agentmods.dev

Unreal_mcp: Instructions file for GitHub Copilot

.github/copilot-instructions.md

Unreal_mcp copilot-instructions.md is an instructions file for GitHub Copilot from ChiR24/Unreal_mcp. It costs 837 tokens per session, scanned A, original, MIT.

Project instructions for coding agents working with an Unreal Engine MCP integration. Unreal Engine is software for building games and other real-time 3D applications; MCP connects an agent to tools in that environment.

In plain words
What is it for?
Use them when changing the TypeScript MCP server, its Unreal Editor bridge, tool routing, automation flow, tests, or Unreal asset paths.
Why use it?
They explain the project architecture and critical rules, reducing the risk of broken communication, invalid asset paths, or unsafe Unreal Engine changes.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions AGENTS.md.

This is ChiR24/Unreal_mcp's own configuration. It tells GitHub Copilot 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 →

not rated 978repo +17 changed today A scan 837 tokens original MIT
View source ↗ ChiR24/Unreal_mcp enginewire.dev
Reuse

Borrowing it

Nothing to install: this file belongs to ChiR24/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/ChiR24/Unreal_mcp/dev/.github/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/ChiR24/Unreal_mcp

Made for: GitHub Copilot.

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 copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chir24/unreal_mcp/copilot-instructions/github.svg)](https://agentmods.dev/instructions/chir24/unreal_mcp/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/chir24/unreal_mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/chir24/unreal_mcp/copilot-instructions/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 copilot-instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chir24/unreal_mcp/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/chir24/unreal_mcp/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 837 This file is loaded in full into every session.
When invoked 837 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 $0.00837 $0.00837
Opus 5.5 $0.00335 $0.00335
Sonnet 5.5 $0.00167 $0.00167
Haiku 4.5 $0.00084 $0.00084

Measured today against content hash d04b01bf15eb, 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 copilot-instructions.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 today.

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.

.github/copilot-instructions.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot instructions for Unreal MCP

Architecture

  • The Unreal Editor plugin in plugins/EngineWire/ does all the work and serves MCP itself at /mcp (port 3000). src/ holds the capability records every contract is generated from, and a stdio proxy (src/proxy/native-proxy.ts) that relays to /mcp.
  • Typical flow is the single unreal gateway tool -> native capability lookup + strict schema validation -> C++ subsystem queue -> game-thread handler. There is no TypeScript gateway or per-action layer.
  • Keep workspace-wide guidance here and rely on the closer AGENTS.md files for area-specific detail under src/tools/, tests/, and plugins/EngineWire/.

Critical constraints

  • Keep stdout JSON-only. Logs go through src/utils/logging/logger.ts to stderr; do not use console.log in runtime code.
  • Preserve path normalization. Prefer /Game/... asset paths and do not add new code that depends on /Content/... input staying unnormalized.

UE 5.7 safety

  • Do not use UPackage::SavePackage() in plugin code. Use the safe wrappers under plugins/EngineWire/Source/EngineWire/Private/Safety/.
  • For Blueprint component templates, let SCS own nodes and templates through CreateNode() and AddNode() patterns.
  • Do not introduce new ANY_PACKAGE usage; use modern lookup patterns such as nullptr where required by newer UE versions.

Build and test

  • npm run dev: run the proxy from TypeScript.
  • npm run build:core: compile the TypeScript.
  • npm run automation:sync: sync the Unreal plugin into a target project.
  • npm run test:unit: run Vitest unit tests without Unreal. No mocks or fakes.
  • npm test: run the MCP integration suite. This requires Unreal Editor serving /mcp.

Connection and runtime behavior

  • The plugin listens on loopback by default: native MCP on 3000 (on by default), the WebSocket bridge on 8090 and 8091.
  • The proxy talks HTTP to UNREAL_MCP_URL (default http://127.0.0.1:3000/mcp) and reads the capability token from UE_PROJECT_PATH (or MCP_AUTOMATION_CAPABILITY_TOKEN). While the editor is down every call answers NOT_CONNECTED.

Read the full file on GitHub · 44 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. today Changed · -6 lines · -118 tokens per session d04b01bf15eb
  2. 12d ago Changed · -7 tokens per session 152b0e43b386
  3. 26d ago Changed · -3 lines · -64 tokens per session 6f5fc6fdf4d2
  4. 1mo ago First seen · 53 lines · 1,026 tokens per session scan A 0aa62f9df570

Subscribe to this mod's changes

Unreal_mcp copilot-instructions.md is an instructions file published in the GitHub repository ChiR24/Unreal_mcp (978 stars, last pushed today), licensed MIT. It adds 837 tokens to every session, about $0.0033 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 developmentmcpmcp-serverunreal-engineunreal-engine-5
Related

Other instructions, from other repositories

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 · 9,715 tokens

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 · 7,581 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 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 · 4,261 tokens