FunseaAI Unity MCP

Funplay MCP for Unity

The Most Advanced MCP Server for Unity Editor

中文 | English

💖 If you find this project useful, please consider giving it a Star. It helps more Unity developers discover it and supports ongoing development.

---

Funplay MCP for Unity is an MIT-licensed Unity Editor MCP server that lets AI assistants like Claude Code, Cursor, Kimi Code, LM Studio, Windsurf, Codex, and VS Code Copilot operate directly inside your running Unity project.

Describe your game in one sentence — your AI assistant builds it in Unity through Funplay MCP for Unity's built-in tools for scene creation, script generation, runtime validation, input simulation, performance analysis, and editor automation.

*"Build a snake game with a 10x10 grid, food spawning, score UI, and game-over screen"*

Your AI assistant handles it through Funplay MCP for Unity: creates the scene, generates all scripts, sets up the UI, and configures the game logic — all from a single prompt.

16-second demo — AI generates a 3D model and integrates it into the scene end-to-end. Watch HD MP4 .

Quick Start

If you just want to get connected fast, do these three things:

• Install the Unity package from the Git URL
• Start Funplay > MCP Server
• Use the built-in one-click client configuration

1. Install via UPM (Git URL)

In Unity, go to Window → Package Manager → + → Add package from git URL:

https://github.com/FunplayAI/funplay-unity-mcp.git

💡 Before you clone or install, a quick ⭐ on GitHub would be greatly appreciated.

Optional: Install via OpenUPM

If you want Unity Package Manager to show registry-backed package version history and allow version selection, install from OpenUPM instead of Git.

Using the OpenUPM CLI:

openupm add com.gamebooom.unity.mcp

Or add the scoped registry manually in Packages/manifest.json:

{

"scopedRegistries": [ { "name": "OpenUPM", "url": "https://package.openupm.com", "scopes": [ "com.gamebooom" ] } ], "dependencies": { "com.gamebooom.unity.mcp": "0.7.5" } }

If you installed from a Git URL before, remove the Git dependency first, then install from OpenUPM. Git-installed packages only show the resolved Git version in Unity and do not get the registry-backed Version History list.

2. Start the MCP Server

Menu: Funplay → MCP Server to start the server.

A new project gets its own port, derived from the project path, so two editors opened on different projects never fight over one port. The MCP Server window shows the exact URL (http://127.0.0.1: /mcp/project/ /); the one-click configuration writes that URL for you. Type a port in Server Port to pin a fixed one (CI, a firewall rule) and Use Per-Project Port to derive one instead.

Upgrading preserves the existing pinned port, but v0.7.1 binds generated URLs to the project. Old root URLs remain readable; writes require a verified expected_context. Re-run Reconfigure MCP + Skills in the existing blue Skills notice card and reconnect your client, or explicitly pass the guard from an independently verified intended Editor. Click Use Per-Project Port when you want that project to run beside another editor. See Running Several Unity Projects at Once for the full setup guide.

If the window reports a fallback port, do not use a client entry that still targets the occupied stable port; it could reach the process that owns that port. One-click configuration stays blocked until you click Use Per-Project Port or Pin Current Port and the server finishes restarting.

Direct in-process HTTP is the default transport. If you need stronger connection continuity across Unity script recompiles or Play Mode domain reloads, enable Experimental Broker Mode in the MCP Server window. It runs a tiny local broker with Unity's bundled Mono, keeps the same 127.0.0.1 port for MCP clients, and requires no client config change.

Open Funplay → Tool Exposure if you want to edit the exact tools exposed by core or full.

Open Funplay → MCP Settings if you need to adjust execute_code safety defaults or plugin debug logging.

3. Configure Your AI Client

Use the built-in One-Click MCP Configuration in the Funplay > MCP Server window first.

Select your target client, click Configure, and the package writes the recommended MCP config entry for you.

For Claude Code, Cursor, Codex, OpenCode, and DeepSeek Harness, click Configure + Skills to also install both built-in project skills.

If you want project-specific AI guidance for the current Unity project, open Funplay → Project Skills to choose supported platforms and install the built-in unity-mcp-workflow and unity-ui-composition skills. The UI skill covers responsive portrait and landscape uGUI work.

Version 0.7.0 keeps these two built-in skills and adds four task-specific references, informed by the official Unity plugin 0.1.8-beta: UI framework selection, safe Sprite importer edits, TMP/localization verification, and package readiness. Agents read only the references relevant to their task; no default tools or extra skills are added. MCP-first operation, project conventions, prefab preservation and design fidelity remain authoritative. Update existing installations through Project Skills; missing or outdated references also trigger the skills-update notice. User-owned reference files are protected from overwrite.

Version 0.7.1 adds execution-trust guidance to both built-ins, including project identity, actual frame progress, strict input routes, owned verification cleanup and conditional handling of blocking native Unity dialogs. The shared blue setup card reports MCP and Skills issues with one Reconfigure MCP + Skills action; resolving one issue preserves the other. See execution trust and migration.

If you prefer to edit config files manually, use the examples below as fallback references. Replace with this project's entry name, with its port and with the ID in its full bound URL -- copy these from the MCP Server window, not from a different Editor:

Claude Code / Claude Desktop

{

"mcpServers": { "funplay- ": { "type": "http", "url": "http://127.0.0.1: /mcp/project/ /" } } }

Cursor

{

"mcpServers": { "funplay- ": { "url": "http://127.0.0.1: /mcp/project/ /" } } }

LM Studio

LM Studio's mcp.json location can vary by version and platform. Prefer Program > Install > Edit mcp.json in LM Studio. Funplay's one-click Configure button opens LM Studio's lmstudio://add_mcp link and only updates an existing config file if one is already present, instead of creating a guessed path.

{

"mcpServers": { "funplay- ": { "url": "http://127.0.0.1: /mcp/project/ /" } } }

VS Code

{

"servers": { "funplay- ": { "type": "http", "url": "http://127.0.0.1: /mcp/project/ /" } } }

Trae

{

"mcpServers": { "funplay- ": { "url": "http://127.0.0.1: /mcp/project/ /" } } }

Kiro

{

"mcpServers": { "funplay- ": { "type": "http", "url": "http://127.0.0.1: /mcp/project/ /" } } }

Kimi / Kimi Code

Current Kimi Code releases load project-level MCP servers from .kimi-code/mcp.json (official MCP documentation). Funplay's one-click Configure target writes there so the current Unity server is only visible to Kimi sessions started in this project. If the machine only has the legacy Kimi CLI data directory, it writes the compatible user-level ~/.kimi/mcp.json instead. Start a new Kimi session from the Unity project root after configuring; on first use, review the loopback URL and trust the workspace. The generated project file contains this machine's local port, so normally keep it uncommitted unless the team deliberately shares one pinned port.

{

"mcpServers": { "funplay- ": { "url": "http://127.0.0.1: /mcp/project/ /" } } }

Codex

[mcp_servers.funplay-<project>]

url = "http://127.0.0.1: /mcp/project/ /"

OpenCode

Written to the repository's own .opencode/opencode.json (not the global config), so only OpenCode sessions started inside this repo see this editor's tools.

{

"mcp": { "funplay- ": { "type": "remote", "url": "http://127.0.0.1: /mcp/project/ /", "enabled": true } } }

DeepSeek Harness

Written as a delimited managed block into every DeepSeek Harness profile's ~/.dsh/profiles/ /cordis.patch.yml, because DSH composes its plugins per launch through --profile and exposes no single active profile to target from outside. Anything outside the block is preserved on reconfigure, and deleting the block by hand uninstalls the entry.

# >>> funplay-mcp:funplay-<project> begin (managed by Funplay MCP -- reconfigure from Unity > Funplay > MCP Server)

Funplay Unity MCP endpoint served by this editor; tools appear as mcpfunplay- .

• insert:
• id: mcp-funplay- name: '@deepseek-ai/dsh-mcp-client' config: serverName: funplay- transport: streamable-http url: http://127.0.0.1: /mcp/project/ /

<<< funplay-mcp:funplay- end

Antigravity

Written to the workspace-local .agents/mcp_config.json with mcpServers entries using serverUrl for Funplay's Streamable HTTP endpoint. This keeps the server out of unrelated workspaces. Use a current Antigravity version supporting workspace MCP configuration, then reload its MCP servers.

The workspace root is the nearest ancestor containing .git (including a worktree's .git file), or the Unity project directory when it is outside Git. Open that directory as the Antigravity workspace. Configure + Skills places .agents/mcp_config.json, .agents/skills/, and the managed AGENTS.md block at this same root, including when the Unity project is