Jonpojonpo Comfy Ui MCP Server

An MCP server that connects to local ComfyUI, providing note management and summary generation functions

Note-taking tools Knowledge management and memory #Note Management #Summary Generation #MCP Service #Local Connection .Python

rating : 2 points

downloads : 20

update time : 2025-04-29

What is the ComfyUI MCP Server?

The ComfyUI MCP Server serves as a bridge between your local ComfyUI installation and client applications, offering note management capabilities and AI-driven note summarization.

How to use the ComfyUI MCP Server?

After installation and configuration, you can interact with the server through supported client applications to manage and generate note summaries.

Use Cases

Suitable for researchers, developers, and data scientists for experimental inference, rapid prototyping, and plugin-based enhancements to models.

Support for Multiple Input Formats

Supports multiple input formats such as JSON, Markdown, and plain text to meet different needs.

Intelligent Content Summarization

Utilizes AI technology to automatically generate structured summaries for notes, improving work efficiency.

Plugin-based Expansion

Supports expanding functionality through plugins, enhancing the server's flexibility and customizability.

Installation Guide

Clone the project repository to your local machine

Install project dependencies

Start the server and begin using it

Usage Instructions

Frequently Asked Questions

How to handle server connection issues?

Which programming languages are supported?

How to upgrade the server version?

More Resources

MCP Inspection Tool

A tool for debugging MCP server communication.

ComfyUI Official Documentation

Official documentation resources for ComfyUI.

MCP Protocol Specification

Detailed specification of the Model Context Protocol.

🚀 Comfy-UI MCP Server

A server for connecting to the local Comfy-UI.

🚀 Quick Start

📦 Installation

Desktop (Mac & Windows)

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development/Unreleased Server Configuration

``` "mcpServers": { "comfy-ui-mcp-server": { "command": "uv", "args": [ "--directory", "E:\\Claude\\comfy-ui-mcp-server", "run", "comfy-ui-mcp-server" ] } } ```

Released Server Configuration

``` "mcpServers": { "comfy-ui-mcp-server": { "command": "uvx", "args": [ "comfy-ui-mcp-server" ] } } ```

✨ Features

🔍 Resources

The server implements a simple note storage system with:

A custom note:// URI scheme for accessing individual notes.
Each note resource includes a name, description, and a text/plain format type.

💡 Prompts

The server provides a prompt:

summarize-notes: Generate a summary of all stored notes.
- An optional "style" parameter to control the level of detail (concise/detailed).
- Generate a prompt containing all current notes based on style preferences.

🛠️ Tools

The server implements a tool:

add-note: Add a new note to the server.
- Accept "name" and "content" as required string parameters.
- Update the server state and notify clients of resource changes.

📚 Documentation

⚙️ Configuration

[To-do: Add implementation-specific configuration details]

🛠️ Development

🔨 Build and Publish

Prepare the package for distribution:

Synchronize dependencies and update the lock file:

uv sync

Build the package distribution:

uv build

This will create source and wheel format distributions in the dist/ directory.

Publish to PyPI:

uv publish

Note: You need to set your PyPI credentials via environment variables or command-line flags:

Token: --token or UV_PUBLISH_TOKEN
Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

🐞 Debugging

Since the MCP server runs via stdio, debugging can be challenging. For the best debugging experience, we highly recommend using MCP Inspector.

You can start the MCP inspector via npm with the following command:

npx @modelcontextprotocol/inspector uv --directory E:\\Claude\\comfy-ui-mcp-server run comfy-ui-mcp-server

After starting, the inspector will display a URL that you can access in your browser to begin debugging.

Featured MCP Services

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

4.3 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.

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

150

4.5 points

Duckduckgo MCP Server

Certified

The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.

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.

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.

573

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.

The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.

Python

761

4.8 points

Zhiqi Future, Your AI Solution Think Tank

English 简体中文繁體中文にほんご