Unreal_mcp and unreal-mcp

These are competing implementations of MCP servers for Unreal Engine control, both offering similar natural language AI integration capabilities but differing in their underlying architecture (native C++ Automation Bridge versus a more general MCP approach).

Unreal_mcp
52
Established
unreal-mcp
36
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 9/25
Community 20/25
Maintenance 2/25
Adoption 10/25
Maturity 1/25
Community 23/25
Stars: 362
Forks: 61
Downloads:
Commits (30d): 0
Language: C++
License: MIT
Stars: 1,546
Forks: 235
Downloads:
Commits (30d): 0
Language: C++
License:
No Package No Dependents
No License Stale 6m No Package No Dependents

About Unreal_mcp

ChiR24/Unreal_mcp

A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal Engine through the native C++ Automation Bridge plugin. Built with TypeScript and C++.

Provides runtime type introspection and dynamic discovery for Unreal Engine subsystems (lights, debug shapes, sequencer tracks), with graceful degradation allowing the server to start without an active connection and automatic reconnection via exponential backoff. Exposes 36 MCP tools covering asset management, actor control, animation, VFX, sequencer, and blueprint graph editing, routing all operations through a native C++ Automation Bridge plugin with command safety validation and asset caching for performance optimization.

About unreal-mcp

chongdashu/unreal-mcp

Enable AI assistant clients like Cursor, Windsurf and Claude Desktop to control Unreal Engine through natural language using the Model Context Protocol (MCP).

Implements a native C++ TCP server plugin paired with a Python MCP server using FastMCP, enabling comprehensive Unreal workflows including actor manipulation, Blueprint creation with node graph editing, and real-time viewport control. The architecture uses stdio transport between AI clients and the Python server, which communicates via TCP (port 55557) with the Unreal plugin to execute serialized commands and return responses.

Scores updated daily from GitHub, PyPI, and npm data. How scores work