Borrowing it
Nothing to install: this file belongs to geuneda/geuneda-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.
curl -O https://raw.githubusercontent.com/geuneda/geuneda-mcp-unity/main/AGENTS.mdgit clone --depth 1 https://github.com/geuneda/geuneda-mcp-unityWrote 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.
[](https://agentmods.dev/instructions/geuneda/geuneda-mcp-unity/agents-md)<a href="https://agentmods.dev/instructions/geuneda/geuneda-mcp-unity/agents-md"><img src="https://agentmods.dev/badge/instructions/geuneda/geuneda-mcp-unity/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.02715 | $0.02715 |
| Opus 5 | $0.01358 | $0.01358 |
| Sonnet 5 | $0.00543 | $0.00543 |
| Haiku 4.5 | $0.00271 | $0.00271 |
Grade A, and why
geuneda-mcp-unity AGENTS.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 7d 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Unity — AI 에이전트 가이드 (MCP 패키지)
목적 (이 저장소가 하는 일)
MCP Unity는 MCP 지원 클라이언트에 Unity Editor 기능을 노출합니다. 다음을 실행하여 동작합니다:
- Unity 측 "클라이언트" (C# Editor 스크립트): Unity Editor 내부에서 도구/리소스를 실행하는 WebSocket 서버.
- Node 측 "서버" (TypeScript): MCP 도구/리소스를 등록하고 WebSocket을 통해 Unity로 요청을 전달하는 MCP stdio 서버.
동작 방식 (상위 수준 데이터 흐름)
- MCP 클라이언트 ⇄ (stdio / MCP SDK) ⇄ Node 서버 (
Server~/src/index.ts) - Node 서버 ⇄ (WebSocket JSON-RPC 유사) ⇄ Unity Editor (
Editor/UnityBridge/McpUnityServer.cs+McpUnitySocketHandler.cs) - 도구/리소스 이름은 Node와 Unity에서 정확히 일치해야 합니다 (일반적으로
lower_snake_case).
기본값 및 불변 사항
- Unity WebSocket 엔드포인트: 기본값
ws://localhost:8090/McpUnity. - 설정 파일:
ProjectSettings/McpUnitySettings.json(Unity에서 작성/읽기; Node에서 기회적으로 읽기). - 실행 스레드: 도구/리소스 실행은
EditorCoroutineUtility를 통해 디스패치되며 Unity 메인 스레드에서 실행됩니다. 동기 작업은 짧게 유지하세요; 긴 작업에는 비동기 패턴을 사용하세요.
저장소 레이아웃 (어디에서 무엇을 변경할지)
/
├── Editor/ # Unity Editor 패키지 코드 (C#)
│ ├── Tools/ # 도구 (McpToolBase 상속)
│ ├── Resources/ # 리소스 (McpResourceBase 상속)
│ ├── UnityBridge/ # WebSocket 서버 + 메시지 라우팅
│ ├── Services/ # 도구/리소스에서 사용하는 테스트/로그 서비스
│ └── Utils/ # 공유 헬퍼 (설정, 로깅, 워크스페이스 통합)
├── Server~/ # Node MCP 서버 (TypeScript, ESM)
│ ├── src/index.ts # 도구/리소스/프롬프트를 MCP SDK에 등록
│ ├── src/tools/ # MCP 도구 정의 (zod 스키마 + 핸들러)
│ ├── src/resources/ # MCP 리소스 정의
│ └── src/unity/mcpUnity.ts # Unity와 통신하는 WebSocket 클라이언트
└── server.json # MCP 레지스트리 메타데이터 (이름/버전/패키지)
빠른 시작 (로컬 개발)
-
Unity 측
- 이 패키지가 설치된 Unity 프로젝트를 엽니다.
- 서버가 실행 중인지 확인합니다 (자동 시작은
McpUnitySettings.AutoStartServer로 제어됩니다). - 설정은
ProjectSettings/McpUnitySettings.json에 저장됩니다.
-
Node 측 (빌드)
cd Server~ && npm run build- MCP 진입점은
Server~/build/index.js입니다 (MCP stdio 서버로 게시됨).
-
Node 측 (디버그/검사)
cd Server~ && npm run inspector로 MCP Inspector를 사용합니다.
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.
- 7d ago First seen · 164 lines · 2,715 tokens per session scan A d231cd9b0026
geuneda-mcp-unity AGENTS.md is an instructions file published in the GitHub repository geuneda/geuneda-mcp-unity (1 stars, last pushed 6mo ago), licensed MIT. It adds 2,715 tokens to every session, about $0.0136 per session on Opus 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.