Funplay MCP for Cocos

<strong>An Embedded MCP Server for Cocos Creator Editor</strong>






<a href="#"><img src="https://img.shields.io/badge/Cocos%20Creator-3.8%2B-blue" alt="Cocos Creator 3.8+"></a>
<a href="#"><img src="https://img.shields.io/badge/License-MIT-blue.svg" alt="License: MIT"></a>
<a href="#"><img src="https://img.shields.io/badge/MCP-Compatible-green" alt="MCP Compatible"></a>
<a href="#"><img src="https://img.shields.io/badge/Platform-Editor%20Only-orange" alt="Editor Only"></a>
<a href="https://store.cocos.com/app/detail/8913"><img src="https://img.shields.io/badge/Cocos%20Store-Install-brightgreen" alt="Install from Cocos Store"></a>






<a href="https://github.com/FunplayAI/funplay-cocos-mcp/raw/v0.4.1/README_CN.md">中文</a> | English

If this project helps your Cocos workflow, please consider giving it a Star. It helps more developers discover the project and supports ongoing development.

---

Funplay MCP for Cocos is an MIT-licensed Cocos Creator extension that embeds an HTTP MCP server directly inside the editor. It lets AI assistants such as Claude Code, Cursor, Codex, VS Code Copilot, Trae, and Kiro inspect and operate your running Cocos project.

The package follows the same product direction as Funplay MCP for Unity: keep the default tool surface focused, provide a one-click client configuration window, and make one high-flexibility execution tool the primary workflow.

For Cocos, the primary tool is execute_javascript:

• context: "scene" runs JavaScript in the active Cocos scene/runtime context
• context: "editor" runs JavaScript in the Cocos editor/browser context

"Create a login page UI with account/password fields and a main login button."

Your AI assistant can call execute_javascript, build the UI hierarchy under the active Canvas, attach Cocos components, inspect the result, and capture a screenshot for validation.

Quick Start

If you just want to connect quickly, do these three things:

• Install this repository as a Cocos Creator extension
• Open Funplay > MCP Server
• Use the built-in one-click MCP client configuration

1. Install as a Cocos Creator Extension

Recommended install: use the official Cocos Store page and install the extension into your target Cocos Creator project.

For local development or unreleased builds, clone or copy this repository into your Cocos project extension directory:

cd /path/to/your-cocos-project
mkdir -p extensions
git clone https://github.com/FunplayAI/funplay-cocos-mcp.git extensions/funplay-cocos-mcp

Then restart Cocos Creator or reload extensions from the editor.

For a non-git install, download Funplay.CocosMcp.v<version>.zip from the GitHub Releases page, unzip it, and move the extracted funplay-cocos-mcp folder into your project extensions/ directory.

You can also install it globally by copying the folder into your Cocos Creator user extensions directory.

2. Start the MCP Server

Open the editor menu:

Funplay > MCP Server

The server runs on http://127.0.0.1:8765/ by default.

If the configured port is already occupied, the extension first checks whether the existing listener belongs to the same Cocos project. Same-project listeners are reused safely; unrelated listeners trigger automatic fallback to the next available local port.

The panel is intentionally small:

• Enable or disable the MCP server
• Open focused Tool Exposure, MCP Settings, and Activity windows
• Automatically check the installed version against the latest GitHub release
• Open the release page or install verified release packages from the panel
• Configure AI clients with one click and preview the selected client config
• Keep advanced tool profile editing, transport settings, diagnostics, and logs out of the main server window

The separate Tool Exposure window uses grouped tool lists with per-tool toggles and category select/clear actions. The Activity window uses a single recent-call stream with OK / ERR / INT badges, matching the simpler Funplay Unity MCP information architecture instead of putting every maintenance workflow into the main server panel.

3. Configure Your AI Client

Use the built-in MCP Client Config section in the Funplay > MCP Server panel first.

Select your target client, click One-Click Configure, and the extension writes the recommended MCP config entry for you.

The MCP server name written to clients is:

funplay_cocos

If you prefer to edit config files manually, use the examples below as fallback references.

Claude Code / Claude Desktop

{
  "mcpServers": {
    "funplay_cocos": {
      "type": "http",
      "url": "http://127.0.0.1:8765/"
    }
  }
}

Cursor

{
  "mcpServers": {
    "funplay_cocos": {
      "url": "http://127.0.0.1:8765/"
    }
  }
}

VS Code

{
  "servers": {
    "funplay_cocos": {
      "type": "http",
      "url": "http://127.0.0.1:8765/"
    }
  }
}

Trae

{
  "mcpServers": {
    "funplay_cocos": {
      "url": "http://127.0.0.1:8765/"
    }
  }
}

Kiro

{
  "mcpServers": {
    "funplay_cocos": {
      "type": "http",
      "url": "http://127.0.0.1:8765/"
    }
  }
}

Codex

[mcp_servers.funplay_cocos]
url = "http://127.0.0.1:8765/"

Optional: npm stdio Wrapper

If your MCP client prefers a local stdio command, install the npm wrapper after starting the Cocos editor server:

npm install -g funplay-cocos-mcp

Example MCP client entry:

{
  "mcpServers": {
    "funplay_cocos": {
      "command": "funplay-cocos-mcp",
      "env": {
        "FUNPLAY_COCOS_MCP_URL": "http://127.0.0.1:8765/"
      }
    }
  }
}

The wrapper bridges stdio MCP traffic to the embedded Cocos HTTP endpoint. You can also run it with npx funplay-cocos-mcp --url http://127.0.0.1:8765/.

4. Verify the Connection

Open your AI client and try a few safe requests first:

• "Call get_project_info and summarize the current Cocos project."
• "Read cocos://project/context and tell me the editor status."
• "Use execute_javascript with context: \"scene\" to return the active scene name."
• "Use execute_javascript with context: \"editor\" to return the project path."

If these work, the MCP server, resources, prompts, and primary execution tool are connected correctly.

For local transport debugging, the panel can copy these commands, or you can run them directly:

curl http://127.0.0.1:8765/health
curl http://127.0.0.1:8765/tools

5. Start Building

Try a higher-level prompt in your AI client:

Create a login page UI in the current Cocos scene with account/password fields, a login button, and a guest-login button. Use execute_javascript first, inspect the hierarchy, then capture a screenshot.

Before You Start

• This extension is Editor-only. It is meant to automate Cocos Creator, not to add runtime dependencies to your final game build.
• The MCP server listens on http://127.0.0.1:8765/ by default.
• If the configured port is busy, the server automatically falls back to the next available port and the panel/client config use the actual running port.
• GET /health and GET /tools are read-only debug endpoints for quick local checks outside an MCP client.
• The default core profile exposes 37 high-signal tools. Switch to full for all 102 tools, or use custom to include/exclude tool categories and individual tools.
• The panel checks GitHub releases automatically and also supports manual checks.
• One-click update downloads the GitHub Release zip, verifies SHA256SUMS.txt, backs up the current extension, replaces the package files, and reloads the extension when the Cocos package API supports it. If reload is unavailable, restart Cocos Creator after installation. Git worktree and symlink installs are intentionally left to manual git pull or package replacement.
• Streamable HTTP responses follow the MCP transport requirements for Accept, MCP-Protocol-Version, JSON-RPC notifications/responses, and optional Mcp-Session-Id sessions.
• Tool listings include MCP outputSchema and annotations; structured tool results use a standard envelope with ok, tool, callId, summary, data, and follow-up refs.
• execute_javascript safety checks are enabled by default. They block obvious risky filesystem and shell patterns such as delete/truncate calls, raw writable streams, path traversal, user/system absolute paths, and child_process. This is a guardrail, not a full sandbox; a call can explicitly pass safety_checks: false when you have reviewed the risk.
• All exposed MCP tools execute directly. There is no extra approval toggle inside the Cocos extension.
• File tools and cocos://asset/path/... resources are restricted to the active Cocos project root.
• The recommended workflow is execute_javascript first, then focused helper tools for screenshots, diagnostics, assets, and inspection.
• If you change the server port or tool exposure in the panel, the extension saves the config and restarts the server when needed.

Why This Project

• execute_javascript First — One high-flexibility JavaScript tool can orchestrate scene/runtime work and editor-side automation without flooding AI clients with too many narrow tool calls
• Embedded Cocos Extension — No separate Python daemon or external bridge process is required for the Cocos-side plugin
• One-Click Client Configuration — Configure Claude Code, Cursor, VS Code, Trae, Kiro, and Codex directly from Cocos Creator
• Project Context Built In — Exposes live project, scene, selection, script diagnostics, logs, and interaction-history resources
• Focused by Default, Full When Needed — core reduces tool-list noise; full exposes every available tool; custom plus saved profiles lets you tune and restore tool exposure by category or tool
• Visual Validation — Scene/editor/preview screenshots and input simulation help AI verify UI and gameplay changes

Highlights

• 102 Built-in Tools — Scene hierarchy, editor state, selection workflows, prefabs, assets, asset dependencies, project instructions, UI creation, components, files, logs, script diagnostics, screenshots, runtime control, build/preview helpers, editor preferences, event binding, and input simulation
• Primary Unified Tool — execute_javascript supports both scene and editor contexts
• Resources & Prompts — Live project/log resources plus reusable workflows like script fixing, scene validation, and playable prototype creation
• Cocos Panel UI — A compact Funplay > MCP Server dashboard plus focused Tool Exposure, MCP Settings, and Activity windows for larger workflows
• Screenshot and Input Support — Capture editor/scene/game/preview screenshots and send Electron-level mouse/keyboard events
• Vendor Agnostic — Works with any AI client that supports MCP over HTTP JSON-RPC

Relationship to Funplay MCP for Unity

Funplay MCP for Cocos follows the same design principles as Funplay MCP for Unity, adapted to Cocos Creator's JavaScript/TypeScript editor environment.

Area	Funplay MCP for Cocos	Funplay MCP for Unity
Editor integration	Cocos Creator extension	Unity Editor package
Embedded server	Built-in HTTP MCP server	Built-in HTTP MCP server
Primary execution tool	execute_javascript	execute_code
Primary language	JavaScript in scene/editor contexts	C# in Unity editor/runtime contexts
Default profile	core with 37 tools	core focused tool profile
Full profile	102 tools plus custom exposure	79 tools
Client setup	One-click config panel	One-click config window

MCP Capabilities

The current package exposes four capability layers:

• Tools — 37 tools in core, 102 tools in full, plus custom include/exclude rules and saved tool profiles
• Primary execution — execute_javascript for scene/runtime and editor/browser automation
• Prompts — fix_script_errors, create_playable_prototype, scene_validation, and auto_wire_scene
• Resources — project context, scene summaries, current selection, script diagnostics, asset selection, logs, and MCP interaction history

For the generated tool reference, including categories, profiles, and read/mutation hints, see docs/TOOLS.md.

The default core set is intentionally small: execute_javascript, execute_scene_script, execute_editor_script, get_editor_state, get_tool_catalog, check_for_updates, get_selection, list_project_instructions, read_project_instruction, set_selection, get_project_info, get_build_status, get_scene_info, get_hierarchy, list_scenes, open_scene, inspect_prefab, validate_prefab_references, inspect_prefab_instance, list_assets, inspect_asset, inspect_asset_dependencies, validate_asset_dependencies, open_asset, select_asset, run_script_diagnostics, get_recent_logs, search_project_logs, clear_logs, validate_scene, get_performance_snapshot, get_script_diagnostic_context, get_runtime_state, capture_editor_screenshot, capture_scene_screenshot, capture_preview_screenshot, and list_editor_windows.

Built-in Resources

Resource	Description
cocos://project/context	Full project and editor context
cocos://project/summary	Short project summary
cocos://scene/active	Active scene snapshot
cocos://scene/current	Alias for t