═╝ ╚══════╝╚══════╝╚═╝ ╚═╝ ╚═══╝ ╚══════╝╚═╝ ╚═╝
An MCP Server for automating the PlayCanvas Editor using an LLM.
[!IMPORTANT]
At the moment, the MCP Server needs to be driven by Anthropic's Claude. Our experience shows that the free tier for Claude does not deliver a big enough chat context to operate the MCP Server reliably. Therefore, we strongly recommend subscribing to a Pro Claude account.
Available Tools
- Entity
list_entitiescreate_entitiesdelete_entitiesduplicate_entitiesmodify_entitiesreparent_entityadd_componentsremove_componentsadd_script_component_script
- Asset
list_assetscreate_assetsdelete_assetsinstantiate_template_assetsset_script_textscript_parseset_material_diffuse
- Scene
query_scene_settingsmodify_scene_settings
- Store
store_searchstore_getstore_download
Installation
Run npm install to install all dependencies.
Install Chrome Extension
- Visit
chrome://extensions/and enable Developer mode - Click
Load unpackedand select theextensionsfolder - Load the PlayCanvas Editor. The extension should be loaded.
Run MCP Server
The MCP Server can be driven by Cursor or Claude Desktop.
[!TIP]
We have found Claude Desktop to be generally more reliable.
Claude Desktop
- Install Claude Desktop.
- Go to
Claude>Settings. - Select
Developerand thenEdit Config. - This will open
claude_desktop_config.json, your MCP Config JSON file.
Cursor
- Install Cursor.
- Select
File>Preferences>Cursor Settings. - Click
+ Add new global MCP server. - This will open
mcp.json, your MCP Config JSON file.
[!TIP]
Also inCursor Settings, selectFeaturesand scroll to theChatsection. ActivateEnable auto-run modeto allow the LLM to run MCP tools without requiring constant authorization. You do this at your own risk (but we prefer it)!
[!IMPORTANT]
In Cursor, ensure you haveAgentselected.AskandEditmodes will not recognize the MCP Server.
MCP Config JSON File
This is how your config should look:
Windows
{
"mcpServers": {
"playcanvas": {
"command": "cmd",
"args": [
"/c",
"npx",
"tsx",
"C:\\\\path\\\\to\\\\mcp-editor\\\\src\\\\server.ts"
],
"env": {
"PORT": "52000"
}
}
}
}
macOS
{
"mcpServers": {
"playcanvas": {
"command": "npx",
"args": [
"tsx",
"/path/to/mcp-editor/src/server.ts"
],
"env": {
"PORT": "52000"
}
}
}
}
Connecting the Editor to the MCP Server
The PlayCanvas Editor does not connect to the MCP Server automatically. To connect:
- Activate a Chrome tab running the PlayCanvas Editor.
- Select the Extensions icon to the right of the address bar.
- Select PlayCanvas Editor MCP Extension to open the extension popup.
- Select
CONNECT(the port number should match what is set in your MCP Config JSON File).
[!NOTE] You can currently only connect one instance of the PlayCanvas Editor to the MCP Server at any one time.
You should now be able to issue commands in Claude Desktop or Cursor.
Recommend MCP Servers 💡
touchdesigner-mcp-server
An MCP server implementation that enables AI agents to control and operate TouchDesigner projects
Skyvern
Skyvern's MCP server connects AI applications to the browser, enabling form filling, file downloading, and web research.
vmware-fusion-mcp-server
A Model Context Protocol (MCP) server for managing VMware Fusion virtual machines via the Fusion REST API
@peakmojo/applescript-mcp
A Model Context Protocol (MCP) server that lets you run AppleScript code to interact with Mac.
espressif/esp-rainmaker-mcp
A Model Context Protocol (MCP) server wrapper around the esp-rainmaker-cli Python library for controlling ESP RainMaker IoT devices
@browserstack/mcp-server
BrowserStack's official MCP Server enables users to manage test cases, execute manual or automated tests, debug issues, and fix code directly within AI tools like Cursor, Claude, or any MCP-enabled client using natural language. It integrates with BrowserStack's comprehensive test platform for mobile app, web, automated, and accessibility testing.