Marketplace for trusted AI agent skills

Skill Detail

Control Unity Editor scenes and assets through MCP for Unity

Connect MCP-compatible agents to Unity Editor so they can inspect scenes, manage assets, edit scripts, run tests, and automate game-development tasks.

Integrations & ConnectorsMCP
Integrations & Connectors MCP Security Reviewed
⭐ 10.6k GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill control-unity-editor-scenes-and-assets-through-mcp-for-unity Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
View source Documentation
At a glance
Tools required
Unity Editor, Python 3.10+, MCP-compatible client such as Claude, Codex, VS Code, or Cursor
Install & setup
In Unity Package Manager, choose Add package from git URL and add https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main, then run Window -> MCP for Unity -> Configure All Detected Clients before prompting the connected MCP client.
Author
CoplayDev
Publisher
Organization
Last updated
Jun 13, 2026
Quick brief

Use MCP for Unity when an agent needs to operate inside an active Unity project instead of giving instructions for a human to replay manually. The workflow is to install the Unity package, configure detected MCP clients, open the Unity Editor, and let the agent create or modify scene objects, assets, scripts, tests, and related project state. The scope is Unity Editor automation through MCP, not a general game-development framework or Unity product card.

How it works

What this skill actually does

Inputs and prerequisites: Unity Editor, Python 3.10+, MCP-compatible client such as Claude, Codex, VS Code, or Cursor.

Setup notes: In Unity Package Manager, choose `Add package from git URL` and add `https://github.com/CoplayDev/unity-mcp.git?path=/MCPForUnity#main`, then run `Window -> MCP for Unity -> Configure All Detected Clients` before prompting the connected MCP client.

Source and verification boundary: use https://coplaydev.github.io/unity-mcp/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.

Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.