Skip to main content
Glama

πŸ–₯️ Windows System MCP

NPM Version NPM Downloads License TypeScript Node.js

A comprehensive Model Context Protocol (MCP) server that provides AI models with powerful Windows system management capabilities. This MCP enables AI assistants to interact with Windows systems through a secure, well-structured interface.

✨ Features

πŸ“ File System Management

  • Directory Browsing: Navigate and explore directory structures

  • File Operations: Read files, get file information, and search for files

  • Disk Analysis: Monitor disk usage and find large files

  • Advanced Search: Pattern-based file searching with recursive options

βš™οΈ Process Management

  • Process Monitoring: List and monitor running processes

  • Resource Tracking: Track CPU and memory usage by process

  • Process Control: Start, stop, and manage processes

  • Process Tree: Visualize parent-child process relationships

πŸ”§ System Information

  • Hardware Details: CPU, memory, disk, and network adapter information

  • OS Information: Windows version, updates, and system configuration

  • Environment: Environment variables and system paths

  • User Management: User accounts and current user information

πŸ“‹ Registry Operations

  • Registry Reading: Access Windows registry keys and values

  • System Configuration: Retrieve system settings from registry

  • Startup Programs: List programs that start with Windows

  • Installed Software: Enumerate installed applications

πŸ› οΈ Service Management

  • Service Control: Start, stop, and restart Windows services

  • Service Monitoring: Monitor service status and dependencies

  • Startup Services: Manage services that start automatically

  • Service Search: Find services by name or description

🌐 Network Operations

  • Network Diagnostics: Ping, traceroute, and connectivity testing

  • Port Scanning: Check open ports and network connections

  • Network Configuration: View adapters, IP configuration, and routing

  • WiFi Management: List and manage WiFi profiles

πŸ“Š Performance Monitoring

  • Real-time Metrics: CPU, memory, disk, and network performance

  • Resource Analysis: Identify top resource-consuming processes

  • Performance Counters: Access Windows performance counters

  • System Health: Monitor overall system performance

Related MCP server: PowerShell MCP Server

πŸ“₯ Installation

# Global installation (recommended)
npm install -g windows-system-mcp

# Or use directly with npx
npx windows-system-mcp

πŸš€ Quick Start

Prerequisites

  • Windows 10/11

  • Node.js 18+

  • PowerShell 5.1+

Installation Options

npm install -g windows-system-mcp

Option 2: Build from Source

  1. Clone the repository:

    git clone https://github.com/guangxiangdebizi/windows-system-mcp.git
    cd windows-system-mcp
  2. Install dependencies:

    npm install
  3. Build the project:

    npm run build

Local Development (Stdio)

If installed globally:

windows-system-mcp

If built from source:

npm start

Development

For development with auto-rebuild:

npm run dev

SSE Deployment (Supergateway)

If installed globally:

npx supergateway --stdio "windows-system-mcp" --port 3100

If built from source:

npm run sse

This will start the server on http://localhost:3100/sse

πŸ”§ Configuration

Claude Desktop Integration

Stdio Configuration

If installed globally:

{
  "mcpServers": {
    "windows-system-mcp": {
      "command": "windows-system-mcp"
    }
  }
}

If built from source:

{
  "mcpServers": {
    "windows-system-mcp": {
      "command": "node",
      "args": ["path/to/windows-system-mcp/build/index.js"]
    }
  }
}

SSE Configuration

{
  "mcpServers": {
    "windows-system-mcp": {
      "type": "sse",
      "url": "http://localhost:3100/sse",
      "timeout": 600
    }
  }
}

Note: For SSE mode, start the server first using the commands shown in the deployment section above.

πŸ“– Usage Examples

File System Operations

// List directory contents
{
  "action": "list_directory",
  "path": "C:\\Users",
  "recursive": true,
  "max_depth": 2
}

// Search for files
{
  "action": "search_files",
  "pattern": "*.log",
  "path": "C:\\Windows\\Logs",
  "recursive": true
}

// Find large files
{
  "action": "find_large_files",
  "path": "C:\\",
  "size_threshold": 500
}

Process Management

// List running processes
{
  "action": "list_processes",
  "sort_by": "cpu",
  "limit": 20
}

// Get process details
{
  "action": "get_process_details",
  "process_name": "chrome"
}

// Kill a process
{
  "action": "kill_process",
  "process_id": 1234
}

System Information

// Get system overview
{
  "action": "get_system_overview"
}

// Get hardware information
{
  "action": "get_hardware_info",
  "category": "cpu"
}

// Get environment variables
{
  "action": "get_environment_vars",
  "filter": "PATH"
}

Network Operations

// Ping a host
{
  "action": "ping_host",
  "host": "google.com",
  "count": 4
}

// Scan ports
{
  "action": "scan_open_ports",
  "host": "localhost",
  "port_range": "80,443,3000-3010"
}

// Get network adapters
{
  "action": "get_network_adapters"
}

πŸ›‘οΈ Security Considerations

  • Principle of Least Privilege: Run with minimal required permissions

  • Input Validation: All inputs are validated and sanitized

  • Safe Operations: Read-only operations are prioritized

  • Error Handling: Comprehensive error handling prevents system exposure

  • Audit Trail: All operations can be logged for security auditing

🀝 Contributing

We welcome contributions! Please see our Contributing Guidelines for details.

Development Setup

  1. Fork the repository

  2. Create a feature branch: git checkout -b feature/amazing-feature

  3. Make your changes

  4. Add tests if applicable

  5. Commit your changes: git commit -m 'Add amazing feature'

  6. Push to the branch: git push origin feature/amazing-feature

  7. Open a Pull Request

πŸ“„ License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

πŸ‘¨β€πŸ’» Author

Xingyu Chen

πŸ™ Acknowledgments

  • Model Context Protocol for the excellent MCP framework

  • The Windows PowerShell team for providing powerful system management capabilities

  • The TypeScript and Node.js communities for excellent tooling

πŸ“Š Project Stats

  • NPM Package: Available as windows-system-mcp

  • Language: TypeScript

  • Runtime: Node.js

  • Platform: Windows

  • License: Apache 2.0

  • MCP Version: 0.6.0


Available Tools

7 tools
filesystemC

Comprehensive file system operations including directory browsing, file reading, searching, and basic file operations

Inputs: action (required), path, pattern, recursive, +2 more.

networkC

Network information and diagnostics including network adapters, connections, ports, routing, and network testing

Inputs: action (required), host, port, port_range, +3 more.

performanceC

System performance monitoring including CPU usage, memory usage, disk I/O, network I/O, and system performance counters

Inputs: action (required), duration, interval, process_count, +1 more.

process_managerC

Comprehensive process management including listing processes, getting process details, killing processes, and monitoring resource usage

Inputs: action (required), process_id, process_name, sort_by, +2 more.

registryC

Windows Registry operations including reading registry keys, values, and searching registry entries

Inputs: action (required), key_path, value_name, search_term, +2 more.

service_managerC

Windows service management including listing services, getting service details, starting/stopping services, and monitoring service status

Inputs: action (required), service_name, status_filter, startup_type_filter, +2 more.

system_infoC

Comprehensive system information including hardware details, OS info, environment variables, and system configuration

Inputs: action (required), category, filter.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct domain and purpose: filesystem handles files, network manages network operations, performance monitors system metrics, process_manager controls processes, registry accesses the Windows Registry, service_manager manages services, and system_info provides system details. There is no overlap or ambiguity between these tools.

    Naming Consistency5/5

    All tool names follow a consistent snake_case pattern with clear, descriptive nouns (e.g., filesystem, network, performance). There are no deviations in naming style, making the set predictable and easy to understand.

    Tool Count5/5

    With 7 tools, this server is well-scoped for Windows system management. Each tool covers a distinct aspect of the system (e.g., files, network, processes), and the count is neither too thin nor too heavy, fitting the domain appropriately.

    Completeness5/5

    The tool set provides comprehensive coverage for Windows system management, including file operations, network diagnostics, performance monitoring, process control, registry access, service management, and system information. There are no obvious gaps, and it supports full lifecycle operations for each domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      F
      maintenance
      A secure Model Context Protocol server that allows AI models to safely interact with Windows command-line functionality, enabling controlled execution of system commands, project creation, and system information retrieval.
      8
      10
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      A comprehensive Model Context Protocol server that provides over 50 file and system management tools for AI models, including navigation, file operations, search, compression, and system information capabilities.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that gives any AI full control over a Windows PC, enabling application control, mouse/keyboard automation, screen capture, browser automation, and more.
      48 PyPI
      6
      MIT