Drives a live Unreal Editor through the unreal-mcp server: spawn actors, edit Blueprints, materials and sequences, change properties and trigger Live Coding.

MITAuto-check passedGame Development

Install Unreal Engine MCP

skills CLI
$ npx skills add EpicGames/unreal-engine-skills-for-claude-code-plugin --skill unreal-mcp -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install EpicGames/unreal-engine-skills-for-claude-code-plugin unreal-mcp --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/EpicGames/unreal-engine-skills-for-claude-code-plugin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/unreal-mcp .claude/skills/unreal-mcp && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
unreal-mcp
GitHub stars
338
Token cost
~1.8k tokens
SKILL.md length
872 words
Files
3 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Drives a live Unreal Editor through the unreal-mcp server: spawn actors, edit Blueprints, materials and sequences, change properties and trigger Live Coding.

  • Works in 3 steps: Call list_toolsets to see what's… → Invoke the tool with call_tool: pass… → Top-level dispatch (omitting…
  • Spawning, moving or duplicating actors in an Unreal level
  • SKILL.md covers First step every time:…, Safety rules, Project skills and Reference files, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The skill connects the agent to a running Unreal Editor through the `unreal-mcp` MCP server, which offers hundreds of tools in more than 30 toolsets such as actors, Blueprints, materials, Niagara, Sequencer, Control Rigs, GAS, automation tests and Live Coding. The agent inspects and changes editor state itself instead of telling you to do it by hand.

Because tool search is on by default, the server shows only three meta-tools. The agent calls `list_toolsets`, then `describe_toolset` to read schemas, and runs the chosen tool through `call_tool` with a toolset name, tool name and arguments. If tools seem missing, it checks the `unreal-mcp` or `unreal-mcp-proxy` connection and verifies recovery with a read-only call, since a proxy can stay connected while the editor is down. Setup and operations are covered in reference files. The skill is not meant for conceptual questions, Unity or Godot.

When your agent uses it

  • Spawning, moving or duplicating actors in an Unreal level
  • Creating or editing Blueprints, widgets, materials, Niagara systems or Sequencer assets
  • Reading or writing properties on actors in the open project
  • Triggering a Live Coding recompile after editing C++

Example prompts

  • “Spawn five point lights around the PlayerStart in the current level.”
  • “Set bIsLocked to true on BP_DoorActor in the open map.”
  • “Create a material instance of M_Rock and tint it darker.”
  • “I changed UMyComponent in C++; run a Live Coding recompile.”

Requirements

  • Unreal Editor running with the unreal-mcp server connected

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Call list_toolsets to see what's registered, then describe_toolset on the candidate(s) to read their tool schemas. If you already know…
  2. Invoke the tool with call_tool: pass toolset_name, tool_name, and an arguments object matching the schema you just read. The result comes…
  3. Top-level dispatch (omitting toolset_name) is reserved for tools registered directly on the MCP server and is rejected for call_tool itself.

What it can do on your machine

Read from SKILL.md and the folder at commit a6aa73a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Unreal Engine MCP loads about 1.8k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 254 tokens; SKILL.md has 872 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~254
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from EpicGames/unreal-engine-skills-for-claude-code-plugin at commit a6aa73a, republished under its MIT licence (© EpicGames). 872 words, ~1,774 tokens.

Download SKILL.mdSave it as .claude/skills/unreal-mcp/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
unreal-mcp
description
Use this skill to perform actions inside an Unreal Engine project via a live-editor MCP connection. Trigger when the user wants to change, query, or run something in their Unreal Engine project, not for conceptual or docs questions. Concrete triggers: spawn/move/duplicate/transform actors in a level, open a `.uproject`, add things around a PlayerStart, create or edit a Blueprint/Widget/Material/Niagara/Control Rig/Sequencer/Behavior Tree/GAS ability, read or write properties on actors (e.g. `bIsLocked` on `BP_DoorActor`), Live Coding recompile after editing C++ (`AActor`, `UMyComponent::Method`, `UPROPERTY`), or modify Static/Skeletal Mesh assets. Treat as Unreal context even without the word "Unreal": asset prefixes `BP_`, `WBP_`, `M_`, `MI_`, `NS_`, `CR_`, `SK_`, `SM_`, `ABP_`; UE C++ types/macros; `.uproject`; Content Browser; Outliner; PlayerStart; "in my game" plus UE signals. Skip for: pure conceptual/docs questions, Unity, Godot, or unrelated uses of "blueprint"/"sequencer"/"widget".

Unreal MCP

You are wired into a live Unreal Editor through the unreal-mcp MCP server. The server exposes hundreds of tools across 30+ toolsets (actors, blueprints, materials, Niagara, Sequencer, Control Rigs, GAS, automation tests, Live Coding, and more) registered through Unreal's ToolsetRegistry. Use it to inspect and mutate live editor state instead of telling the user to do it manually.

You don't need to memorize tool names. The flow below has you discover them on demand.

The connection can appear as unreal-mcp-proxy when the engine's optional proxy is installed. Use that connection for Unreal tools. The proxy keeps Unreal's native tool definitions; it does not introduce replacement discovery or dispatch tools. See references/setup.md for installation.

First step every time: discover the tool you need, then dispatch it via call_tool

Tool search is on by default, so the MCP server advertises only three meta-tools for the whole session: list_toolsets, describe_toolset, and call_tool. Tool names like BlueprintTools.create or SequencerTools.create_level_sequence are not in tools/list. They are dispatched server-side through call_tool and never registered as native MCP tools. This is deliberate. It keeps your context window small and the prompt cache warm.

When you start work:

  1. Call list_toolsets to see what's registered, then describe_toolset on the candidate(s) to read their tool schemas. If you already know which toolset you need (the user said "make a Blueprint" → the Blueprint toolset), skip the listing and go straight to describe_toolset to confirm the available tools and their signatures.
  2. Invoke the tool with call_tool: pass toolset_name, tool_name, and an arguments object matching the schema you just read. The result comes back on the same turn. No extra round-trip needed.
  3. Top-level dispatch (omitting toolset_name) is reserved for tools registered directly on the MCP server and is rejected for call_tool itself.

Missing tools do not prove that the editor is stopped. Check the configured unreal-mcp or unreal-mcp-proxy connection and follow references/operations.md. A proxy can stay connected while Unreal is unavailable, and a client can keep a stale catalog after recovery. unreal_mcp_status reports the proxy's session state, not current reachability. Verify recovery with a read-only Unreal tool call. For first-time configuration, follow references/setup.md.

Safety rules

Follow these rules to protect live editor state.

  • Save first, then save again. Tell the user to save the project (or call AssetTools save APIs) before any bulk change, and again after. MCP edits are not always undoable, especially across compilation boundaries. Treat anything that touches multiple assets as a destructive operation that needs a recovery point.
  • Wait for compilation. If C++ or shader compilation is in flight, your tool calls will hang or fail in confusing ways. To rebuild C++ from the running editor, drive LiveCodingToolset.CompileLiveCoding and wait on its result instead of asking the user to switch to the IDE. That tool blocks until the compile actually finishes and surfaces MSVC diagnostics.
  • Control concurrent calls. MCP accepts concurrent requests and handles dispatch synchronization. Asynchronous tools can overlap, and request order does not guarantee execution or completion order. Serialize dependent calls and mutations that can affect the same asset or editor state. Use parallel calls only for independent work when the tools support safe overlap. Multiple agents can use one editor, but their conflicting changes can cause adverse effects.
  • Always check the result. Blueprint compilation, widget creation, material edits: many tools return a status that flips between success and failure with no exception thrown on the wire. Read the response before moving on. Treat anything that isn't an explicit success as a stop.
  • Mind PIE. Editor-only tools (asset creation in particular) behave differently while Play-in-Editor is active. If a result looks wrong, check whether PIE is running and stop it if so.
Show full SKILL.md (262 more words)Show less

Project skills

A project or plugin can register Agent Skills: named bundles of instructions that capture workflow knowledge the agent wouldn't otherwise have (a project's naming conventions, folder layout, required setup steps, or the canonical sequence for a multi-step task). These are separate from the toolsets themselves and are reached through the agent skill toolset (AgentSkillToolset), not through list_toolsets.

Check for them the same way you discover tools, and do it whenever you start unfamiliar work in a project rather than just once:

  1. Call AgentSkillToolset.ListSkills (through call_tool) to see what skills the project registers. Each entry carries a short description of what it covers and when it applies.
  2. If a skill's description looks relevant to what the user asked, call AgentSkillToolset.GetSkills on it to load the full instructions, then follow them.
  3. If nothing matches, fall back to the tool-discovery flow above.

A relevant project skill's instructions take precedence over your generic defaults: it exists precisely because the project's way of doing something differs from the obvious one. (Authoring or editing these skills is a separate task covered by the unreal-skill companion skill below.)

Reference files

  • references/setup.md: first-time MCP server setup, client configuration, and optional proxy installation.
  • references/operations.md: console commands, settings, proxy recovery, and troubleshooting for missing tools or failed calls.

Companion skills

  • create-toolset: use when authoring a new toolset or adding tools to an existing one. Covers design principles, C++ and Python conventions, registration, error handling, and testing.
  • unreal-skill: use when creating, updating, or reviewing an Agent Skill. Covers what makes a good skill and how to structure one.

© EpicGames, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/unreal-mcp of EpicGames/unreal-engine-skills-for-claude-code-plugin.

  • SKILL.md
  • references/operations.md
  • references/setup.md

Open the folder on GitHubat commit a6aa73a

Compare with similar skills

Unreal Engine MCP next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Unreal Engine MCP compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Unreal Engine MCP this skillEpicGames/unreal-engine-skills-for-claude-code-plugin338—~1.8kAutomated safety check: PassMIT
Unreal Blueprint Authoringflopperam/unreal-engine-mcp1.1k—~1.6kAutomated safety check: PassNone
Unreal Scene Buildingflopperam/unreal-engine-mcp1.1k—~1.4kAutomated safety check: PassNone
Unreal Engine MCP Overviewflopperam/unreal-engine-mcp1.1k—~1.7kAutomated safety check: PassNone
Vibeuekevinpbuckley/VibeUE730—~5.2kAutomated safety check: PassMIT
Unreal MCPLuciole-Studio/Misaka-Agent1711 repos~3.5kAutomated safety check: PassMIT

Similar skills

  • Unreal Blueprint Authoring

    flopperam/unreal-engine-mcp

    Walks an agent through creating and editing Unreal Engine Blueprints with the Flopperam MCP's bp_* tools, from inspection to commit and verification.

    1.1k GitHub stars~1.6k tokensUpdated 3 mo ago
    Game DevelopmentAuto-check passed
  • Unreal Scene Building

    flopperam/unreal-engine-mcp

    Guides scene and world building in Unreal Engine through the Flopperam MCP: placing actors, sculpting landscapes, scattering foliage, editing materials and verifying the level.

    1.1k GitHub stars~1.4k tokensUpdated 3 mo ago
    Game DevelopmentAuto-check passed
  • Unreal Engine MCP Overview

    flopperam/unreal-engine-mcp

    Maps the tools of the Flopperam Unreal Engine MCP server and how to choose among them when working with a live Unreal Editor.

    1.1k GitHub stars~1.7k tokensUpdated 3 mo ago
    Game DevelopmentAuto-check passed
  • Vibeue

    kevinpbuckley/VibeUE

    Unreal Engine 5 development using the VibeUE Python API. An agent skill from kevinpbuckley/VibeUE.

    730 GitHub stars~5.2k tokensUpdated 3 days ago
    Game DevelopmentAuto-check passed
  • Unreal MCP

    Luciole-Studio/Misaka-Agent

    Automate Unreal Engine editor scenes, actors, and renders. An agent skill from Luciole-Studio/Misaka-Agent.

    171 GitHub starsUsed in 1 repo~3.5k tokens
    Game DevelopmentAuto-check passed
  • UMG MCP Authoring

    winyunq/UnrealMotionGraphicsMCP

    Builds and edits Unreal Engine UMG interfaces through the Unreal Motion Graphics MCP, covering widget trees, HLSL materials, Sequencer animations and readback checks.

    210 GitHub stars~2.6k tokensUpdated 2 mo ago
    Game DevelopmentAuto-check passed

Questions about Unreal Engine MCP

What does Unreal Engine MCP do?

Drives a live Unreal Editor through the unreal-mcp server: spawn actors, edit Blueprints, materials and sequences, change properties and trigger Live Coding. The skill connects the agent to a running Unreal Editor through the `unreal-mcp` MCP server, which offers hundreds of tools in more than 30 toolsets such as actors, Blueprints, materials, Niagara, Sequencer, Control Rigs, GAS, automation tests and Live Coding. The agent inspects and changes editor state itself instead of telling you to do it by hand.

When should I use Unreal Engine MCP?

Unreal Engine MCP fits situations like: spawning, moving or duplicating actors in an Unreal level; creating or editing Blueprints, widgets, materials, Niagara systems or Sequencer assets; reading or writing properties on actors in the open project; triggering a Live Coding recompile after editing C++.

How do I install Unreal Engine MCP in Claude Code?

Run `npx skills add EpicGames/unreal-engine-skills-for-claude-code-plugin --skill unreal-mcp -a claude-code`. Or copy the skill folder (skills/unreal-mcp in EpicGames/unreal-engine-skills-for-claude-code-plugin) into .claude/skills/unreal-mcp in your project. Claude Code loads it when a task matches its description.

How do I install Unreal Engine MCP in Codex?

Run `npx skills add EpicGames/unreal-engine-skills-for-claude-code-plugin --skill unreal-mcp -a codex`. Or copy the skill folder (skills/unreal-mcp in EpicGames/unreal-engine-skills-for-claude-code-plugin) into .agents/skills/unreal-mcp in your project. Codex loads it when a task matches its description.

Can I use Unreal Engine MCP in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add EpicGames/unreal-engine-skills-for-claude-code-plugin --skill unreal-mcp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/unreal-mcp, .gemini/skills/unreal-mcp, .github/skills/unreal-mcp and .opencode/skills/unreal-mcp in your project.

What does Unreal Engine MCP need to run?

SKILL.md names no scripts, command-line tools or credentials: Unreal Engine MCP is instructions for the agent only. Our summary lists: Unreal Editor running with the unreal-mcp server connected.

Does Unreal Engine MCP access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Unreal Engine MCP safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Unreal Engine MCP use?

Unreal Engine MCP is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Unreal Engine MCP use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.1k tokens, read only when the agent opens those files.

What are the alternatives to Unreal Engine MCP?

Skills that share tags, products or a category with Unreal Engine MCP: Unreal Blueprint Authoring (flopperam/unreal-engine-mcp, 1.1k stars), Unreal Scene Building (flopperam/unreal-engine-mcp, 1.1k stars), Unreal Engine MCP Overview (flopperam/unreal-engine-mcp, 1.1k stars) and Vibeue (kevinpbuckley/VibeUE, 730 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Unreal Engine MCP?

EpicGames (a GitHub organization) maintains it in EpicGames/unreal-engine-skills-for-claude-code-plugin, which has 338 GitHub stars. The repository was last updated on September 17, 2026.

Source: EpicGames/unreal-engine-skills-for-claude-code-plugin on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.