OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
MCP & Tooling

Unity MCP

Unity MCP is an open-source developer integration that connects MCP-compatible AI coding assistants to Unity through editor tools, project-specific AI skills and a CLI. It also lets developers expose C# methods as callable tools.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Unity MCP — OpenViST project profile in MCP & Tooling.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want an MCP-compatible assistant to work with Unity project operations, or when you need to make selected C# methods available as tools.

Who it is for

  • Unity developers who want an AI coding assistant to interact with editor operations.
  • Teams looking to expose selected project-specific C# methods to an MCP-compatible assistant.

Documented uses

  • Connect an AI coding assistant to Unity editor tools.
  • Use AI assistance to generate game code and support development or testing tasks.
  • Expose a C# method as a tool an AI client can invoke.
Before you choose

Requirements & limits

The repository is public and lists an Apache-2.0 license. It names Claude, Gemini, GitHub Copilot and Cursor among compatible assistant ecosystems.

  • The assistant must support the MCP integration approach.
  • The repository distinguishes default Unity editor tools from generated, project-aware skills and custom C# tools.
  • Local stdio and remote HTTP configurations are described; Docker is referenced, but its setup requirements are not detailed here.
  • The repository also describes runtime use inside compiled games, including NPC behavior and debugging.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the Unity MCP plugin with the CLI

Install the Unity MCP plugin into an existing Unity project using the documented CLI flow.

Before you start

  • A Unity project whose path contains no spaces.
  • Node.js and npm, for installing and running the unity-mcp-cli.

Steps

  1. Install the CLI with the command below.

    Documented command
    npm install -g unity-mcp-cli

  2. Install the plugin into the project by running unity-mcp-cli install-plugin ./MyUnityProject.

  3. Open the Unity project; the README describes it as auto-connecting and generating skills.

Expected outcome

The Unity MCP plugin is installed in the project, ready for the documented Unity-side agent configuration.

Guide limitations

  • The project path cannot contain spaces.
  • This recipe covers plugin installation only; it does not document completing AI-agent configuration or verifying a connection.
Documentation 1 ↗
Source-based practical guide

Configure an AI agent from the Unity window

Use the Unity MCP window to generate AI skills or configure MCP for an installed project.

Before you start

  • The Unity MCP plugin is installed in the Unity project.
  • An AI agent/MCP client to configure.

Steps

  1. Open the Unity project.

  2. Open Window/AI Game Developer.

  3. Choose Auto-generate Skills (recommended) or Configure MCP.

  4. If the MCP client is not listed, use the raw JSON shown in the window and follow that client's instructions.

Expected outcome

The Unity window generates skills or provides MCP configuration for the selected client.

Guide limitations

  • Client-specific manual configuration instructions are not detailed here.
  • The README states that the raw JSON route requires following the individual MCP client's instructions.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Unity MCPConnect an AI coding assistant to Unity editor tools.CLI, Desktop, DockerThe repository is public and lists an Apache-2.0 license. It names Claude, Gemini, GitHub Copilot and Cursor among compatible assistant ecosystems.
OvertureInspect a coding agent’s planned steps and branches before code is written.Self-hosted, Server, WebOpen-source software under the MIT license. The documented setup runs the MCP server locally and opens its web interface at `http://localhost:3031` by default.
WigoloSearch the web and fetch pages for an agent’s research task.CLI, Self-hosted, ServerThe quickstart lists macOS, Linux and Windows, and requires Node.js 20 or later with about 1.5 GB of free disk space. The repository labels the project public beta.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 October 2026
Original website title
IvanMurzak/Unity-MCP · Official homepage title · retained in its source language
How we review sourcesSuggest a correction