Unreal-MCP
★ 39
vs
Comfy-Cozy
★ 25
Unreal-MCP vs Comfy-Cozy
Unreal-MCP: UnrealMCP is an AI bridge for Unreal Engine 5, allowing AI coding assistants to control the UE5 editor through a rich set of 280+ commands. It streamlines game development by enabling AI to create materials, blueprints, VFX, manage data, and profile performance directly from the terminal.; Comfy-Cozy: Comfy Cozy is an AI agent that allows users to interact with ComfyUI using plain English, automating complex workflow tasks like loading, patching, and running generations. It learns user preferences over time, offers reversible changes, and supports multiple LLM providers.
01
TL;DR
Unreal-MCPWorkflow Automation · ★ 39
Material Creation: Generate complex materials with specific properties and graphs (e.g., "Create a red metallic material at /Game/Materials/M_RedMetal with roughness 0.3 and metallic 1.0").
Comfy-CozyWorkflow Automation · ★ 25
Loading and dynamically adjusting parameters of ComfyUI workflows.
02
Side-by-Side Comparison
Field
Unreal-MCPComfy-CozyCategory
Workflow Automation
Workflow Automation
Stars
★ 39
★ 25
License
MPL-2.0
MIT
Install Command
npm install -g unrealcli
git clone https://github.com/JosephOIbrahim/Comfy-Cozy.git && cd Comfy-Cozy && pip install -e .
Updated
2mo ago
3mo ago
Open Source
Yes
Yes
Tags
Unreal Engine, AI Assistant, Game Development
ComfyUI Automation, LLM Agent, Generative AI
03
Features
Unreal-MCP01Comprehensive Editor Control: Over 280 commands across 13 categories for assets, blueprints, materials, data tables, actors, Niagara VFX, StateTree, and performance profiling.
02AI Assistant Integration: Seamlessly integrates with various AI coding assistants like Claude Code, Cursor, VS Code/Copilot, and others via CLI or MCP Server.
03Dual Interface: Offers both a standalone Go CLI (ue-cli) for direct TCP communication and a Python-based MCP server for broader AI tool compatibility.
04Automated Content Creation: Enables AI to programmatically create and modify complex game assets such as materials, blueprints, Niagara VFX, and StateTrees.
05Performance Profiling & Diagnostics: Provides commands to start/stop performance traces and analyze insights directly from the editor.
Comfy-Cozy01Interact with ComfyUI using plain English to automate workflow tasks.
02All changes are non-destructive and reversible with a full undo stack.
03The agent learns and adapts to your personal style and preferences over multiple sessions.
04Supports multiple LLM providers (Anthropic, OpenAI, Gemini, Ollama) via a unified abstraction layer.
05Autonomous mode for self-composing and optimizing workflows based on creative intent.
04
Use Cases
Unreal-MCP↳Material Creation: Generate complex materials with specific properties and graphs (e.g., "Create a red metallic material at /Game/Materials/M_RedMetal with roughness 0.3 and metallic 1.0").
↳Actor Spawning & Placement: Programmatically spawn and position actors in a level (e.g., "Spawn 5 point lights in a circle around the origin at height 300").
↳Blueprint Logic Development: Create Blueprint actors, add components, and implement event-driven logic (e.g., "Create a Blueprint actor called BP_HealthPickup... set it up so on BeginOverlap it prints 'Health Picked Up'").
↳Performance Profiling: Start, stop, and diagnose performance bottlenecks in Unreal Engine (e.g., "Start a performance trace, play for 10 seconds, stop it, then diagnose the bottlenecks").
↳Data Table Management: Interact with and modify data tables (e.g., "Show me the schema of DT_Items, then add a new row called 'IronIngot' with StackSize 100").
Comfy-Cozy↳Loading and dynamically adjusting parameters of ComfyUI workflows.
↳Discovering, downloading, and wiring new models (e.g., from CivitAI, HuggingFace).
↳Automatically repairing broken workflows by installing missing nodes and fixing connections.
↳Analyzing generated outputs using Vision AI and suggesting improvements or optimizations.
↳Executing workflows with specified parameters and monitoring progress.
FAQ
FAQ
What is the difference between Unreal-MCP and Comfy-Cozy?
Both Unreal-MCP and Comfy-Cozy are in the Workflow Automation category. Unreal-MCP has 39 stars, while Comfy-Cozy has 25 stars.
Which is better, Unreal-MCP or Comfy-Cozy?
The best choice depends on your use case. Choose Unreal-MCP if Material Creation: Generate complex materials with specific properties and graphs (e.g., "Create a red metallic material at /Game/Materials/M_RedMetal with roughness 0.3 and metallic 1.0")., and Comfy-Cozy if Loading and dynamically adjusting parameters of ComfyUI workflows..
Is Unreal-MCP free or open source?
Yes, Unreal-MCP is open source on GitHub (MPL-2.0).
Is Comfy-Cozy free or open source?
Yes, Comfy-Cozy is open source on GitHub (MIT).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→