What is unreal-mcp CLAUDE.md?

A project instruction file for an MCP server that lets a language model control the Unreal Editor through a Python server and an Unreal Engine plugin.

Use it when developing, debugging, or extending Unreal Editor actions, the MCP server, or its Unreal Engine plugin.

It explains how requests travel between the model, the server, and Unreal, including the repository's grouped action system.

How GenOrca/unreal-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to GenOrca/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/GenOrca/unreal-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/GenOrca/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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/genorca/unreal-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/genorca/unreal-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/genorca/unreal-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/genorca/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.

Your own site · 80×15

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

Per session 2,258 This file is loaded in full into every session.

When invoked 2,258 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	$0.02258	$0.02258
Opus 5.5	$0.00903	$0.00903
Sonnet 5.5	$0.00452	$0.00452
Haiku 4.5	$0.00226	$0.00226

Measured 2mo ago against content hash 6cdb3299686f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 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 · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 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.

What this is

An MCP server that lets an LLM drive the Unreal Editor. Two halves:

mcp-server/ — Python FastMCP server (the MCP side, talks to the LLM over stdio).
Plugins/UnrealMCPython/ — a UE plugin: a C++ TCP server (port 12029) plus Python "action" modules that actually call the Unreal API.

Request path: LLM → FastMCP dispatcher → TCP :12029 → C++ server → ue_* Python function → back.

Architecture (the non-obvious parts)

Namespace dispatcher, not one-tool-per-action. The MCP surface is 10 domain tools (actor, asset, behavior_tree, blueprint, editor, game, level, material, umg, util), each taking (action, params). This keeps the tool-list context cost fixed no matter how many actions exist. action="list_actions" returns a domain's catalog. See mcp-server/src/unreal_mcp/dispatcher.py.

The catalog is generated, never hand-written. dispatchers/_catalog.py is produced by generate_catalog.py, which AST-extracts param names, defaults, and the docstring first line from every ue_* function in Plugins/.../UnrealMCPython/*_actions.py. The dispatcher passes params straight through as ue_<action>(**params), so catalog param names must equal the real signatures — generation guarantees this. Never edit _catalog.py by hand.

Responses are double-wrapped. The C++ server runs print(execute_action(...)) and puts the captured stdout (the action's JSON string) into a result field, with an outer success that means "Python ran", not "action succeeded". core._unwrap_result() unwraps it so callers get the real action dict. execute_python / livecoding_compile use separate TCP message types and are intentionally not unwrapped.

Commands

# All run from mcp-server/
cd mcp-server

# Regenerate the catalog after adding/changing a ue_* function
uv run python generate_catalog.py

# Gate 1 — catalog vs signatures drift guard
uv run python validate_tools.py

# Gate 2 — offline tests (routing, unwrap, coverage). E2E auto-skips with no editor.
uv run --extra dev pytest

# Single test / by name
uv run --extra dev pytest tests/test_dispatcher.py -k routing

Read the full file on GitHub · 178 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 · 178 lines · 2,258 tokens per session scan A 6cdb3299686f

Subscribe to this mod's changes

unreal-mcp CLAUDE.md is an instructions file published in the GitHub repository GenOrca/unreal-mcp (147 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 2,258 tokens to every session, about $0.0090 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.

Building agents Game development LLM mcp ue5 unreal-engine-5 unreal-mcp

unreal-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unreal-mcp CLAUDE.mdGenOrca/unreal-mcp	Instructions file	147	4mo ago	Apache-2.0	A	2,258	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

unreal-mcp: Instructions file for Claude Code