MCP Comfy Ui Builder
An MCP server for ComfyUI node discovery and workflow building, providing a knowledge base, dynamic workflow building, real-time execution, and model management tools.
rating : 2 points
downloads : 4.9K
What is ComfyUI Builder MCP Server?
This is an MCP server specifically designed for ComfyUI, which allows you to intelligently discover, build, and manage ComfyUI workflows through AI assistants (such as Cursor or Claude). It includes a knowledge base, node discovery, workflow templates, and real-time execution functions, enabling you to avoid manually writing complex JSON workflows.How to use ComfyUI Builder?
After installation, configure the MCP server in Cursor or Claude Desktop, and then you can discover nodes, build workflows, and execute image generation tasks through natural language instructions. The system will automatically handle technical details, and you only need to focus on creative needs.Applicable Scenarios
Suitable for AI image generation enthusiasts, designers, content creators, and anyone who wants to simplify the ComfyUI workflow creation process. Particularly suitable for: 1. Rapid prototyping 2. Batch image generation 3. Complex workflow construction 4. Learning and exploring ComfyUI node functionsMain Features
Intelligent Node Discovery
Built-in knowledge base of 62 seed nodes, which can be synchronized to over 600 nodes. Supports node search, compatibility check, and intelligent suggestions.
Dynamic Workflow Building
No need to manually write JSON. You can create, connect, and verify workflow nodes through natural language instructions.
Preset Template System
Provides 9 preset templates (txt2img, img2img, inpainting, upscale, LoRA, ControlNet, etc.) to quickly start common tasks.
Real-time WebSocket Execution
Supports real-time progress tracking via WebSocket, providing sub-second updates and reducing network traffic by 90% compared to polling.
Batch and Chained Execution
Supports batch concurrent execution and sequential chained workflows, allowing data transfer to improve efficiency.
Intelligent Resource Management
Automatically detects system resources (GPU/VRAM/RAM) and provides suggestions on resolution, model size, and batch size to avoid memory overflow.
Model Management
Supports the management and inspection of various models such as checkpoints, LoRA, VAE, ControlNet, upscale, embedding, and CLIP.
Plugin System
A data-driven plugin system that supports viewing and reloading the plugin list.
Advantages
No technical background required: Build complex workflows through natural language
Real-time feedback: WebSocket provides sub-second execution progress updates
Intelligent suggestions: Node compatibility check and recommendation based on the knowledge base
Resource optimization: Batch execution reduces network traffic by 90%
Ready to use: Built-in rich templates and node knowledge base
Highly scalable: Supports the installation of custom nodes and models
Limitations
Requires a ComfyUI environment: ComfyUI must be installed and running
Learning curve: Basic ComfyUI concepts need to be understood
Network dependency: Some functions require a connection to a ComfyUI instance
Complex configuration: Initial MCP server configuration requires technical operations
How to Use
Install Dependencies
Ensure that Node.js 18+ and ComfyUI are installed. Install the MCP server via npm.
Build the Project
Build the project to generate the knowledge base and server files.
Configure the MCP Client
Add the MCP server configuration in Cursor or Claude Desktop. The absolute path to dist/mcp-server.js needs to be provided.
Configure Environment Variables (Optional)
If you need to execute workflows, set the COMFYUI_HOST environment variable to point to your ComfyUI instance.
Restart the Client
Restart Cursor or Claude Desktop to load the new MCP server configuration.
Start Using
In the chat interface, you can start using natural language instructions to build and manage ComfyUI workflows.
Usage Examples
Rapid Text-to-Image Generation
The user wants to quickly generate an image based on a text description without manually building a complex workflow.
Image Repair and Enhancement
The user has an old photo that needs to be repaired and enhanced, including denoising, color correction, and resolution improvement.
Batch Generation with Consistent Styles
Content creators need to generate a series of social media images with consistent styles, using the same artistic style but different themes.
Exploration of Complex Workflows
Advanced users want to explore new ComfyUI node combinations and test the impact of different parameter settings on the output results.
Frequently Asked Questions
Do I need to install ComfyUI first?
Why does the MCP server fail to start with the error 'spawn node ENOENT'?
Can I use this tool offline?
How to update the node knowledge base?
Which ComfyUI versions are supported?
Can I create custom templates?
What are the advantages of batch execution?
How to avoid memory overflow errors?
Related Resources
GitHub Repository
Project source code, issue tracking, and contribution guidelines
MCP Registry
Official registry of the Model Context Protocol
ComfyUI Official
Official repository and documentation of ComfyUI
Docker Image
Pre-built Docker container image
Complete Document Index
Complete index of all project documents
MCP Setup Guide
Detailed MCP server configuration and troubleshooting guide
Workflow Building Guide
Detailed instructions and examples for workflow building
WebSocket Function Guide
Detailed instructions for real-time WebSocket functions

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.3K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
25.4K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.7K
4.3 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.1K
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.4K
4.5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.0K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
98.2K
4.7 points


