MCP Puppet Pipeline

MCP Puppet Pipeline

Enables browser automation and AI-driven workflows through Puppeteer integration, with file management, agent coordination, and QNAP network storage support.

Category
访问服务器

README

MCP Puppet Pipeline

Model Context Protocol (MCP) puppet automation pipeline for browser automation and AI-driven workflows.

Overview

A comprehensive MCP server implementation that provides tools and workflows for automated browser control, file operations, and AI agent coordination. Includes file hygiene management, conversation continuity, and QNAP integration.

Features

  • MCP Server: Full MCP protocol implementation
  • Browser Automation: Puppet-based web automation
  • File Hygiene: Automated file organization and cleanup
  • Conversation Continuity: Agent state management across sessions
  • QNAP Integration: Network storage integration
  • Auto-Startup: System initialization and startup automation
  • Logging System: Comprehensive logging and monitoring
  • Handoff System: Agent-to-agent task handoffs

Tech Stack

  • TypeScript/Node.js
  • Model Context Protocol (MCP)
  • Puppeteer for browser automation
  • QNAP network storage integration

Getting Started

Prerequisites

  • Node.js (v18+ recommended)
  • QNAP NAS (for storage integration)
  • Access to MCP-compatible AI systems

Installation

npm install

Configuration

  1. Configure QNAP connection in qnap-config.json
  2. Set up logging preferences in logging-config.json
  3. Configure MCP server in mcp-server-config.js
  4. Review and customize startup scripts

Usage

# Run setup
./run_mcp_setup.sh

# Start MCP system (Windows)
START-MCP-SYSTEM.bat

# Run pre-initialization
node run-pre-init.js

# Start server
npm start

Project Structure

  • src/ - Source code
    • server.ts - Main MCP server
    • agents/ - Agent implementations
    • integrations/ - External service integrations
    • tools/ - MCP tools
    • logging/ - Logging system
  • workflows/ - Workflow definitions
  • handoffs/ - Agent handoff sessions
  • inventory/ - File and resource inventory
  • public/ - Public assets

Key Components

File Hygiene Agent

Automated file organization, cleanup, and management system with registry tracking.

Conversation Continuity Agent

Maintains context and state across agent sessions and handoffs.

Affogato Integration

Character pipeline and asset management through Affogato API.

Auto Handoff System

Automated task routing and handoffs between agents.

Documentation

See individual markdown files for detailed documentation:

  • AUTO-STARTUP-SETUP.md - Startup automation
  • FILE_HYGIENE_MCP_GUIDE.md - File hygiene system
  • REMEDIATION_CHECKLIST.md - System remediation

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选