agentmods.dev

UEMCP AGENTS.md

Project-specific instructions for UEMCP, a bridge between AI assistants and Unreal Engine development tools.

In plain words
What is it for?
Use them when building, testing, running, or modifying the TypeScript server, Unreal Engine plugin, integration tests, or supporting scripts.
Why use it?
They give an agent the repository layout, setup commands, coding rules, and tests it must follow when changing the project.

Instructions file for CodexOpenCode

18 20d ago A scan 767 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/agents-md
Clone the repo
git clone --depth 1 https://github.com/atomantic/UEMCP

Made for: Codex, OpenCode.

Per session 767 This file is loaded in full into every session.
When invoked 767 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 $0.00767 $0.00767
Opus 5 $0.00383 $0.00383
Sonnet 5 $0.00153 $0.00153
Haiku 4.5 $0.00077 $0.00077

Measured 2d ago against content hash e48808df9106, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

UEMCP 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 2d 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.

AGENTS.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Modules

  • server/: TypeScript MCP server (src, tests, dist). Build, lint, typecheck live here.
  • plugin/: Unreal Engine plugin (Python ops, C++ stub, uplugin). Python lives under plugin/Content/Python.
  • tests/: Integration/E2E helpers and scenarios; Python test example under tests/python.
  • scripts/: Local diagnostics and utilities (e.g., mcp-diagnostic.js, bump-version.js).
  • docs/, README.md, CLAUDE.md: Architecture, workflows, contributor info.

Build, Test, Run

  • Install/setup: ./setup.sh (detects Node, builds server, configures MCP clients).
  • Dev server: npm run dev (from repo root; runs server in watch mode).
  • Build: npm run build (invokes tsc in server).
  • Tests (root):
    • npm test or npm run test:e2e — E2E suite.
    • npm run test:unit — Jest unit tests in server.
    • npm run test:integration — Integration checks.
    • cd server && npm run test:python — Python plugin tests via pytest.
    • CI-like run: ./test-ci-locally.sh.

Coding Style & Naming

  • Indentation: JS/TS/JSON 2 spaces; Python 4 spaces (.editorconfig).
  • TypeScript: ESLint + strict rules (server/.eslintrc.js): no any, explicit returns, no unused vars, no floating promises. Run npm run lint and npm run lint:fix.
  • Filenames: kebab- or lowerCamel for TS files; Python modules snake_case under plugin/Content/Python.
  • Public tool exports live in server/src/tools and are registered via server/src/index.ts.
  • Error handling: Avoid try/catch (TS) and try/except (Py) whenever possible. Prefer validation + specific errors and the UEMCP framework decorators/utilities. See docs/development/error-handling-philosophy.md, docs/improved-error-handling.md, and docs/development/code-standards.md.
  • Linting standard: Zero warnings and zero errors. TS: cd server && npm run lint. Python: flake8 in plugin/Content/Python with --max-line-length=120. Do not merge code with any lint output.

Read the full file on GitHub · 42 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. 2d ago First seen · 42 lines · 767 tokens per session scan A e48808df9106

Subscribe to this mod's changes

UEMCP AGENTS.md is an instructions file published in the GitHub repository atomantic/UEMCP (18 stars, last pushed 20d ago), licensed MIT. It adds 767 tokens to every session, about $0.0038 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 developmentLanguagesTestingclaude-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

unreal-ai-connection copilot-instructions.md

Instructions for NAJEMWEHBE/unreal-ai-connection, covering copilot review instructions — unreal ai connection, what this repo is, review priorities (in order), handler shape (one file = one tool) and what to skip / not flag.

NAJEMWEHBE/unreal-ai-connection · 1,862 tokens

unreal-ai-connection CLAUDE.md

Instructions for NAJEMWEHBE/unreal-ai-connection, covering unreal ai connection — agent context, where to look first for any change and house rules carried forward across sessions.

NAJEMWEHBE/unreal-ai-connection · 1,867 tokens

unreal-ai-connection AGENTS.md

Instructions for NAJEMWEHBE/unreal-ai-connection, covering quick orientation, where to look first, house rules carried across all agents, mcp server setup per agent and trap-table — read before writing c++ or modifying bridge.

NAJEMWEHBE/unreal-ai-connection · 2,876 tokens