unity
A Unity MCP server that allows MCP clients like Claude Desktop or Cursor to perform Unity Editor actions.
claude mcp add --transport stdio wondeks-unity-mcp standalone \ --env UNAVAILABLE="Configuration not specified in README; configure locally as needed"
How to use
The Unity MCP server lets MCP clients such as Claude Desktop or Cursor send requests to the Unity Editor to perform a variety of editor actions. It acts as a central hub that translates MCP protocol messages into Unity Editor operations, enabling automation, asset management, scene modifications, and other editor tasks from remote clients. By connecting an MCP client to this server, you can trigger predefined Unity actions, orchestrate workflows, and leverage AI-assisted capabilities integrated into the server to streamline development workflows.
Once the server is up, configure your MCP clients to point to the Unity MCP server endpoint. From there, you can browse available editor actions, chain operations together, and send commands to the Unity Editor to execute tasks such as transforming objects, manipulating assets, modifying scenes, or running automated editor scripts. The goal is to provide a seamless bridge between external MCP clients and the Unity Editor to improve efficiency and consistency across development tasks.
How to install
Prerequisites:
- Unity installed on your machine (compatible with the server package).
- Access to the Unity MCP release package described in the repository (a downloadable ZIP in this case).
- JavaScript/Node.js environment or any runtime the server requires (per packaging; not explicitly specified in the README).
Installation steps:
- Download the latest Unity MCP release package from the repository release link provided in the README (the ZIP file).
- Extract the release ZIP to a desired directory on your machine.
- Follow any included installation/integration instructions within the release package (readme or docs inside the ZIP) to install dependencies, set up Unity integration, and configure the server to run.
- Start the server using the recommended startup command from the release package (the README does not specify a concrete command; use the instructions provided in the ZIP's docs).
- Configure your MCP clients (e.g., Claude Desktop, Cursor) to connect to the server endpoint once the server is running.
- Verify connectivity and begin sending Unity Editor action requests from MCP clients.
Additional notes
Tips and considerations:
- The README emphasizes AI integration and a wide range of Unity Editor actions; explore the provided release package for example actions or scripts.
- Ensure the Unity editor and the MCP server are running on compatible versions to avoid integration issues.
- If you encounter connection problems, verify network access, server listen address/port, and any required authentication tokens described in the release docs.
- The repository provides download links to a ZIP containing Editor/Commands; refer to the contents of that package for exact setup steps, available actions, and how to trigger them from MCP clients.
- If environment variables are required by the server, set them in the server's process environment as described in its documentation or release notes.
Related MCP Servers
mcp-proxy
An MCP proxy server that aggregates and serves multiple MCP resource servers through a single HTTP server.
dexto
A coding agent and general agent harness for building and orchestrating agentic applications.
mcp-graphql
Model Context Protocol server for GraphQL
Remote
A type-safe solution to remote MCP communication, enabling effortless integration for centralized management of Model Context.
git
An MCP (Model Context Protocol) server enabling LLMs and AI agents to interact with Git repositories. Provides tools for comprehensive Git operations including clone, commit, branch, diff, log, status, push, pull, merge, rebase, worktree, tag management, and more, via the MCP standard. STDIO & HTTP.
boilerplate
TypeScript Model Context Protocol (MCP) server boilerplate providing IP lookup tools/resources. Includes CLI support and extensible structure for connecting AI systems (LLMs) to external data sources like ip-api.com. Ideal template for creating new MCP integrations via Node.js.