unreal-world-builder

unreal-world-builder is a skill for Claude Code from qfoldit/Protein-Design-MCP. It costs 117 tokens per session (906 once invoked), scanned A, original, Apache-2.0.

A tool for turning a validated Universal Assembly Graph into a live Unreal Engine scene. A Universal Assembly Graph is a structured description of a game or digital-twin world, such as its objects, lights, attachments, and interactions.

In plain words
What is it for?
It is for creating Unreal scenes from validated world descriptions, mapping objects and relationships to Unreal actors and components, and connecting interactions such as grabbing objects.
Why use it?
It removes the manual work of rebuilding that structured world inside Unreal Engine and checks that the required Unreal setup is ready first.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the qfoldit-skills plugin — 20 skills shipped together

Good fit It is for creating Unreal scenes from validated world descriptions, mapping objects and relationships to Unreal actors and components, and connecting interactions such as grabbing objects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qfoldit/protein-design-mcp/unreal-world-builder
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.

Any agent
npx skills add qfoldit/Protein-Design-MCP --skill unreal-world-builder
Clone the repo
git clone --depth 1 https://github.com/qfoldit/Protein-Design-MCP

Made for: Claude Code.

Or install qfoldit-skills, the plugin that ships this one along with the rest of its 20 skills.

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-world-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/unreal-world-builder/github.svg)](https://agentmods.dev/skills/qfoldit/protein-design-mcp/unreal-world-builder)
Your own site
<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/unreal-world-builder"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/unreal-world-builder/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-world-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/qfoldit/protein-design-mcp/unreal-world-builder"><img src="https://agentmods.dev/badge/skills/qfoldit/protein-design-mcp/unreal-world-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 906 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00117 $0.00906
Opus 5 $0.00059 $0.00453
Sonnet 5 $0.00023 $0.00181
Haiku 4.5 $0.00012 $0.00091

Measured 11d ago against content hash cde2610df247, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

unreal-world-builder 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 11d 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-skills/skills/unreal-world-builder/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

unreal-world-builder

Status: official. Built on EpicGames/unreal-engine-skills-for-claude-code-plugin, published by Epic Games directly.

Prerequisites (do not skip)

  1. Unreal Editor with BOTH plugins enabled: ModelContextProtocol AND AllToolsets (AllToolsets provides the tools -- without it the MCP server exposes none).
  2. MCP server running: console command ModelContextProtocol.StartServer (or bAutoStartServer).
  3. bash on PATH (macOS/Linux native; Windows needs Git Bash or WSL).
  4. Generate client config from the editor console: ModelContextProtocol.GenerateClientConfig ClaudeCode (default localhost:8000, path /mcp).

UAG -> Unreal mapping

Use game-designer/references/uag_schema.md mapping table as the baseline (mesh -> StaticMeshActor, light -> Point/DirectionalLight actor, parent_child -> Attach, physics_collision -> collision component/preset, on_grab -> Enhanced Input + Interaction Component). Before calling any tool, use the meta-tools list_toolsets -> describe_toolset -> call_tool (tool search is on by default) rather than guessing tool names from memory.

Workflow

  1. Confirm the UAG passed game-designer/scripts/uag_validate.py (re-run it if unsure -- do not export an unvalidated graph).
  2. list_toolsets to see available domains (Actors/Scene, Blueprints, Materials, Niagara, UMG, Gameplay Ability System, Sequencer, etc.).
  3. For each UAG node, map to the corresponding Unreal tool call per the table above; for type/trigger values with no established mapping (flagged as warnings by the validator), stop and ask the user how they want it represented rather than guessing.
  4. For interactions (on_grab, on_proximity, etc.) needing custom logic beyond a direct tool call, prefer Blueprint tools over execute_tool_script unless Python is specifically required -- see security note below.

Security (read before a live session)

  • localhost is not a trust boundary -- any local process from the same user can connect. Don't run the MCP server on shared/untrusted machines or expose the port beyond loopback.
  • ProgrammaticToolset.execute_tool_script runs arbitrary Python inside the editor process with full project/asset access -- treat every call as privileged, and prefer it only when no dedicated tool covers the need.
  • Don't run with --dangerously-skip-permissions against a real project -- it removes per-tool confirmation. Use a disposable sandbox project instead if this mode is truly needed.
  • Commit or shelve in version control before a long MCP session -- tools mutate live UObjects and can move/delete tracked assets in one call.

Read the full file on GitHub · 40 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. 11d ago First seen · 40 lines · 117 tokens per session scan A cde2610df247

Subscribe to this mod's changes

unreal-world-builder is a skill published in the GitHub repository qfoldit/Protein-Design-MCP (1 stars, last pushed 14d ago), licensed Apache-2.0. It adds 117 tokens to every session and 906 once invoked, about $0.0006 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 skills, from other repositories

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

godot-signals-groups

Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…

gamedev-skills/awesome-gamedev-agent-skills · 95 tokens

unity-addressables

Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).

Besty0728/Unity-Skills · 25 tokens

motion

How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.

OpenDCAI/GameFactory-3A · 0 tokens

threejs-exposure-color-grading

Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.

scottstts/Threejs-Awesome-Graphics-Agent-Skills · 60 tokens