Skip to main content
hc
Submit
mcpSource-backedReview first Safety ✓ Privacy ✓

AI Game Developer Unity MCP Server

Unity MCP server, plugin, CLI, and skill generator for controlling Unity Editor and runtime projects from MCP clients through built-in game-dev tools.

by Ivan Murzak·added 2026-06-06·
Claude CodeClaude Desktop
HarnessClaude CodeClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • AI Game Developer can create, move, copy, modify, and delete Unity assets, scenes, GameObjects, components, scripts, packages, and generated project files.
  • Tools include dynamic C# script execution, C# reflection method lookup and calls, package installation/removal, Unity test execution, editor state changes, play mode control, screenshots, and profiler access.
  • The MCP server supports streamable HTTP and stdio; HTTP deployments should require a bearer token and stay bound to trusted interfaces.
  • Server variables include optional authorization and webhook settings; webhook endpoints can receive tool, prompt, resource, connection, and authorization events.
  • Unity runtime connections can expose compiled game state or in-game behavior to an MCP client, not just editor-only project data.
  • Use source control, backups, tool filtering, and explicit review before allowing destructive tools such as asset deletion, package removal, script execution, or reflection calls.

Privacy notes

  • Tool calls may expose Unity project paths, asset names, scene hierarchy, serialized object data, scripts, logs, screenshots, profiler metrics, test output, package metadata, and runtime state.
  • MCP config files and Unity plugin config can contain server URLs, connection modes, bearer tokens, authorization settings, enabled tool IDs, and cloud or local endpoint details.
  • Optional webhooks can receive tool, prompt, resource, connection, authorization, and token-bearing request data.
  • Screenshots from Game View, Scene View, cameras, or isolated GameObjects may include proprietary artwork, level design, UI, debug overlays, or unreleased game content.
  • Generated skills and AI-client configuration files can reveal available tools, project structure, installed packages, and local workflow assumptions.

Prerequisites

  • Unity project using Unity 2022.3 or newer for the current package metadata.
  • Unity Hub or a local Unity Editor installation.
  • Node.js 20.19 or newer, or Node.js 22.12 or newer, for `unity-mcp-cli`.
  • An MCP client such as Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, GitHub Copilot, Cline, or another supported client.
  • Project backup, version control, and a reviewed tool allowlist before granting an AI agent write access to a Unity project.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
20 minutes
Difficulty
advanced
Tool listing metadata
Disclosure
Apache-2.0 open source Unity MCP project by Ivan Murzak. It is a separate project from the existing CoplayDev Unity MCP Server catalog entry.
Full copyable content
{
  "mcpServers": {
    "ai-game-developer": {
      "type": "streamableHttp",
      "url": "LOCAL_UNITY_MCP_ENDPOINT"
    }
  }
}

About this resource

Content

AI Game Developer Unity MCP Server is Ivan Murzak's Unity MCP project for connecting MCP clients to Unity Editor and runtime workflows. It combines a Unity plugin, an MCP server, a cross-platform CLI, generated AI skills, and a large default tool set for game-development automation.

Use it when an agent needs to work inside a real Unity project: inspecting assets and scenes, creating or modifying GameObjects, updating scripts, running tests, installing packages, capturing screenshots, reading profiler data, or connecting to runtime builds. Treat it as a high-trust development bridge rather than a read-only reference server.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, MCP server docs, default tool reference, CLI docs, npm package metadata, license, and Unity package metadata for current setup details.

Features

  • Install and configure the Unity plugin through unity-mcp-cli.
  • Connect MCP clients over streamable HTTP or stdio.
  • Run local automatic server binaries, Docker, or manual release binaries.
  • Generate MCP client config and Unity-focused AI skills for supported clients.
  • Create, find, copy, move, modify, delete, refresh, and inspect Unity assets.
  • Create, open, save, unload, and inspect scenes and scene hierarchies.
  • Create, duplicate, destroy, find, parent, and modify GameObjects and components.
  • Read, create, update, delete, compile, and execute C# scripts.
  • Search, add, list, and remove Unity packages.
  • Capture Game View, Scene View, camera, or isolated GameObject screenshots.
  • Run EditMode or PlayMode tests and inspect Unity console logs.
  • Read editor state, selection, profiler status, memory, rendering, and script timing data.

Installation

Install the CLI and add the plugin to a Unity project:

npm install -g unity-mcp-cli
unity-mcp-cli install-plugin ./MyUnityProject
unity-mcp-cli open ./MyUnityProject

The repository also documents Unity Editor UI setup through Window/AI Game Developer, OpenUPM installation, Docker, and release-binary deployments.

For streamable HTTP, use the default local endpoint:

{
    "mcpServers": {
      "ai-game-developer": {
        "type": "streamableHttp",
      "url": "LOCAL_UNITY_MCP_ENDPOINT"
      }
    }
  }

For stdio or Docker, follow the server docs for the exact binary or Docker command and matching --client-transport value.

Use Cases

  • Ask an agent to create or modify Unity scene objects and prefabs.
  • Generate or update C# gameplay scripts and run Unity tests.
  • Inspect project assets, packages, shaders, scene data, and console logs.
  • Capture screenshots during visual debugging or gameplay iteration.
  • Run profiler queries while optimizing frame timing, rendering, memory, or script execution.
  • Generate Unity-aware skills for AI clients so they use project-specific tools more consistently.
  • Connect compiled Unity runtime builds to MCP for in-game debugging or AI behavior experiments.

Safety and Privacy

AI Game Developer Unity MCP can alter real Unity projects. Keep the project in version control, start with a small enabled-tool set, and avoid destructive tools until the agent's workflow is understood. Pay special attention to package installation, script execution, reflection method calls, scene saves, asset deletion, and runtime connections.

If you expose the server over HTTP, use authentication, keep it on trusted interfaces, and review webhook configuration. Tool calls can reveal proprietary game assets, source code, scene design, screenshots, logs, profiler data, and runtime state to the MCP client and any configured webhooks.

Duplicate Notes

The catalog already includes Unity-related MCP entries, including the separate CoplayDev Unity MCP Server. This entry covers IvanMurzak/Unity-MCP, its unity-mcp-cli package, AI Game Developer Unity plugin, generated skills, and HTTP/stdio server deployment path.

#unity#game-development#editor#runtime#automation

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.