unity-mcp: Skill for Claude Code

.claude/skills/unity-mcp-skill/SKILL.md

unity-mcp-orchestrator is a skill for Claude Code from CoplayDev/unity-mcp. It costs 72 tokens per session (4,000 once invoked), scanned A, original, MIT.

A guide for controlling the Unity game editor through MCP, a standard way for software tools to exchange commands and data.

In plain words
What is it for?
Use it to create or modify GameObjects, scenes, scripts, and tests, and to inspect the Unity console or capture screenshots.
Why use it?
It provides a consistent workflow for inspecting Unity projects, making changes, and checking for errors afterward.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is CoplayDev/unity-mcp's own configuration. It tells Claude Code how to work on unity-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unity-mcp configures →

About the project

Unity MCP connects AI coding assistants to the Unity Editor through the Model Context Protocol, letting them manage game assets, scenes, scripts, tests, and builds. It is for developers who want to control Unity workflows with natural-language requests, and the catalogue entries provide add-ons for using the project.

CoplayDev/unity-mcp · 15,028 stars · on GitHub · coplaydev.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to CoplayDev/unity-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/CoplayDev/unity-mcp/beta/.claude/skills/unity-mcp-skill/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/CoplayDev/unity-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for unity-mcp-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/skills/coplaydev/unity-mcp/unity-mcp-skill/github.svg)](https://agentmods.dev/skills/coplaydev/unity-mcp/unity-mcp-skill)
Your own site
<a href="https://agentmods.dev/skills/coplaydev/unity-mcp/unity-mcp-skill"><img src="https://agentmods.dev/badge/skills/coplaydev/unity-mcp/unity-mcp-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for unity-mcp-orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/skills/coplaydev/unity-mcp/unity-mcp-skill"><img src="https://agentmods.dev/badge/skills/coplaydev/unity-mcp/unity-mcp-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,000 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.04000
Opus 5.5 $0.00029 $0.01600
Sonnet 5.5 $0.00014 $0.00800
Haiku 4.5 $0.00007 $0.00400

Measured 9d ago against content hash 7a1728157072, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unity-mcp-orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/unity-mcp-skill/SKILL.md · 291 lines

How it starts

The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity-MCP Operator Guide

This skill helps you effectively use the Unity Editor with MCP tools and resources.

Template Notice

Examples in references/workflows.md and references/tools-reference.md are reusable templates. They may be inaccurate across Unity versions, package setups (UGUI/TMP/Input System), and project-specific conventions. Please check console, compilation errors, or use screenshot after implementation.

Before applying a template:

  • Validate targets/components first via resources and find_gameobjects.
  • Treat names, enum values, and property payloads as placeholders to adapt.

Quick Start: Resource-First Workflow

Always read relevant resources before using tools. This prevents errors and provides the necessary context.

1. Check editor state     → mcpforunity://editor/state
2. Understand the scene   → mcpforunity://scene/gameobject-api
3. Find what you need     → find_gameobjects or resources
4. Take action            → tools (manage_gameobject, create_script, script_apply_edits, apply_text_edits, validate_script, delete_script, get_sha, etc.)
5. Verify results         → read_console, manage_camera(action="screenshot"), resources

If a tool you need is not in your tool list, it is not necessarily missing. Check these before troubleshooting the connection:

  • Project custom tools (C# [McpForUnityTool]): with project-scoped tools enabled on the server, they are not callable by name. List them via mcpforunity://custom-tools and run them with execute_custom_tool(tool_name="...", parameters={...}). With it disabled, they are registered as ordinary tools and appear in your list.
  • Disabled tool groups: over HTTP, a session starts with only the core group enabled. Over stdio, all groups start enabled and are then synced to the tool toggles in the Unity editor, so a tool can still be hidden. manage_tools(action="list_groups") shows the groups, manage_tools(action="activate", group="...") enables one.

Critical Best Practices

Read the full file on GitHub · 291 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago Changed · +4 lines 7a1728157072
  2. 27d ago Changed · +5 lines 3ac889d099d7
  3. 1mo ago First seen · 282 lines · 72 tokens per session scan A 45a6fd0007ee

Subscribe to this mod's changes

unity-mcp-orchestrator is a skill published in the GitHub repository CoplayDev/unity-mcp (15,028 stars, last pushed 8d ago), licensed MIT. It adds 72 tokens to every session and 4,000 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

tests-run

Execute Unity tests (EditMode or PlayMode) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.

IvanMurzak/Unity-MCP · 68 tokens

screenshot-isolated

Render a target GameObject from a chosen camera angle with optional layer-based isolation, configurable background (solid/skybox/transparent), multi-light setup via JSON, and Composite (2x2 Front/Right/Back/Top) mode. Returns a PNG image. When isolated=true, inactive children may briefly fire OnEnable — see the body…

IvanMurzak/Unity-MCP · 78 tokens

script-execute

Compiles and executes C# code dynamically using Roslyn. Supports a full-code mode (default) and a body-only mode — see the skill body for the difference and for how to pass Unity object references as parameters.

IvanMurzak/Unity-MCP · 48 tokens

unity-skill-create

Create a new skill (MCP tool) for the Unity Editor by writing a C# (.cs) file that Unity compiles into the project. After compilation the new tool becomes callable through MCP. The file must be a partial class decorated with [AiToolType], each tool method must be decorated with [AiTool], the class name should match…

IvanMurzak/Unity-MCP · 142 tokens

unity-rql

How to read and change anything in the Unity Editor with RQL (rql-query / rql-mutate / rql-schema): the query language, operators, sources (scene objects, assets, scenes, prefabs, console logs, Editor state), Editor operations (create, add components, scenes, prefabs, assets, selection, Play Mode) and what installed…

IvanMurzak/Unity-MCP · 82 tokens

package-list

List all UPM packages installed in the Unity project — name, version, source, description. Optionally filter by source (registry, embedded, local, git, built-in, local tarball), by name/display/description substring, and by direct-dependency-only.

IvanMurzak/Unity-MCP · 57 tokens