mcp-everything-search

mcp-everything-search

Integrates Everything file search with Claude Desktop, enabling instant Windows filesystem search via natural language queries.

Category
Visit Server

README

Everything MCP Server

PyPI version License: MIT

An MCP (Model Context Protocol) server that integrates Everything file search with Claude Desktop. Search your entire Windows filesystem instantly from Claude.

Features

  • Instant search - Leverages Everything's lightning-fast file indexing
  • 🔍 Multiple search modes - Basic, filtered, regex, type-based, attribute-based
  • 📁 Folder operations - Search within specific paths, find empty folders
  • 📊 Statistics - Get file counts and total sizes without listing files
  • 🕐 Recent files - Find recently modified files
  • 📋 Duplicate finder - Locate files with the same name
  • 💾 Export - Save results to txt, csv, json, and more

Prerequisites

  1. Windows - Everything only runs on Windows
  2. Everything must be installed and running
  3. es.exe (Everything command-line) installed
    • Install from: https://github.com/voidtools/es
    • Must be in %LOCALAPPDATA%\Microsoft\WindowsApps

Installation

Using uvx (recommended)

uvx mcp-everything-search

Using pip

pip install mcp-everything-search

Configuration

Add this to your Claude Desktop config file:

Location: %APPDATA%\Claude\claude_desktop_config.json

Using uvx

{
  "mcpServers": {
    "everything-search": {
      "command": "uvx",
      "args": ["mcp-everything-search"]
    }
  }
}

Using pip

{
  "mcpServers": {
    "everything-search": {
      "command": "python",
      "args": ["-m", "mcp_everything_search"]
    }
  }
}

Everything 1.5 Alpha Users

If you're using Everything 1.5 alpha, add the EVERYTHING_INSTANCE environment variable:

{
  "mcpServers": {
    "everything-search": {
      "command": "uvx",
      "args": ["mcp-everything-search"],
      "env": {
        "EVERYTHING_INSTANCE": "1.5a"
      }
    }
  }
}

Then restart Claude Desktop.

Available Tools

Basic Search

Tool Description
search_files Basic file search with wildcards (*, ?), sorting options
search_with_filters Search with extension, size, path filters, files/folders only
search_regex Search using regular expressions

Specialized Search

Tool Description
search_by_type Search by category: audio, video, image, document, executable, compressed, code
search_folders Find only directories
search_recent_files Find recently modified files
search_duplicates Find files with the same name
search_by_attributes Filter by hidden, system, read-only, compressed, encrypted
search_empty_folders Find empty directories
search_large_files Find files over a specified size

Utilities

Tool Description
search_with_details Search with detailed output (size, dates)
get_result_count Get count of matches without listing (fast)
get_total_size Get total size of all matching files
open_file_location Open containing folder in Explorer
get_file_info Get file size, dates, and details
export_search_results Export to txt, csv, json, m3u, m3u8, tsv, efu

Example Queries

Ask Claude things like:

  • "Find all Python files in D:\Projects"
  • "Search for PDF files larger than 10mb"
  • "Find images modified in the last 3 days"
  • "Look for duplicate files named config.json"
  • "Find all video files in my Downloads folder"
  • "Search for files matching regex test_.*\.py$"
  • "Find empty folders in D:\Archive"
  • "What's the total size of all MP3 files?"
  • "How many JavaScript files are in this project?"
  • "Find hidden files in C:\Windows"
  • "Export all log files to a CSV"

Sort Options

Many tools support sort_by parameter:

  • name, path, size, extension
  • date-modified, date-created, date-accessed
  • Add -descending for reverse order (e.g., size-descending)

Development

# Clone the repo
git clone https://github.com/essovius/mcp-everything-search.git
cd mcp-everything-search

# Create virtual environment
python -m venv venv
.\venv\Scripts\activate

# Install in development mode
pip install -e .

# Run the server
python -m mcp_everything_search

License

MIT License - see LICENSE for details.

Acknowledgments

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured