Server profile

Unreal MCP

Unreal MCP links assistant requests to Unreal Editor through a Python server and C++ plugin. It covers scene objects, Blueprint construction, and viewport adjustments, but the project explicitly remains experimental.

Server facts

Unreal MCP

Project

License
Not specified
Category
Games & 3D

Tech

Runtime / language
c++C++ and Python
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
2,096
Last commit
Data as of

Tags

  • Blueprint Editing
  • Cpp
  • Editor Control
  • Python
  • Unreal Engine

Overview

Unreal MCP requires an editor-side component as well as an assistant-facing server. The native UnrealMCP plugin integrates with editor subsystems and accepts commands over TCP. A Python process built with FastMCP manages the connection, translates commands and responses, and registers the available tool modules. The documented link between those processes uses port 55557. For initial experimentation, the repository includes a blank Unreal sample with its plugin configuration already present. An existing project can instead receive a copied plugin, followed by enabling it and building the native code. Neither route removes the plugin build requirement.

Once connected, the integration reaches across scene editing and Blueprint development. It can reposition or inspect actors, create objects such as lights and cameras, and remove actors from a level. Blueprint work includes component setup, physics properties, compilation, spawning, and player-input mappings. Graph editing adds another layer: assistants can introduce variables and event or function nodes, connect them, and work with component or self references. Viewport commands control focus and camera placement. The stated baseline is Python 3.12 together with Unreal Engine 5.5, or newer versions of each, plus an MCP-capable client. However, the README warns that functionality and interfaces may change substantially, documentation can lag, and production deployment is discouraged. It describes capabilities without supplying individual tool identifiers, so no named tool list is inferred here.

Install & configure

Requirements

  • Unreal Engine version 5.5 or above
  • Python version 3.12 or above
  • uv, as used in the supplied client example
  • Built and enabled UnrealMCP plugin
  • Client capable of connecting to an MCP server
Documented launch / install command
uv --directory '' run unreal_mcp_server.py

This preserves the README argument array, whose directory value is empty. Fill that value with the server's Python directory before launching; the example is incomplete without it. Prepare and build the plugin separately, or build the supplied sample project that already includes its configuration.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "unreal-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "",
        "run",
        "unreal_mcp_server.py"
      ],
      "env": {}
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "unreal-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "",
        "run",
        "unreal_mcp_server.py"
      ],
      "env": {}
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "unreal-mcp": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "--directory",
        "",
        "run",
        "unreal_mcp_server.py"
      ],
      "env": {}
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "unreal-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "",
        "run",
        "unreal_mcp_server.py"
      ],
      "env": {}
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "unreal-mcp": {
      "type": "stdio",
      "command": "uv",
      "args": [
        "--directory",
        "",
        "run",
        "unreal_mcp_server.py"
      ],
      "env": {}
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

No individual tool names were confirmed in the source material. Check the repository for its current tool list.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Prototype a scene by creating actors and changing their placement from an assistant.
  • Build out a Blueprint's components, physics options, and input mappings.
  • Experiment with event and function connections inside a Blueprint graph.
  • Move the editor view to an actor or a requested location.

Strengths

  • Reaches both scene-level operations and Blueprint graph construction.
  • Includes a starter Unreal project with plugin configuration in place.
  • Allows the native integration to be added to an existing project.

Limitations

  • Experimental status includes the possibility of breaking changes and unfinished behavior.
  • Native plugin compilation and a separate Python server are both part of setup.
  • Exact MCP tool names: Not stated in the README.

Frequently asked questions

The C++ plugin connects to Unreal Editor subsystems. A separate FastMCP process in Python communicates with it through a TCP socket.

No. It already contains the plugin configuration, but the quickstart still calls for generating project files and building the project with the plugin.

Yes. Documented areas include Blueprint components and node graphs, player-control mappings, and editor viewport operations.

The README advises against production use. It warns about unstable or incomplete features, shifting interfaces, and potentially stale documentation.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

BlenderMCP

Games & 3D

BlenderMCP links AI assistants to Blender for scene inspection, object and material changes, and Python execution. Optional asset integrations add Poly Haven downloads, Sketchfab models, and generated 3D assets.

MCP for Unity

Games & 3D

MCP for Unity links AI assistants to the Unity Editor for scene work, asset management, script editing, testing, and builds. It targets game developers who want to direct editor workflows through natural language.

Godot MCP

Games & 3D

Godot MCP lets AI agents open the editor, run projects, and inspect debug output. It also supports scene and node operations, sprite loading, mesh-library export, and UID maintenance for supported Godot versions.

MCP Unity Editor

Games & 3D

Connect AI assistants to Unity Editor through a Unity package and Node.js MCP bridge. Manage scenes, GameObjects, materials, packages, tests, and console logs, with resources and guided workflow prompts.

Unreal Engine Generative AI Support Plugin

Games & 3D

This Unreal Engine plugin combines generative AI API integrations with MCP-based editor control. Assistants can manipulate scene objects, work with some Blueprint features, and run editor scripts, although MCP development is inactive.

Minecraft MCP Server

Games & 3D

Minecraft MCP Server lets an AI assistant control a Minecraft character through Mineflayer. Tools cover movement, blocks, inventory, smelting, entities, and chat, with a documented local LAN-world setup.