ue-official-mcp: Instructions file for Claude Code

CLAUDE.md

ue-official-mcp CLAUDE.md is an instructions file for Claude Code from tc-imba/ue-official-mcp. It costs 1,653 tokens per session, scanned A, original, MIT.

Project instructions for a toolkit that connects to Unreal Engine, a game-development editor, through its official Model Context Protocol server. It records the server's tools and data formats for each exact Epic release as a reusable Claude skill.

In plain words
What is it for?
Maintaining the toolkit, preserving version-specific tool catalogs, regenerating reference files, and working safely with Unreal Engine releases.
Why use it?
It avoids repeatedly asking the live editor what tools exist and prevents mismatches when small software updates change those tools or data formats.

Instructions file for Claude Code

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

This is tc-imba/ue-official-mcp's own configuration. It tells Claude Code how to work on ue-official-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 ue-official-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tc-imba/ue-official-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/tc-imba/ue-official-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tc-imba/ue-official-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 ue-official-mcp CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tc-imba/ue-official-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tc-imba/ue-official-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,653 This file is loaded in full into every session.
When invoked 1,653 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 $0.01653 $0.01653
Opus 5 $0.00826 $0.00826
Sonnet 5 $0.00331 $0.00331
Haiku 4.5 $0.00165 $0.00165

Measured 10d ago against content hash 76de632f47c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ue-official-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 · 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-specific context for Claude Code sessions. The README is the user-facing doc — this file captures what Claude needs to know that isn't obvious from reading the code.

What this is

A toolkit that probes a live UE editor's official ModelContextProtocol server, captures every toolset's tools + schemas, and publishes the catalog as a portable Claude skill (one per Epic release). Replaces blind live describe_toolset discovery with file reads (~1,000–3,000× faster). See README.md "Why this exists" for the full motivation.

Core invariants — don't break these

  1. Skill folder name == probe filename version. skills/ue-official-mcp-X.Y.Z/ matches probes/X.Y.Z.json exactly. paths.skill_name() enforces this; route any new path through paths.py rather than hardcoding strings.
  2. Both axes use the full X.Y.Z version. Patch releases (5.8.1, 5.8.2) get their own probe AND their own skill. Rationale: MCP is Experimental and schemas drift across patches; pinning prevents silent breakage when a consumer's editor and the cached schemas disagree.
  3. Generated files are never hand-edited. Everything under skills/<X.Y.Z>/references/ regenerates from probes/<X.Y.Z>.json via generate.py. Each generated file has a "do not hand-edit" header.
  4. Frontmatter name: in each SKILL.md must equal its parent folder name (Anthropic skill convention).
  5. toolset_map.yaml is the curator source for domain grouping. Shared across all engine versions — one map, many skills. Edit the map, then re-generate; never edit the <domain>.md outputs directly.

Common commands

All commands run via uv (Python deps managed by uv, not pip directly):

  • uv run ue-mcp-skills sync --engine X.Y.Z --launch — launches UE, probes it, writes probes/X.Y.Z.json + regenerates the matching skill folder.
  • uv run ue-mcp-skills sync --engine X.Y.Z --endpoint URL — same, against an already-running editor (skips the launch step).
  • uv run ue-mcp-skills generate [--engine X.Y[.Z]] — offline rebuild from a saved probe. With X.Y, picks the highest patch present.
  • uv run ue-mcp-skills build [--serve] — mkdocs site over the engine pinned in mkdocs.yml.
  • uv run python -m mkdocs build --strict — direct mkdocs invocation (what CI runs).

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. 10d ago First seen · 108 lines · 1,653 tokens per session scan A 76de632f47c7

Subscribe to this mod's changes

ue-official-mcp CLAUDE.md is an instructions file published in the GitHub repository tc-imba/ue-official-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,653 tokens to every session, about $0.0083 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 2026-08-31.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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