Unreal-MCP: Instructions file for Claude Code

CLAUDE.md

Unreal-MCP CLAUDE.md is an instructions file for Claude Code from IvanMurzak/Unreal-MCP. It costs 7,108 tokens per session, scanned A, original, Apache-2.0.

Instructions for using Unreal-MCP, a bridge between coding agents and Unreal Engine through the Model Context Protocol. Unreal Engine is software for building games and interactive 3D applications.

In plain words
What is it for?
Guide changes to the Unreal-MCP project, including editor automation, in-game runtime control, Blueprints, C++, screenshots, and related builds and tests.
Why use it?
They explain the project’s architecture and the difference between controlling the Unreal Editor and controlling a running game, helping agents follow the correct build and test process.

Instructions file for Claude Code

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

This is IvanMurzak/Unreal-MCP's own configuration. It tells Claude Code how to work on Unreal-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 Unreal-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to IvanMurzak/Unreal-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/IvanMurzak/Unreal-MCP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/IvanMurzak/Unreal-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 Unreal-MCP CLAUDE.md

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

agentmods 80×15 button for Unreal-MCP CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ivanmurzak/unreal-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ivanmurzak/unreal-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,108 This file is loaded in full into every session.
When invoked 7,108 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 $0.07108 $0.07108
Opus 5 $0.03554 $0.03554
Sonnet 5 $0.01422 $0.01422
Haiku 4.5 $0.00711 $0.00711

Measured 10d ago against content hash 920f7773d4a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Unreal-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 10d 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 · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Unreal-MCP

Unreal-MCP bridges LLMs (Claude, Cursor, Copilot, …) with Unreal Engine via the Model Context Protocol — the Unreal-engine sibling of Unity-MCP and Godot-MCP. It works in two modes: an editor mode (the default — drive the Unreal Editor: spawn actors, edit levels, author/compile Blueprints, edit/compile C++, capture screenshots, …) and an opt-in in-game runtime mode (drive a running PIE / Standalone / packaged Development build so an AI can operate your live game). Status: beta — the plugin, the .NET sidecar, the unreal-mcp-cli, the AI Game Developer editor UI, and 61 built-in editor tools across 7 families (plus 3 §2.4 system tools) have shipped and are covered by CI. The unreal-mcp-cli is published on npm (the Fab / Epic Marketplace listing for the precompiled plugin is coming soon). The local MCP server is the shared, engine-agnostic GameDev-MCP-Server (binary gamedev-mcp-server) — no server source lives in this repo.

The authoritative design is docs/ARCHITECTURE.md (defer to it on any conflict). Read the relevant section before implementing anything non-trivial — it locks the IPC protocol (§1), dynamic tool registration (§2), schema generation (§3), the game-thread dispatcher (§4), extensions (§5), sidecar lifecycle (§6), UI (§7), config (§8), repo/versioning/CI (§9), the tool-family roadmap (§10), risks (§11), runtime (in-game) support (§12), and custom prompts & resources (§A). The user-facing entry point is README.md; the release runbook is docs/RELEASING.md; the extension author guide is docs/EXTENSIONS.md; the in-game operator walkthrough is docs/RUNTIME-E2E.md.

Architecture in one screen

Unlike Unity/Godot (C# engines that host the .NET McpPlugin/ReflectorNet/SignalR stack in-process), Unreal's editor and runtime are C++ and cannot host that .NET stack. So the McpPlugin host runs as an auto-managed .NET 9 sidecar process (unreal-mcp-bridge, bridge/) that is a local child of whichever host loads the plugin — the Editor in dev, or the game process itself in an opt-in packaged build. It is never remote: the C++ plugin listens on a loopback TCP port and the sidecar dials it, authenticating with a one-shot token delivered over stdin (never argv — §1.4). The sidecar relays IPC ⇄ SignalR to the MCP server (cloud ai-game.dev by default, or a local gamedev-mcp-server). See the §0 system-overview diagram.

Read the full file on GitHub · 319 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. 10d ago First seen · 319 lines · 7,108 tokens per session scan A 920f7773d4a5

Subscribe to this mod's changes

Unreal-MCP CLAUDE.md is an instructions file published in the GitHub repository IvanMurzak/Unreal-MCP (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 7,108 tokens to every session, about $0.0355 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 2026-08-30.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens