mcp-unity: Instructions file for Claude Code

CLAUDE.md

mcp-unity CLAUDE.md is an instructions file for Claude Code from st-VALVe/mcp-unity. It costs 1,242 tokens per session, scanned A, original, MIT.

Project instructions for developing MCP Unity, which connects coding agents to Unity Editor capabilities through a Node.js server and a WebSocket connection.

In plain words
What is it for?
Use them when building or testing the TypeScript server, Unity-side C# code, MCP tools, resources, WebSocket communication, or Unity integration.
Why use it?
They explain the project structure, development commands, data flow, and important defaults so changes are made in the correct part of the system.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

This is st-VALVe/mcp-unity's own configuration. It tells Claude Code how to work on mcp-unity 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 mcp-unity configures →

Reuse

Borrowing it

Nothing to install: this file belongs to st-VALVe/mcp-unity. 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/st-VALVe/mcp-unity/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/st-VALVe/mcp-unity

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 mcp-unity CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/st-valve/mcp-unity/claude-md/github.svg)](https://agentmods.dev/instructions/st-valve/mcp-unity/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/st-valve/mcp-unity/claude-md"><img src="https://agentmods.dev/badge/instructions/st-valve/mcp-unity/claude-md/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 mcp-unity CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/st-valve/mcp-unity/claude-md"><img src="https://agentmods.dev/badge/instructions/st-valve/mcp-unity/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,242 This file is loaded in full into every session.
When invoked 1,242 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01242 $0.01242
Opus 5.5 $0.00497 $0.00497
Sonnet 5.5 $0.00248 $0.00248
Haiku 4.5 $0.00124 $0.00124

Measured 2mo ago against content hash 6952b31352f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-unity CLAUDE.md 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 2mo 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.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

MCP Unity exposes Unity Editor capabilities to MCP-enabled clients (Cursor, Windsurf, Claude Code, Codex CLI, GitHub Copilot) through a two-tier architecture:

  • Unity Editor (C#): WebSocket server inside Unity that executes tools/resources
  • Node.js Server (TypeScript): MCP stdio server that bridges AI clients to Unity via WebSocket

Data flow: MCP Client ⇄ (stdio) ⇄ Node Server (Server~/src/index.ts) ⇄ (WebSocket) ⇄ Unity Editor (Editor/UnityBridge/McpUnityServer.cs)

Build & Development Commands

Node.js Server (Server~/)

npm install          # Install dependencies
npm run build        # Compile TypeScript to build/
npm run watch        # Watch mode compilation
npm start            # Run server (node build/index.js)
npm test             # Run Jest tests (uses --experimental-vm-modules)
npm run test:watch   # Watch mode testing
npm run inspector    # Launch MCP Inspector for debugging

Unity Side

  • Build/Test via Unity Editor
  • Tools > MCP Unity > Server Window for configuration
  • Window > General > Test Runner for EditMode tests

Key Directories

Editor/                       # Unity Editor package (C#)
├── Tools/                    # MCP tools (inherit McpToolBase)
├── Resources/                # MCP resources (inherit McpResourceBase)
├── Services/                 # TestRunnerService, ConsoleLogsService
├── UnityBridge/              # WebSocket server + message routing
│   ├── McpUnityServer.cs     # Singleton managing server lifecycle
│   └── McpUnitySocketHandler.cs  # WebSocket handler
└── Utils/                    # Logging, config, workspace helpers

Server~/                      # Node.js MCP server (TypeScript/ESM)
├── src/index.ts              # Entry point - registers tools/resources
├── src/tools/                # MCP tool definitions (zod + handler)
├── src/resources/            # MCP resource definitions
└── src/unity/mcpUnity.ts     # WebSocket client connecting to Unity

Read the full file on GitHub · 133 lines

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. 2mo ago First seen · 133 lines · 1,242 tokens per session scan A 6952b31352f0

Subscribe to this mod's changes

mcp-unity CLAUDE.md is an instructions file published in the GitHub repository st-VALVe/mcp-unity (10 stars, last pushed 5mo ago), licensed MIT. It adds 1,242 tokens to every session, about $0.0050 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 2026-08-31.

Related

mcp-unity CLAUDE.md compared with instructions from other repositories

mcp-unity CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp-unity CLAUDE.mdst-VALVe/mcp-unityInstructions file105mo agoMITA1,242Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode