agentmods.dev

UEMCP CLAUDE.md

Project instructions for UEMCP, an MCP server that lets AI assistants work with Unreal Engine through TypeScript and Python bridges.

In plain words
What is it for?
Use them when modifying or testing the MCP server, Python bridge, Unreal Engine plugin, documentation, or hot-reload workflow.
Why use it?
They describe the architecture, setup, testing requirements, and zero-warning policy so changes can be checked consistently.

Instructions file

18 21d ago A scan 889 tokens original MIT
View the source file atomantic/UEMCP
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/atomantic/uemcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/atomantic/UEMCP
Per session 889 This file is loaded in full into every session.
When invoked 889 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00889 $0.00889
Opus 5 $0.00445 $0.00445
Sonnet 5 $0.00178 $0.00178
Haiku 4.5 $0.00089 $0.00089

Measured 3d ago against content hash 35f219157a75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

UEMCP 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 3d 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 · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Project-wide context for UEMCP - an MCP server bridging AI assistants with Unreal Engine development.

Architecture Overview

  • MCP Server (TypeScript/Node.js): Implements Model Context Protocol, handles AI assistant requests
  • Python Bridge (Python 3.11): Interfaces with Unreal Engine's Python API via HTTP
  • UE Plugin (Content-only): Python listener that runs inside Unreal Engine

Quick Start

# Setup
npm install
pip install -r requirements.txt

# Testing & CI
./test-ci-locally.sh  # Run before committing - MUST pass with zero warnings
npm test              # JavaScript/TypeScript tests
python -m pytest      # Python tests

CRITICAL: Zero warnings policy enforced by pre-commit hooks

Module-Specific Context

  • Server Module (server/CLAUDE.md): TypeScript standards, MCP implementation
  • Plugin Module (plugin/CLAUDE.md): UE Python integration, hot reload workflow
  • Documentation (docs/): Detailed comparisons, architecture diagrams

Core Development Principles

MCP Tool Usage

  • Claude Code Integration: MCP server starts automatically with claude -c
  • Direct Tool Usage: Call MCP tools directly, no test scripts needed
  • Hot Reload: Use restart_listener() in UE console for instant updates

Tool Development Philosophy

CRITICAL: Never use python_proxy as a workaround for missing tool functionality.

  • Fix or create proper MCP tools instead
  • Tools provide 85% less code, better error handling, type safety
  • Only use python_proxy for one-off debugging or exploration

See docs/mcp-tools-vs-python-proxy.md for detailed comparisons.

Code Style Philosophy

  • Line Endings: Always use LF (Unix-style), never CRLF
  • Exception Handling: Minimize try/catch - prefer validation
  • Zero Warnings Policy: Enforced by pre-commit hooks
  • Post-Feature Simplification: Always run /simplify after implementing a feature to catch duplication, quality issues, and efficiency problems before committing

Read the full file on GitHub · 108 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. 3d ago First seen · 108 lines · 889 tokens per session scan A 35f219157a75

Subscribe to this mod's changes

UEMCP CLAUDE.md is an instructions file published in the GitHub repository atomantic/UEMCP (18 stars, last pushed 21d ago), licensed MIT. It adds 889 tokens to every session, about $0.0044 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.

Game developmentclaude-codemcp-serverunreal-engine
Related

Other instructions, from other repositories

Unreal_mcp AGENTS.md

Instructions for ChiR24/Unreal_mcp, covering project knowledge base, structure, where to look, code map and conventions.

ChiR24/Unreal_mcp · 7,761 tokens

ue-mcp CLAUDE.md

Instructions for db-lyon/ue-mcp, covering claude.md, repo at a glance, development workflow, git and commits and versioning.

db-lyon/ue-mcp · 4,230 tokens

Unreal_mcp copilot-instructions.md

Instructions for ChiR24/Unreal_mcp, covering copilot instructions for unreal mcp, architecture, critical constraints, ue 5.7 safety and build and test.

ChiR24/Unreal_mcp · 1,026 tokens

mcp-unreal CLAUDE.md

Instructions for remiphilippe/mcp-unreal, covering claude.md — mcp-unreal, project overview, key facts, repository structure and code standards.

remiphilippe/mcp-unreal · 6,281 tokens

Unity-MCP copilot-instructions.md

Instructions for IvanMurzak/Unity-MCP, covering project guidelines, critical rules, no c# reflection for private access, code review and code style.

IvanMurzak/Unity-MCP · 895 tokens

better-godot-mcp CLAUDE.md

Instructions for n24q02m/better-godot-mcp, covering claude.md - better-godot-mcp, commands, setup, lint & type check and fix.

n24q02m/better-godot-mcp · 1,423 tokens