Enhanced Everything MCP Server
Integrates voidtools Everything search engine with AI assistants to provide lightning-fast file search, GitHub integration, intent-based code research, and spec-driven development tools for Windows.
README
Enhanced Everything MCP Server
A comprehensive Model Context Protocol (MCP) server that transforms voidtools Everything search engine into an intelligent development research platform. Integrates with AI assistants like Cursor, Kiro IDE, SpecStory, and Claude to provide lightning-fast file search, GitHub integration, intent-based code research, and spec-driven development tools.
šÆ Kiro IDE Integration Workflow
Complete spec-driven development workflow from requirements to implementation
š Features
Core Search Capabilities
- Lightning Fast Search: Leverages Everything's instant search capabilities
- Advanced Filtering: Filter by file types, size, date, and more
- Multiple Sort Options: Sort by name, size, date, or path
- Regex Support: Use regular expressions for complex searches
- Service Health Checks: Verify Everything service status
Enhanced Research Features
- š§ Intent-Based Code Research: Analyzes specifications and finds matching implementations across GitHub
- š GitHub MCP Integration: Seamless local/remote search with repository metadata
- š SQLite Knowledge Base: Builds searchable library of code patterns over time
- š CSV Export Integration: Structured data export using ES tools
- šÆ Implementation Suggestions: AI-powered recommendations based on research findings
Spec-Driven Development
- š Specification Awareness: Understands requirements, design, and task documents
- š Traceability Analysis: Cross-references between specs and implementation
- š Progress Tracking: Monitors specification coverage and task completion
- š„ļø Terminal UI (TUI): Rich terminal interface for interactive project management
Integration & Automation
- ā” One-Click Kiro Installation: Automated setup and configuration
- š§ Comprehensive Logging: Full trace logging with structured debugging
- š Easy Integration: Simple setup with Cursor, Kiro, SpecStory, and other MCP clients
š Prerequisites
- Windows OS: Everything only runs on Windows
- Python 3.8+: Required for virtual environment management
- Python Virtual Environment: All operations must run in an activated venv
- Everything Installed: Download from voidtools.com
- Node.js 18+: Required for MCP server
- es.exe Available: Command-line interface must be accessible
Environment Setup
-
Create and activate Python virtual environment:
python -m venv everything-mcp-env everything-mcp-env\Scripts\activate -
Install Everything from voidtools.com
-
Ensure the Everything service is running
-
Verify
es.exeexists at:C:\Program Files\Everything\es.exe -
Test with:
"C:\Program Files\Everything\es.exe" test
ā ļø Important: All commands must be run within the activated virtual environment.
š ļø Installation
Option 1: One-Click Kiro Installation (Coming Soon)
# Ensure virtual environment is activated
python -m venv everything-mcp-env
everything-mcp-env\Scripts\activate
# One command installs and configures everything for Kiro
npm install -g everything-mcp-kiro
kiro-everything --setup
Option 2: From Source (Recommended)
# Create and activate virtual environment
python -m venv everything-mcp-env
everything-mcp-env\Scripts\activate
# Clone the repository
git clone https://github.com/SoMaCoSF/mcp-everything.git
cd mcp-everything
# Install dependencies
npm install
# Build the server
npm run build
# Test the installation (includes venv validation)
npm run test:kiro
Option 3: Manual Configuration
# Ensure virtual environment is activated
python -m venv everything-mcp-env
everything-mcp-env\Scripts\activate
npm install -g everything-mcp-server
š§ Usage with AI Assistants
Cursor IDE
Add to your Cursor settings.json:
{
"mcp": {
"servers": {
"everything-search": {
"command": "node",
"args": ["path/to/everything-mcp/dist/index.js"],
"env": {
"EVERYTHING_PATH": "C:\\Program Files\\Everything\\es.exe",
"TRACE_DIRECTORY": "D:\\outputs\\traces"
}
}
}
}
}
Kiro IDE
Kiro is an agentic IDE that supports MCP servers for external tool integration. To add Everything search to Kiro:
- Open Kiro IDE and navigate to your project
- Create or edit your MCP configuration following Kiro's MCP documentation
- Add the Everything MCP server to your Kiro configuration:
{
"mcpServers": {
"everything-search": {
"command": "node",
"args": ["path/to/everything-mcp/dist/index.js"],
"env": {
"EVERYTHING_PATH": "C:\\Program Files\\Everything\\es.exe",
"TRACE_DIRECTORY": "D:\\outputs\\traces"
},
"description": "Everything search integration for fast file/folder search"
}
}
}
- Restart Kiro to load the new MCP server
- Use Everything search through Kiro's agentic chat interface
Kiro-specific features:
- Specs Integration: Use Everything search to find files when planning features with Kiro's spec-driven development
- Hooks Automation: Set up automated file searches triggered by development events
- Natural Language: Ask Kiro to "find all TypeScript files modified today" and it will use Everything search
- Project Context: Kiro understands your project structure and can combine Everything search with its codebase knowledge
SpecStory
SpecStory is a documentation and specification platform designed for LLM integration. To add Everything search to SpecStory workflows:
- Set up MCP integration in your SpecStory environment
- Add the Everything MCP server to your SpecStory MCP configuration:
{
"mcpServers": {
"everything-search": {
"command": "node",
"args": ["path/to/everything-mcp/dist/index.js"],
"env": {
"EVERYTHING_PATH": "C:\\Program Files\\Everything\\es.exe",
"TRACE_DIRECTORY": "D:\\outputs\\traces"
},
"description": "Everything search for finding specification files and documentation"
}
}
}
- Restart SpecStory to load the new MCP server
- Use Everything search to find relevant specification files, documentation, and project artifacts
SpecStory-specific features:
- Specification Search: Quickly find spec files, requirements documents, and related artifacts
- Documentation Discovery: Search across all project documentation and markdown files
- Cross-Reference Lookup: Find files referenced in specifications using Everything's fast indexing
- Version Control Integration: Search for spec files across different versions and branches
- Context-Aware Documentation: Combine Everything search with SpecStory's LLM context for comprehensive documentation workflows
Example SpecStory workflows:
{
"query": "user authentication",
"docTypes": ["md", "mdx", "txt"],
"sortBy": "relevance",
"includeArchived": false
}
Use the specialized documentation search:
{
"tool": "everything_search_docs",
"query": "API specification",
"docTypes": ["md", "yaml", "json"],
"sortBy": "relevance"
}
š Available Tools
1. everything_search
Basic file and folder search with Everything syntax support.
Parameters:
query(required): Search query using Everything syntaxmaxResults(optional): Maximum results to return (default: 50)fileOnly(optional): Search files only (default: false)folderOnly(optional): Search folders only (default: false)
2. everything_search_advanced
Advanced search with comprehensive filtering and sorting options.
Parameters:
query(required): Search querymaxResults(optional): Maximum results (default: 50)sortBy(optional): Sort by 'name', 'size', 'date', or 'path'fileTypes(optional): Array of file extensions to filterincludeHidden(optional): Include hidden files/foldersregex(optional): Use regex searchcaseSensitive(optional): Case sensitive search
3. everything_check_service
Verify Everything service is running and accessible.
4. everything_search_docs
Specialized documentation and specification search optimized for SpecStory workflows.
Parameters:
query(required): Search query for documentation filesmaxResults(optional): Maximum results (default: 50)docTypes(optional): Documentation file types to search ['md', 'mdx', 'txt', 'rst', 'adoc']includeArchived(optional): Include archived/old documentation (default: false)sortBy(optional): Sort by 'relevance', 'date', 'name', or 'size'
Features:
- Smart categorization: Automatically categorizes docs as specs, requirements, designs, APIs, etc.
- Priority ranking: Relevance-based sorting puts most important docs first
- Archive filtering: Excludes deprecated/old documentation by default
- SpecStory optimization: Designed for specification and documentation workflows
5. everything_deep_research (Coming Soon)
Intent-based code research across public GitHub repositories.
Parameters:
specification(required): Path to specification document or text contentsearchDepth(optional): 'shallow', 'medium', or 'deep' research depthlanguages(optional): Preferred programming languagesmaxRepositories(optional): Maximum repositories to analyze
Features:
- Intent Analysis: Parses specifications to understand implementation goals
- Pattern Discovery: Finds code patterns that match specification requirements
- Quality Assessment: Evaluates code quality, license compatibility, and maintenance status
- Knowledge Base: Stores findings in SQLite database for future reference
6. everything_github_search (Coming Soon)
Combined local and GitHub repository search.
Parameters:
query(required): Search queryincludeLocal(optional): Include local file search (default: true)includeGitHub(optional): Include GitHub repository search (default: true)repositories(optional): Specific repositories to search
7. everything_tui_launch (Coming Soon)
Launch Terminal User Interface for interactive project management.
Features:
- Project Dashboard: Overview of specifications, tasks, and progress
- Interactive Search: Real-time search with filtering and sorting
- Research Interface: Monitor deep research progress and results
- Implementation Suggestions: Browse AI-generated recommendations
š¤ Everything Search Syntax
The server supports full Everything search syntax:
- Wildcards:
*.txt,project* - Extensions:
ext:js,ext:pdf - Size filters:
size:>1mb,size:<100kb - Date filters:
dm:today,dm:thisweek - Path filters:
path:documents,path:"c:\projects" - Boolean operators:
AND,OR,NOT - Exact phrases:
"exact phrase"
š Examples
Basic Search
{
"query": "*.py",
"maxResults": 100
}
Advanced Search
{
"query": "dm:lastweek",
"fileTypes": ["mp4", "mkv", "avi"],
"sortBy": "size"
}
Development Files
{
"query": "component",
"fileTypes": ["jsx", "tsx"],
"caseSensitive": false
}
š§ Troubleshooting
Common Issues
-
"es.exe not found"
- Verify Everything is installed
- Check path:
C:\Program Files\Everything\es.exe - Try running Everything as administrator
-
"No results returned"
- Ensure Everything database is indexed
- Check if Everything service is running
- Use
everything_check_servicetool
-
"Permission denied"
- Run Everything as administrator
- Check Windows permissions
- Verify Everything service is started
Debug Mode
The server logs all operations to the trace directory:
- Default Location:
D:\outputs\traces\everything-mcp-{timestamp} - Files: Operation logs, development diary, error traces
- Use for debugging search queries and server issues
šļø Architecture
The Enhanced Everything MCP Server transforms simple file search into an intelligent development research platform:
Current Architecture (v1.0)
- MCP Client (Cursor/Kiro/SpecStory/Claude) sends search requests
- MCP Server validates and processes requests
- es.exe executes the actual search
- Results are parsed and returned as structured JSON
- Trace System logs all operations for debugging
Enhanced Architecture (v2.0 - In Development)
Intent-based code research with GitHub discovery and pattern analysis
Terminal User Interface Preview
Interactive terminal dashboard for project management and search
Key Components
- Research Engine: Intent-based code discovery and pattern analysis
- Knowledge Base: SQLite database for accumulated research findings
- GitHub Integration: Seamless local/remote search capabilities
- TUI Controller: Rich terminal interface for interactive development
- Spec Awareness: Understanding of requirements, design, and task documents
ļæ½ļø eRoadmap
ā Phase 1: Core Search (v1.0 - Current)
- [x] Basic Everything search integration
- [x] Advanced filtering and sorting
- [x] Documentation search optimization
- [x] MCP protocol implementation
- [x] Comprehensive logging and tracing
š§ Phase 2: Enhanced Research (v2.0 - In Development)
- [ ] GitHub MCP integration
- [ ] Intent-based code research
- [ ] SQLite knowledge base
- [ ] CSV export capabilities
- [ ] Pattern recognition and analysis
š® Phase 3: Intelligence & Automation (v3.0 - Planned)
- [ ] Terminal User Interface (TUI)
- [ ] AI-powered implementation suggestions
- [ ] Automated specification analysis
- [ ] One-click Kiro installation
- [ ] Advanced voidtools integration
š Current Status
The enhanced features are currently in specification phase. See .kiro/specs/enhanced-everything-mcp/ for detailed requirements, design, and implementation plans.
š Development
# Run current version in development mode
npm run dev
# Build for production
npm run build
# Start built server
npm start
# View enhancement specifications
# Open .kiro/specs/enhanced-everything-mcp/ in Kiro IDE
File Structure
everything-mcp/
āāā src/
ā āāā index.ts # Main server implementation
āāā .kiro/specs/ # Enhancement specifications
ā āāā enhanced-everything-mcp/
ā āāā requirements.md # Detailed requirements
ā āāā design.md # Architecture design
ā āāā tasks.md # Implementation plan
āāā dist/ # Built files (generated)
āāā package.json # Dependencies and scripts
āāā tsconfig.json # TypeScript configuration
āāā architecture.svg # Architecture diagram
āāā README.md # This file
š License
MIT License - See LICENSE file for details.
š¤ Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit your changes:
git commit -m 'Add amazing feature' - Push to the branch:
git push origin feature/amazing-feature - Open a Pull Request
š Acknowledgments
- voidtools for the amazing Everything search engine
- Model Context Protocol for the MCP specification
- The Cursor team for MCP integration
- Kiro IDE for agentic development with MCP support
- SpecStory for specification and documentation workflows
Made with ā¤ļø for the Everything and AI community
Recommended Servers
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.
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.
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.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
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.
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.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.