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.
npx skills add AvatarGanymede/ue5.7-mcp --skill unrealgit clone --depth 1 https://github.com/AvatarGanymede/ue5.7-mcpWrote 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.
[](https://agentmods.dev/skills/avatarganymede/ue5.7-mcp/unreal)<a href="https://agentmods.dev/skills/avatarganymede/ue5.7-mcp/unreal"><img src="https://agentmods.dev/badge/skills/avatarganymede/ue5.7-mcp/unreal/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.
<a href="https://agentmods.dev/skills/avatarganymede/ue5.7-mcp/unreal"><img src="https://agentmods.dev/badge/skills/avatarganymede/ue5.7-mcp/unreal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00107 | $0.01560 |
| Opus 5 | $0.00053 | $0.00780 |
| Sonnet 5 | $0.00021 | $0.00312 |
| Haiku 4.5 | $0.00011 | $0.00156 |
Grade A, and why
unreal 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unreal MCP
Use the single unreal tool to discover and execute Unreal Editor workflows. The tool has four actions: health, discover, execute, and task.
Operating workflow
- Call
healthwhen the editor connection or Python state is unknown. Checkdata.is_game_threadanddata.python_loaded; top-levelok: trueonly confirms that the server responded. If Python work is required and remains unavailable, report that instead of pretending an editor change succeeded. - Call
discoverbefore using an unfamiliar UE subsystem, optional plugin, or workflow. It searches a static English capability catalog, so prefer short English API keywords; use an empty query to list domains. Inspect Python modules or reflected types for exact project classes, functions, and signatures. - Inspect the relevant editor or asset state before changing it. Use a read-oriented Python query or
blueprint_graph.inspectand retain stable object, node, and pin identifiers. - Execute the smallest coherent batch. Keep dependent commands together and leave
continue_on_errorfalse unless later commands are genuinely independent. - Verify the result with a separate query, graph inspection, compile result, or asset existence check. Report observed results, not just submitted commands.
Do not route normal calls through scripts/unreal-mcp.sh; that script is for direct Git Bash diagnostics when the MCP tool itself is unavailable.
Choose the command backend
- Use
kind: "python"for UE Python/reflection, assets, actors, components, class defaults, editor subsystems, and project-specific APIs. - Use
kind: "console"for established Unreal console commands and cvars. - Use
kind: "blueprint_graph"only for visible K2 nodes, pins, connections, defaults, layout, compilation, and saving. - Use
kind: "wait"only inside an asynchronous batch when the editor must advance by frames or wall-clock time.
Read references/tool-calls.md when composing an unfamiliar call, an asynchronous task, or Blueprint graph edits.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 104 lines · 107 tokens per session scan A 67e4e31e628c
unreal is a skill published in the GitHub repository AvatarGanymede/ue5.7-mcp (1 stars, last pushed 21d ago), licensed MIT. It adds 107 tokens to every session and 1,560 once invoked, about $0.0005 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.
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.
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).
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…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
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.