What is unity_code_mcp CLAUDE.md?

Project instructions for a Rust-based MCP server that connects AI assistants with the Unity game editor, including log access and test management.

Use them when developing or reviewing this Unity integration, especially its handling of editor reloads, logs, and tests.

They give coding agents the project's purpose, architecture, technologies, and development rules when working on the server.

How hackerzhuli/unity_code_mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hackerzhuli/unity_code_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/hackerzhuli/unity_code_mcp/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/hackerzhuli/unity_code_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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hackerzhuli/unity_code_mcp/claude-md/github.svg)](https://agentmods.dev/instructions/hackerzhuli/unity_code_mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hackerzhuli/unity_code_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hackerzhuli/unity_code_mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hackerzhuli/unity_code_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hackerzhuli/unity_code_mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 550 This file is loaded in full into every session.

When invoked 550 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.

Model	Per session	Once invoked
Fable 5.1	$0.00550	$0.00550
Opus 5.5	$0.00220	$0.00220
Sonnet 5.5	$0.00110	$0.00110
Haiku 4.5	$0.00055	$0.00055

Measured 2mo ago against content hash ad58bfb1f7f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unity_code_mcp 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.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unity Code MCP Server - Project Rules

Project Purpose

This project aims to create a reliable Model Context Protocol (MCP) server that enables AI assistants to communicate effectively with Unity Editor. The primary motivation is to address the limitations of existing Unity MCP servers, particularly their inability to handle Unity's domain reload functionality, which causes Unity Editor components to become unavailable.

Core Objectives

Build a robust MCP server that survives Unity domain reloads
Provide essential Unity integration features:
- Retrieve Unity logs
- Execute and manage Unity tests
Serve as a component for the Unity Code Pro VS Code extension
Enable seamless AI-Unity Editor communication

Tech Stack

Core Technologies

Language: Rust
MCP Framework: rmcp (core dependency)
Async Runtime: Tokio (implicit dependency via rmcp)
Architecture: Single-threaded async to minimize complexity

Dependencies

rmcp: Primary MCP implementation
tokio: Async I/O runtime

Development Guidelines

Architecture Principles

Simplicity First: Use single-threaded async architecture to avoid unnecessary complexity

Code Standards

Rust Best Practices:
- Follow Rust naming conventions
- Maintain comprehensive error handling
Async Programming:
- Leverage Tokio's single-threaded runtime
- Use async/await patterns consistently
- Avoid blocking operations in async contexts
MCP Protocol Compliance:
- Implement MCP tools according to specification
- Ensure proper error handling and response formatting
- Maintain protocol version compatibility

Project Structure

Keep the codebase minimal and focused
Organize code by functionality (logs, tests, core MCP handling)
Maintain clear separation between Unity communication and MCP protocol handling

Testing Strategy

Unit tests for most functionality
A real (but minimal) Unity project is embedded in UnityProject for running related tests (that doesn't require a running Unity Editor instance, just need files, including Unity generated files)
Don't create examples binaries(for testing or any other reason), only do unit tests for testing
Our tests can take a long time to run(30-60 seconds), so avoid running all tests when possible, focus testing individual modules that we're actively working on.

Read the full file on GitHub · 67 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.

2mo ago First seen · 67 lines · 550 tokens per session scan A ad58bfb1f7f3

Subscribe to this mod's changes

unity_code_mcp CLAUDE.md is an instructions file published in the GitHub repository hackerzhuli/unity_code_mcp (11 stars, last pushed 3mo ago), licensed MIT. It adds 550 tokens to every session, about $0.0022 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.

Game development ai game mcp unity

unity_code_mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unity_code_mcp CLAUDE.mdhackerzhuli/unity_code_mcp	Instructions file	11	3mo ago	MIT	A	550	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

unity_code_mcp: Instructions file for Claude Code