Unreal Engine▌

by runreal
Integrate Unreal Engine with your workflow. Streamline game development using Unreal Engine 5 and UE Engine tools for ma
Integrates with Unreal Engine to assist with game development workflows.
best for
- / Game developers using Unreal Engine 5.4+
- / Automating asset management tasks
- / AI-assisted game development workflows
capabilities
- / Execute Python scripts in Unreal Editor
- / List and query project assets
- / Export assets to text format
- / Get asset information and references
- / Run console commands in Unreal
- / Configure engine and project paths
what it does
Connects to Unreal Engine projects to execute Python scripts, query assets, and run console commands directly from AI assistants. Uses Unreal's built-in Python remote execution without requiring custom plugins.
about
Unreal Engine is a community-built MCP server published by runreal that provides AI assistants with tools and capabilities via the Model Context Protocol. Integrate Unreal Engine with your workflow. Streamline game development using Unreal Engine 5 and UE Engine tools for ma It is categorized under developer tools. This server exposes 20 tools that AI clients can invoke during conversations and coding sessions.
how to install
You can install Unreal Engine in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
license
MIT
Unreal Engine is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
readme
unreal-mcp
MCP server for Unreal Engine that uses Unreal Python Remote Execution


⚡ Differences
This server does not require installing a new UE plugin as it uses the built-in Python remote execution protocol.
Adding new tools/features is much faster to develop since it does not require any C++ code.
It can support the full Unreal Engine Python API
⚠️ Note
- This is not an official Unreal Engine project.
- Your AI agents or tools will have full access to your Editor.
- Review any changes your Client suggests before you approve them.
📦 Installation
📋 Requirements
- 🔧 Unreal Engine 5.4+ (verified, may work with earlier versions)
- 🟢 Node.js with npx
- 🤖 MCP Client (Claude, Cursor, etc.)
- Setting up your Editor:
- Open your Unreal Engine project
- Go to
Edit->Plugins - Search for "Python Editor Script Plugin" and enable it
- Restart the editor if prompted
- Go to
Edit->Project Settings - Search for "Python" and enable the "Enable Remote Execution" option

- Set up your Client:
- Edit your Claude (or Cursor) config
{
"mcpServers": {
"unreal": {
"command": "npx",
"args": [
"-y",
"@runreal/unreal-mcp"
]
}
}
}
🔧 Troubleshooting
If you get an error similar to MCP Unreal: Unexpected token 'C', Connection... it means that the mcp-server was not able to connect to the Unreal Editor.
- Make sure that the Python Editor Script Plugin is enabled and that the Remote Execution option is checked in your project settings.
- Try also changing your bind address from
127.0.0.1to0.0.0.0but note that this will allow connections from your local network. - Restart your Unreal Editor fully.
- Fully close/open your client (Claude, Cursor, etc.) to ensure it reconnects to the MCP server. (
File -> Exiton windows). - Check your running processes and kill any zombie unreal-mcp Node.js processes.
🛠️ Available Tools
| Tool | Description |
|---|---|
set_unreal_engine_path | Set the Unreal Engine path |
set_unreal_project_path | Set the Project path |
get_unreal_engine_path | Get the current Unreal Engine path |
get_unreal_project_path | Get the current Unreal Project path |
editor_run_python | Execute any python within the Unreal Editor |
editor_list_assets | List all Unreal assets |
editor_export_asset | Export an Unreal asset to text |
editor_get_asset_info | Get information about an asset, including LOD levels for StaticMesh and SkeletalMesh assets |
editor_get_asset_references | Get references for an asset |
editor_console_command | Run a console command in Unreal |
editor_project_info | Get detailed information about the current project |
editor_get_map_info | Get detailed information about the current map/level |
editor_search_assets | Search for assets by name or path with optional class filter |
editor_get_world_outliner | Get all actors in the current world with their properties |
editor_validate_assets | Validate assets in the project to check for errors |
editor_create_object | Create a new object/actor in the world |
editor_update_object | Update an existing object/actor in the world |
editor_delete_object | Delete an object/actor from the world |
editor_take_screenshot | Take a screenshot of the Unreal Editor |
editor_move_camera | Move the viewport camera to a specific location and rotation for positioning screenshots |
🤝 Contributing
Please feel free to open issues or pull requests. Contributions are welcome, especially new tools/commands.
<a href="https://glama.ai/mcp/servers/@runreal/unreal-mcp"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@runreal/unreal-mcp/badge" /> </a>License MIT
FAQ
- What is the Unreal Engine MCP server?
- Unreal Engine is a Model Context Protocol (MCP) server profile on explainx.ai. MCP lets AI hosts (e.g. Claude Desktop, Cursor) call tools and resources through a standard interface; this page summarizes categories, install hints, and community ratings.
- How do MCP servers relate to agent skills?
- Skills are reusable instruction packages (often SKILL.md); MCP servers expose live capabilities. Teams frequently combine both—skills for workflows, MCP for APIs and data. See explainx.ai/skills and explainx.ai/mcp-servers for parallel directories.
- How are reviews shown for Unreal Engine?
- This profile displays 10 aggregated ratings (sample rows for discoverability plus signed-in user reviews). Average score is about 4.5 out of 5—verify behavior in your own environment before production use.
Ratings
4.5★★★★★10 reviews- ★★★★★Shikha Mishra· Oct 10, 2024
Unreal Engine is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
- ★★★★★Piyush G· Sep 9, 2024
We evaluated Unreal Engine against two servers with overlapping tools; this profile had the clearer scope statement.
- ★★★★★Chaitanya Patil· Aug 8, 2024
Useful MCP listing: Unreal Engine is the kind of server we cite when onboarding engineers to host + tool permissions.
- ★★★★★Sakshi Patil· Jul 7, 2024
Unreal Engine reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
- ★★★★★Ganesh Mohane· Jun 6, 2024
I recommend Unreal Engine for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
- ★★★★★Oshnikdeep· May 5, 2024
Strong directory entry: Unreal Engine surfaces stars and publisher context so we could sanity-check maintenance before adopting.
- ★★★★★Dhruvi Jain· Apr 4, 2024
Unreal Engine has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
- ★★★★★Rahul Santra· Mar 3, 2024
According to our notes, Unreal Engine benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
- ★★★★★Pratham Ware· Feb 2, 2024
We wired Unreal Engine into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
- ★★★★★Yash Thakker· Jan 1, 2024
Unreal Engine is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.