mcp-everything-search
Everything Search MCP Server (PRO)
🇨🇳 中文版
一款专为 Windows 打造的高性能 Model Context Protocol (MCP) 服务器。本工具利用原生的 Everything SDK,为 AI 模型(如 Claude、GPT、Gemini)提供毫秒级的文件搜索、统计分析及磁盘空间洞察能力。
🚀 核心特性
极致速度:基于
Everything64.dll原生调用,数百万个文件搜索仅需毫秒级响应。AI 意图自动引导 (Autopilot):内置运行时意图拦截与专用工具(如
find_largest_folders),防止 AI 模型在处理大数据量任务时陷入低效的递归扫描。智能环境诊断:主动检测磁盘索引状态,并在驱动器未索引时提供精确的修复引导。
完美支持中文:原生解决 Windows 环境下的中文乱码问题,确保路径处理 100% 准确。
多客户端适配:安装程序支持自动配置 OpenCode 和 Claude Desktop。
🛠 包含工具
工具名称 | 功能描述 |
| 元数据搜索(名称、路径、后缀)。极致速度且精准。 |
| 文件分布与大小的深度统计分析。 |
| 磁盘空间分析专用工具(查找占用空间最大的目录)。 |
| 查找包含文件数量最多的目录。 |
| 查看已索引驱动器列表及引擎健康状态。 |
📦 安装指引 (Windows)
从 Releases 页面下载最新的
mcp-everything-search.zip。将压缩包解压到您的本地固定目录。
双击运行
install.exe。程序将自动尝试为 OpenCode 和 Claude Desktop 完成配置。重启您的 AI 客户端。
Related MCP server: everything-mcp-server
🇺🇸 English Version
A high-performance Model Context Protocol (MCP) server built for Windows. Leveraging the native Everything SDK, it provides AI models (like Claude, GPT, Gemini) with millisecond-speed file searching, statistical analysis, and disk usage insights.
🚀 Key Features
Ultra-Fast Search: Powered by
Everything64.dll, searching millions of files in milliseconds.AI-Intent Autopilot: Features runtime intent interception and specialized tools (e.g.,
find_largest_folders) to prevent AI models from falling into inefficient recursive scans.Smart Diagnostics: Proactively monitors indexing status and provides actionable hints for unindexed drives.
Full Unicode Support: Native resolution for Chinese characters and special symbols on Windows.
Multi-Client Support: The installer automatically configures OpenCode and Claude Desktop.
🛠 Tools Available
everything_search: Lightning-fast metadata search.everything_stats: Statistical analysis of file distribution.find_largest_folders: Dedicated tool for disk usage analysis.find_most_files: Locate directories with the highest file counts.get_engine_status: Check indexing status and drive coverage.
📦 Installation (Windows Only)
Download
mcp-everything-search.zipfrom Releases.Extract to a permanent local directory.
Run
install.exe. It will automatically configure OpenCode and Claude Desktop.Restart your AI client.
👨💻 Authors / 作者
guodaxia9527 - Lead Developer / 首席开发
Gemini Flash Latest - AI System Architect / AI 架构师
📜 Credits & License / 鸣谢与许可证
Everything SDK: A product of voidtools (https://www.voidtools.com/).
License: This project is licensed under the MIT License.
Note: This tool requires Windows and may request Administrator privileges (UAC) to access NTFS USN Journals if the Everything service is not running.
This server cannot be deployed
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA minimal and extensible local MCP server that provides core utilities like ping and echo alongside a file search tool integrated with the Everything CLI. It enables fast local file searching and service testing through a standardized stdio transport layer.-
- AlicenseNot gradedqualityDmaintenanceEnables instant file searches on Windows using Everything's native SDK, supporting advanced filters, duplicate detection, and content search through MCP tools.5MIT
- AlicenseAqualityDmaintenanceLocal MCP server for searching a voidtools Everything 1.5a index from Codex, Claude, and other MCP clients.28 npmMIT
- AlicenseCqualityBmaintenanceA full-featured secure MCP server for local file system operations, with built-in image processing, OCR and media tools. Fully compliant with the official Model Context Protocol specification, offering standardized request/response schemas, large-file streaming I/O, multi-transport remote deployment, and comprehensive text search & replace functionality for LLM agent integration.22Apache 2.0