Choose theme
AI Visuals
MCP for Unity
MCP for Unity connects an AI assistant to the Unity Editor so it can work with scenes, GameObjects, assets and C# scripts through tools.
The CoplayDev repository contains the Unity package and its Python server. The project says it is maintained by Aura and is not affiliated with Unity Technologies. Use this as a first read, not a recommendation. Open the original project before trusting details like terms, limits, privacy, cost, setup, or safety.
What it is
An assistant connection to the Editor
The Model Context Protocol connection lets a compatible assistant call Unity tools. Those calls can inspect the project or change its objects, files and settings.
Why it stands out
Tools grouped around Unity work
Core scene, script and asset tools are enabled by default. Other groups cover animation, UI, visual effects, testing, profiling and asset generation.
Availability
Package, server and public source
The installation guide offers Git URL, Unity Asset Store and OpenUPM paths. The repository declares MIT for the code; see the repository for current terms.
Why it matters
What makes it useful
For a scene blockout, an assistant can create GameObjects, add components and change material properties through the documented Editor tools. This gives requests about objects and their appearance a route into the scene you are working on. The console tool also returns Editor messages when you need to inspect errors.
What to know
Where it fits
Install the package into your Unity project, then connect its server to an MCP client. The setup window handles dependency checks and client configuration. Your chosen assistant supplies the model interaction; MCP for Unity supplies access to Editor operations. The project documentation distinguishes the main installation branch from the beta branch.
Notable points
What stands out
A missing animation or test tool may simply belong to an inactive group. The tool-groups guide describes using manage_tools to activate that group for the session, after which its tools appear in the next listing. This helps distinguish an unavailable operation from one that has not been exposed to the assistant yet.
Before using
What to review
The installation guide requires Unity 2021.3 LTS or newer, Python 3.10+ with uv, and an MCP client. Follow its client-specific connection instructions; a configured client may still need its own MCP toggle enabled.
The tool reference includes modification and deletion operations. Review which tools your assistant can use and inspect its changes before keeping them. Optional asset-generation tools require your own provider keys.
The multi-instance guide says a command that times out after execution begins may still have changed Unity. It recommends checking before retrying those operations, since a retry can repeat the effect.
Reader fit
Who may find it relevant
Useful to Unity developers and technical artists who want assistant help with scene setup or repetitive Editor work. When several projects are open, the routing guide shows how to select the target Editor for a session or an individual call, so you can name which project the work should reach.
Editorial note
Why LifeHubber lists it
We list MCP for Unity because adding behavior to a prototype can involve both a C# file and components on scene objects. Its script and object tools give an assistant access to both sides of that work. For a developer moving between code and scene setup, this means a proposed behavior can be expressed through project edits they can examine together, rather than leaving the object setup entirely in chat instructions. The developer still needs to judge whether the result behaves as intended.
Source links
Source materials
Reader note
Before relying on this entry
LifeHubber lists entries to help readers inspect AI projects, not to endorse them or prove they are safe, suitable, accurate, maintained, or right for a specific use. We do not verify every entry in depth. Before relying on anything listed, review the original materials, terms, privacy practices, limits, and risks that matter for your situation.
More in Ecosystem
Keep browsing this category
Explore more AI ecosystem resources.
Laya
NandhaKishorM/laya
An early Apache-2.0 model family and Python runtime for bounded choice, score, and yes-or-no decisions, with English, multilingual, and task-specialized checkpoints plus a router that selects between them.
SPACE by Perplexity
perplexityai/SPACE
Code-execution infrastructure with Firecracker workspaces, HTTP command sessions and separate workspace lifecycles for keeping, pausing, suspending or deleting environments.
OpenDataLoader PDF
opendataloader-project/opendataloader-pdf
A PDF toolkit that combines deterministic local extraction to Markdown, JSON, HTML, text, or annotated PDF with optional AI handling for complex pages, Tagged PDF structure reading, and automated Tagged PDF output.
For project maintainers
Listed here? You can use the badge.
If you maintain a project with a current LifeHubber listing, you may add the optional “Listed on LifeHubber AI Resources” badge to its README, docs, or website. No introduction or permission request is needed.
