WizTree MCP Server
Bridges AI assistants with WizTree to scan drives, find large files/folders, and perform intelligent cleanups.
README
<div align="center"> <h1>🚀 WizTree MCP Server</h1> <p><strong>Supercharge your AI Assistant with the world's fastest disk space analyzer.</strong></p>
<p> <img alt="Platform" src="https://img.shields.io/badge/Platform-Windows-blue?style=flat-square&logo=windows"> <img alt="Python Version" src="https://img.shields.io/badge/Python-3.10%2B-blue?style=flat-square&logo=python"> <img alt="License" src="https://img.shields.io/badge/License-MIT-green?style=flat-square"> <img alt="Protocol" src="https://img.shields.io/badge/Protocol-MCP-purple?style=flat-square"> </p> </div>
🌟 Overview
The WizTree MCP Server seamlessly bridges your AI assistant (Claude, Cursor, Antigravity, etc.) with WizTree, allowing your AI to instantly scan your hard drives, identify massive space hogs, and execute intelligent cleanups.
Turn your AI into a highly contextual storage manager!
✨ Features
- ⚡ Lightning Fast: Leverages WizTree's MFT (Master File Table) reading to scan drives in seconds.
- 🧠 AI-Powered Workflows: Ask your AI: "What's eating up space on my C: drive?" or "Analyze my Downloads folder."
- 🛡️ Built-in Guardrails: Comes with a comprehensive
/skillsdirectory to teach your AI strict deletion policies and safe handling of files. - 💻 Developer Focused: Perfect for finding hidden
node_modules, stray__pycache__folders, or giant dangling Docker images.
🧠 AI Agent Skills
Unlike basic MCP servers that just dump raw data, this repository includes a dedicated /skills directory and a SYSTEM_PROMPT.md. These Markdown files teach your AI client how to use the tools effectively and safely.
Available skills include:
- 🛡️ Deletion Policy: Enforces a strict multi-step workflow before any files are deleted.
- 🗑️ Safe Delete: Defines exactly what is safe to delete (e.g., caches) and what should never be touched (e.g., system files).
- 👨💻 Developer Cleanup: Gives the AI deep knowledge of where dev tools (Docker, npm, pip) hide their massive cache files.
🚀 Installation
1. Prerequisites
- Windows OS
- WizTree (installed at
C:\Program Files\WizTree\WizTree64.exe) - Python 3.10+
2. Clone the Repository
git clone https://github.com/sahmed730/Wiztree-Mcp.git
cd Wiztree-Mcp
3. Setup Virtual Environment
python -m venv .venv
.\.venv\Scripts\Activate
pip install -r requirements.txt
⚙️ Configuration
Add the server to your MCP client configuration (e.g., mcp_config.json for Antigravity, or claude_desktop_config.json for Claude):
{
"mcpServers": {
"wiztree": {
"command": "C:\\path\\to\\Wiztree-Mcp\\.venv\\Scripts\\python.exe",
"args": [
"C:\\path\\to\\Wiztree-Mcp\\server.py"
]
}
}
}
⚠️ Note: Replace
C:\\path\\to\\with the exact absolute path to your cloned directory.
🤖 Example Prompts
Once connected, try asking your AI:
- 💬 "Can you find the 15 largest files on my C: drive?"
- 💬 "My SSD is full. Find the largest folders in my user profile, skipping my personal photos."
- 💬 "Do a developer cleanup on my machine to free up at least 20 GB."
<div align="center"> <i>Built with ❤️ for the MCP Community</i> </div>
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。