MCP Server for AI automation of the PlayCanvas Editor
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"playcanvas": {
"env": {
"PORT": "52000"
},
"args": [
"/c",
"npx",
"tsx",
"C:\\path\\to\\editor-mcp-server\\src\\server.ts"
],
"command": "cmd"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
██████╗ ██╗ █████╗ ██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗ █████╗ ███████╗ ██╔══██╗██║ ██╔══██╗╚██╗ ██╔╝██╔════╝██╔══██╗████╗ ██║██║ ██║██╔══██╗██╔════╝ ██████╔╝██║ ███████║ ╚████╔╝ ██║ ███████║██╔██╗ ██║██║ ██║███████║███████╗ ██╔═══╝ ██║ ██╔══██║ ╚██╔╝ ██║ ██╔══██║██║╚██╗██║╚██╗ ██╔╝██╔══██║╚════██║ ██║ ███████╗██║ ██║ ██║ ╚██████╗██║ ██║██║ ╚████║ ╚████╔╝ ██║ ██║███████║ ╚═╝ ╚══════╝╚═╝ ╚═╝ ╚═╝ ╚═════╝╚═╝ ╚═╝╚═╝ ╚═══╝ ╚═══╝ ╚═╝ ╚═
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in developer-tools / design
Copy/paste detector for programming source code, supports 223 formats. AI-ready with token-efficient reporter, skill and MCP server.
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
Manage Supabase projects — databases, auth, storage, and edge functions
MCP Security Weekly
Get CVE alerts and security updates for Editor Mcp Server and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
██████╗ ██╗ █████╗ ██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗ █████╗ ███████╗
██╔══██╗██║ ██╔══██╗╚██╗ ██╔╝██╔════╝██╔══██╗████╗ ██║██║ ██║██╔══██╗██╔════╝
██████╔╝██║ ███████║ ╚████╔╝ ██║ ███████║██╔██╗ ██║██║ ██║███████║███████╗
██╔═══╝ ██║ ██╔══██║ ╚██╔╝ ██║ ██╔══██║██║╚██╗██║╚██╗ ██╔╝██╔══██║╚════██║
██║ ███████╗██║ ██║ ██║ ╚██████╗██║ ██║██║ ╚████║ ╚████╔╝ ██║ ██║███████║
╚═╝ ╚══════╝╚═╝ ╚═╝ ╚═╝ ╚═════╝╚═╝ ╚═╝╚═╝ ╚═══╝ ╚═══╝ ╚═╝ ╚═╝╚══════╝
███╗ ███╗ ██████╗██████╗ ███████╗███████╗██████╗ ██╗ ██╗███████╗██████╗
████╗ ████║██╔════╝██╔══██╗ ██╔════╝██╔════╝██╔══██╗██║ ██║██╔════╝██╔══██╗
██╔████╔██║██║ ██████╔╝ ███████╗█████╗ ██████╔╝██║ ██║█████╗ ██████╔╝
██║╚██╔╝██║██║ ██╔═══╝ ╚════██║██╔══╝ ██╔══██╗╚██╗ ██╔╝██╔══╝ ██╔══██╗
██║ ╚═╝ ██║╚██████╗██║ ███████║███████╗██║ ██║ ╚████╔╝ ███████╗██║ ██║
╚═╝ ╚═╝ ╚═════╝╚═╝ ╚══════╝╚══════╝╚═╝ ╚═╝ ╚═══╝ ╚══════╝╚═╝ ╚═╝
An MCP Server for automating the PlayCanvas Editor using an LLM.
The MCP client is built into the PlayCanvas Editor — no browser extension is needed. Install the server into your MCP client of choice (Claude Code, Codex, Claude Desktop, Cursor, …) and connect the Editor to it.
list_entitiesresolve_entitiescreate_entitiesdelete_entitiesduplicate_entitiesmodify_entitiesreparent_entityadd_componentsremove_componentsadd_script_component_scriptattach_scriptlist_assetscreate_assetsdelete_assetsinstantiate_template_assetsset_script_textscript_parseset_material_diffuseset_material_propertiesquery_scene_settingsmodify_scene_settingsstore_searchstore_getstore_downloadcapture_viewportfocus_viewportlaunch_startlaunch_stopcapture_runtimeread_runtime_logsinject_inputThe runtime tools drive a real Launch instance (the editor's Launch button) so you can verify that a scene actually runs, not just how it looks at edit time:
launch_start opens https://launch.playcanvas.com/<sceneId>?debug=true in a new
window. The editor hands the MCP port to the launch page, which connects back to the
MCP server as the "runtime" peer. launch_start returns { url, sceneId, ready }.capture_runtime screenshots the running app (scripts/physics/animation active).read_runtime_logs returns the app's console output + uncaught
exceptions/rejections (newest first, paginated; defaults to warnings + errors).inject_input dispatches keyboard / mouse / touch events to the running app
(e.g. hold W for 500ms, click at a canvas coordinate, tap the screen), so you
can drive end-to-end interactions and then verify with capture_runtime.launch_stop closes the launch window.Notes:
launch_start cannot open the window.Every tool returns a single, consistent envelope so agents can pattern-match on a stable shape:
{
"data": <result> | null, // business payload; an empty set is [], never an error
"meta": {
"tool": "entities:list",
"status": "ok" | "error",
"message": "...", // present only on error; actionable, with a recovery hint
// list tools also include pagination metadata:
"total": 120, "count": 50, "hasMore": true, "nextCursor": "50"
}
... [View full README on GitHub](https://github.com/playcanvas/editor-mcp-server#readme)