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 db-lyon/ue-mcp --skill ue-mcp-blueprintgit clone --depth 1 https://github.com/db-lyon/ue-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/db-lyon/ue-mcp/ue-mcp-blueprint)<a href="https://agentmods.dev/skills/db-lyon/ue-mcp/ue-mcp-blueprint"><img src="https://agentmods.dev/badge/skills/db-lyon/ue-mcp/ue-mcp-blueprint/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/db-lyon/ue-mcp/ue-mcp-blueprint"><img src="https://agentmods.dev/badge/skills/db-lyon/ue-mcp/ue-mcp-blueprint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.02580 |
| Opus 5 | $0.00037 | $0.01290 |
| Sonnet 5 | $0.00015 | $0.00516 |
| Haiku 4.5 | $0.00007 | $0.00258 |
Grade A, and why
ue-mcp-blueprint 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 12d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ue-mcp blueprint authoring
The blueprint tool covers reading, authoring, and compiling Blueprints. The default workflow is read → mutate → compile, never fire-and-forget.
Authoring a graph body: prefer the Epic DSL (#711)
When you are authoring the contents of a graph (event graph, function body, macro) - a set of nodes plus their wiring - do not default to node-by-node add_node/connect_pins. Reach for Epic's graph DSL first:
blueprint(action="epic_get_graph_dsl_docs")- read the S-expression grammar once.blueprint(action="epic_write_graph_dsl", ...)- author + compile the whole graph body in one call.
The DSL authors and compiles an entire graph in a single round-trip, which is materially faster and more reliable than stitching individual K2Nodes together (one correct pass vs several failed iterations). Use it for graph bodies whenever it is available.
Availability / fallback. The epic_* actions come from Epic's ToolsetRegistry and require UE 5.8+ with the Epic toolset plugins enabled. Check with epic(action="status"). When they are unavailable (pre-5.8, or the registry is off), fall back to the native node path below.
Keep using the native actions for read/discovery, SCS components, CDO/class defaults, interfaces + event dispatchers, structured compile/validate, and anything with no Epic equivalent - the native path adds idempotency and rollback the raw tools lack. See the ue-mcp-epic-routing skill for the full epic-vs-native decision.
Discovery before authoring
For any existing Blueprint:
blueprint(action="read", assetPath=...)- structure (parent, components, graphs)blueprint(action="read_graph_summary", assetPath=..., graphName=...)- lightweight node+edge summary (~10KB) - use this beforeread_graph(which can be 100KB+)blueprint(action="list_graphs", assetPath=...)- every graph in the BP including event graphs, functions, macros, interface implsblueprint(action="list_variables" | "list_functions" | "list_local_variables")- the member surface.list_functionscovers the same graphs aslist_graphs(own functions, parent overrides, interface impls, event graphs and their entry points, macros, collapsed subgraphs), each tagged withkindandsource; passincludeInherited: trueto also see overridable functions not implemented yetblueprint(action="get_execution_flow", assetPath=..., entryPoint=...)- trace exec pins from an entry pointblueprint(action="get_dependencies", assetPath=..., reverse=false|true)- classes/functions/assets this BP uses, or callers ifreverse: true
What ships with it
1 file 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.
- 12d ago First seen · 139 lines · 74 tokens per session scan A 97be0ba740cb
ue-mcp-blueprint is a skill published in the GitHub repository db-lyon/ue-mcp (328 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 2,580 once invoked, about $0.0004 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.
Other skills, from other repositories
asset-management
Import/export textures crash-safely, query the Content Browser selection, and check if an asset is open (AssetDiscoveryService). Search, load, save, move, rename, duplicate, and delete assets are handled by Unreal's native AssetTools toolset or EditorAssetLibrary. Use when the user asks to import an image from disk…
level-actors
List, find, place, move, rotate, and modify actors in the current level (ActorService + editor subsystems). Use when the user asks to find/list actors in the level, move or rotate an actor, set an actor's properties/folder/transform, or spawn/delete level actors.
materials
Create and edit materials and material instances — graph nodes, parameters, functions, custom HLSL, and instance overrides (MaterialService + MaterialNodeService). Use when the user asks to create or edit a material/material instance, wire material nodes, add material parameters, set blend/shading modes, or recreate a…
vibeue
Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…
gameplay-tags
Create, list, remove, and rename Gameplay Tags with runtime registration (GameplayTagService). Use when the user asks to add or register gameplay tags, list/query existing tags, or rename/remove tags (e.g. Ability.Attack.Melee, State.Stunned).
project-settings
Configure Unreal Engine project settings and editor preferences — UI appearance, toolbar icons, scale, colors, and any UDeveloperSettings subclass (ProjectSettingsService). Use when the user asks to change a project setting or editor preference, configure a UDeveloperSettings category, or read/write project config…