Back to MCP Catalog

Everything Search MCP Server

SearchPython
Cross-platform file search utility for macOS, Windows, and Linux
Available Tools

search

Search for files and directories on your computer using platform-specific search tools. Automatically detects your operating system and uses the appropriate search method: mdfind for macOS, Everything for Windows, or find/locate for Linux.

querybasemacos_paramswindows_paramslinux_params

Everything Search is a powerful Model Context Protocol (MCP) server that enables AI assistants to perform fast and efficient file searches across macOS, Windows, and Linux operating systems. It leverages platform-specific search tools like mdfind (macOS), Everything (Windows), and find/locate (Linux) to provide optimized search capabilities tailored to each platform. With Everything Search, users can quickly locate files and directories using natural language queries, complex search patterns, and platform-specific search parameters. The server handles the translation of search requests into the appropriate commands for each operating system, making it a versatile tool for file management and discovery across different environments.

Overview

Everything Search is a cross-platform file search utility that allows AI assistants to search for files and directories on your computer. It supports macOS, Windows, and Linux, using the most efficient search tools available for each platform:

  • macOS: Uses mdfind (Spotlight search)
  • Windows: Uses the "Everything" search engine
  • Linux: Uses find and locate commands

Installation

Prerequisites

Installation Options

Option 1: Install via pip

pip install mcp-server-everything-search

Option 2: Install via Smithery CLI

smithery install mcp-everything-search

Option 3: Install from source

git clone https://github.com/mamertofabian/mcp-everything-search.git
cd mcp-everything-search
pip install -e .

Usage

After installation, you can start the MCP server by adding it to your AI assistant's configuration. The server will automatically detect your operating system and use the appropriate search method.

Basic Search

You can search for files using the search tool with a query parameter:

search(query="document about project")

Advanced Search

Each platform supports different advanced search parameters:

macOS Advanced Search

search(
  query="project proposal", 
  base="/Users/username/Documents",
  macos_params={
    "onlyin": "/Users/username/Documents",
    "live": true,
    "interpret": true
  }
)

Windows Advanced Search

search(
  query="project proposal", 
  base="C:\\Users\\username\\Documents",
  windows_params={
    "regex": true,
    "case": true,
    "whole_word": false,
    "path": "C:\\Users\\username\\Documents"
  }
)

Linux Advanced Search

search(
  query="project proposal", 
  base="/home/username/Documents",
  linux_params={
    "use_locate": true,
    "case_sensitive": false,
    "regex": true,
    "max_depth": 5,
    "type": "f"
  }
)

Platform-Specific Search Syntax

macOS (mdfind)

macOS uses Spotlight's query syntax, which supports:

  • Natural language queries
  • Boolean operators (AND, OR, NOT)
  • Metadata attributes (kind:, date:, author:)
  • Quotes for exact phrases

Windows (Everything)

Windows uses Everything's search syntax, which supports:

  • Wildcards (* and ?)
  • Boolean operators (AND, OR, NOT)
  • File attributes (size:, ext:, date:)
  • Regular expressions (with regex option enabled)

Linux (find/locate)

Linux uses standard find/locate syntax, which supports:

  • Basic filename patterns
  • Regular expressions
  • File type filtering
  • Date and size constraints

Troubleshooting

  • Windows: Ensure Everything Search Engine is installed and running
  • macOS: If Spotlight indexing is disabled, searches may be slower
  • Linux: For faster searches, ensure the locate database is updated regularly with sudo updatedb

If you encounter any issues, check the server logs for detailed error messages.

Related MCPs

SearXNG
SearchTypeScript

Web search capabilities through SearXNG API integration

Hacker News
SearchPython

Access and search Hacker News content programmatically

Web Search
SearchJavaScript

Free Google search integration with no API keys required

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.