ath-maas/pixelle-mcp

🎨 Pixelle MCP — Фреймворк омнимодального агента

Английский | 中文

✨ Решение AIGC, основанное на протоколе MCP, поддерживающее как локальный режим ComfyUI, так и облачный режим ComfyUI (RunningHub), бесшовно преобразующий рабочие процессы в MCP-инструменты без кода.

https://github.com/user-attachments/assets/65422cef-96f9-44fe-a82b-6a124674c417

📋 Последние обновления

• ✅ 2025-09-29: Добавлена поддержка облачного ComfyUI от RunningHub, позволяющая выполнять рабочий процесс без локальной GPU и среды ComfyUI
• ✅ 2025-09-03: Рефакторинг архитектуры с трёх сервисов в унифицированное приложение; добавлена поддержка инструментов CLI; опубликовано в PyPI
• ✅ 2025-08-12: Интегрирован фреймворк LiteLLM, добавлена поддержка нескольких моделей для Gemini, DeepSeek, Claude, Qwen и других

🚀 Особенности

• ✅ 🔄 Полная модальная поддержка: поддерживает полномодальное преобразование и генерацию TISV (текст, изображение, звук/речь, видео)
• ✅ 🚀 Двойные режимы выполнения: локальная самостоятельная среда ComfyUI + облачный сервис ComfyUI RunningHub, пользователи могут гибко выбирать в зависимости от своих потребностей
• ✅ 🧩 ComfyUI Ecosystem: Построена на ComfyUI, унаследовав все возможности от открытой экосистемы ComfyUI

🎨 Pixelle MCP - Omnimodal Agent Framework

English | 中文

✨ An AIGC solution based on the MCP protocol, supporting both local ComfyUI and cloud ComfyUI (RunningHub) modes, seamlessly converting workflows into MCP tools with zero code.

https://github.com/user-attachments/assets/65422cef-96f9-44fe-a82b-6a124674c417

📋 Recent Updates

• ✅ 2025-09-29: Added RunningHub cloud ComfyUI support, enabling workflow execution without local GPU and ComfyUI environment
• ✅ 2025-09-03: Architecture refactoring from three services to unified application; added CLI tool support; published to PyPI
• ✅ 2025-08-12: Integrated the LiteLLM framework, adding multi-model support for Gemini, DeepSeek, Claude, Qwen, and more

🚀 Features

• ✅ 🔄 Full-modal Support: Supports TISV (Text, Image, Sound/Speech, Video) full-modal conversion and generation
• ✅ 🚀 Dual Execution Modes: Local ComfyUI self-hosted environment + RunningHub cloud ComfyUI service, users can flexibly choose based on their needs
• ✅ 🧩 ComfyUI Ecosystem: Built on ComfyUI, inheriting all capabilities from the open ComfyUI ecosystem
• ✅ 🔧 Zero-code Development: Defines and implements the Workflow-as-MCP Tool solution, enabling zero-code development and dynamic addition of new MCP Tools
• ✅ 🗄️ MCP Server: Based on the MCP protocol, supporting integration with any MCP client (including but not limited to Cursor, Claude Desktop, etc.)
• ✅ 🌐 Web Interface: Developed based on the Chainlit framework, inheriting Chainlit’s UI controls and supporting integration with more MCP Servers
• ✅ 📦 One-click Deployment: Supports PyPI installation, CLI commands, Docker and other deployment methods, ready to use out of the box
• ✅ ⚙️ Simplified Configuration: Uses environment variable configuration scheme, simple and intuitive configuration
• ✅ 🤖 Multi-LLM Support: Supports multiple mainstream LLMs, including OpenAI, Ollama, Gemini, DeepSeek, Claude, Qwen, and more

📁 Project Architecture

Pixelle MCP adopts a unified architecture design, integrating MCP server, web interface, and file services into one application, providing:

• 🌐 Web Interface: Chainlit-based chat interface supporting multimodal interaction
• 🔌 MCP Endpoint: For external MCP clients (such as Cursor, Claude Desktop) to connect
• 📁 File Service: Handles file upload, download, and storage
• 🛠️ Workflow Engine: Supports both local ComfyUI and cloud ComfyUI (RunningHub) workflows, automatically converts workflows into MCP tools

🏃‍♂️ Quick Start