██████╗ ██╗ █████╗ ██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗ █████╗ ███████╗
██╔══██╗██║ ██╔══██╗╚██╗ ██╔╝██╔════╝██╔══██╗████╗ ██║██║ ██║██╔══██╗██╔════╝
██████╔╝██║ ███████║ ╚████╔╝ ██║ ███████║██╔██╗ ██║██║ ██║███████║███████╗
██╔═══╝ ██║ ██╔══██║ ╚██╔╝ ██║ ██╔══██║██║╚██╗██║╚██╗ ██╔╝██╔══██║╚════██║
██║ ███████╗██║ ██║ ██║ ╚██████╗██║ ██║██║ ╚████║ ╚████╔╝ ██║ ██║███████║
╚═╝ ╚══════╝╚═╝ ╚═╝ ╚═╝ ╚═════╝╚═╝ ╚═╝╚═╝ ╚═══╝ ╚═══╝ ╚═╝ ╚═╝╚══════╝
███╗ ███╗ ██████╗██████╗ ███████╗███████╗██████╗ ██╗ ██╗███████╗██████╗
████╗ ████║██╔════╝██╔══██╗ ██╔════╝██╔════╝██╔══██╗██║ ██║██╔════╝██╔══██╗
██╔████╔██║██║ ██████╔╝ ███████╗█████╗ ██████╔╝██║ ██║█████╗ ██████╔╝
██║╚██╔╝██║██║ ██╔═══╝ ╚════██║██╔══╝ ██╔══██╗╚██╗ ██╔╝██╔══╝ ██╔══██╗
██║ ╚═╝ ██║╚██████╗██║ ███████║███████╗██║ ██║ ╚████╔╝ ███████╗██║ ██║
╚═╝ ╚═╝ ╚═════╝╚═╝ ╚══════╝╚══════╝╚═╝ ╚═╝ ╚═══╝ ╚══════╝╚═╝ ╚═╝
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.
list_entities
create_entities
delete_entities
duplicate_entities
modify_entities
reparent_entity
add_components
remove_components
add_script_component_script
list_assets
create_assets
delete_assets
instantiate_template_assets
set_script_text
script_parse
set_material_diffuse
query_scene_settings
modify_scene_settings
store_search
store_get
store_download
Run npm install
to install all dependencies.
chrome://extensions/
and enable Developer modeLoad unpacked
and select the extensions
folderThe MCP Server can be driven by Cursor or Claude Desktop.
[!TIP]
We have found Claude Desktop to be generally more reliable.
Claude
> Settings
.Developer
and then Edit Config
.claude_desktop_config.json
, your MCP Config JSON file.File
> Preferences
> Cursor Settings
.+ Add new global MCP server
.mcp.json
, your MCP Config JSON file.[!TIP]
Also inCursor Settings
, selectFeatures
and scroll to theChat
section. ActivateEnable auto-run mode
to 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 haveAgent
selected.Ask
andEdit
modes will not recognize the MCP Server.
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"
}
}
}
}
The PlayCanvas Editor does not connect to the MCP Server automatically. To connect:
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.
Seamless access to top MCP servers powering the future of AI integration.