System Information MCP Server

A Model Context Protocol (MCP) server that provides real-time system information and metrics. This server exposes CPU usage, memory statistics, disk information, network status, and running processes through a standardized MCP interface.

Features

🛠️ Tools Available

• get_cpu_info - Retrieve CPU usage, core counts, frequency, and load average

• get_memory_info - Get virtual and swap memory statistics

• get_disk_info - Disk usage information for all mounts or specific paths

• get_network_info - Network interface information and I/O statistics

• get_process_list - Running processes with sorting and filtering options

• get_system_uptime - System boot time and uptime information

• get_temperature_info - Temperature sensors and fan speeds (when available)

📚 Resources Available

• system://overview - Comprehensive system overview with all metrics

• system://processes - Current process list resource

⭐ Key Features

• Real-time metrics with configurable caching

• Cross-platform support (Windows, macOS, Linux)

• Security-focused with sensitive data filtering

• Performance optimized with intelligent caching

• Comprehensive error handling

• Environment variable configuration

Installation

Using uvx (Recommended)

The easiest way to install and use this MCP server is with uvx:

Then configure it in your MCP client (like Claude Desktop):

Development Installation

For local development:

1. Clone the repository:

   git clone <repository-url> cd mcp-system-info

2. Install dependencies:

   uv sync

3. Run the server:

   uv run mcp-system-info

Development

Project Structure

Development Setup

1. Install development dependencies:

   uv sync --dev

2. Run tests:

   uv run pytest

3. Run tests with coverage:

   uv run pytest --cov=system_info_mcp --cov-report=term-missing

4. Format code:

   uv run black src/ tests/

5. Lint code:

   uv run ruff check src/ tests/

6. Type checking:

   uv run mypy src/

Building and Publishing

Build the Package

This creates distribution files in the dist/ directory:

• mcp_system_info-*.whl (wheel file)

• mcp_system_info-*.tar.gz (source distribution)

Local Testing with uvx

Test the package locally before publishing:

Publishing to PyPI

Note: You'll need to:

1. Create a PyPI account at https://pypi.org

2. Generate an API token in your account settings

3. Configure uv with your credentials or use environment variables

Environment Configuration

The server supports configuration through environment variables:

Core Settings

• SYSINFO_CACHE_TTL - Cache time-to-live in seconds (default: 5)

• SYSINFO_MAX_PROCESSES - Maximum processes to return (default: 100)

• SYSINFO_ENABLE_TEMP - Enable temperature sensors (default: true)

• SYSINFO_LOG_LEVEL - Logging level (default: INFO)

Transport Configuration

• SYSINFO_TRANSPORT - Transport protocol: stdio, sse, or streamable-http (default: stdio)

• SYSINFO_HOST - Host to bind to for HTTP transports (default: localhost)

• SYSINFO_PORT - Port to bind to for HTTP transports (default: 8001)

• SYSINFO_MOUNT_PATH - Mount path for SSE transport (default: /mcp)

Transport Modes

1. STDIO (Default)

2. SSE (Server-Sent Events)

3. Streamable HTTP

Complete Example:

Usage Examples

Tool Usage

Get CPU Information

Get Process List

Get Disk Information

Resource Usage

System Overview

Process List Resource

Integration with Claude Desktop

Adding to Claude Desktop

1. Locate your Claude Desktop config file:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

   • Windows: %APPDATA%\Claude\claude_desktop_config.json

2. Add the MCP server configuration:

Using uvx (Recommended)

For Local Development

For HTTP Transport (SSE)

3. Restart Claude Desktop to load the new server.

Using with Claude

Once configured, you can ask Claude to:

• "What's my current CPU usage?"

• "Show me the top 10 processes using the most memory"

• "How much disk space is available?"

• "What's my system uptime?"

• "Give me a complete system overview"

Testing

Running Tests

Test Structure

• tests/test_config.py - Configuration validation tests

• tests/test_tools.py - Tool implementation tests

• tests/test_resources.py - Resource handler tests

• tests/test_utils.py - Utility function tests

All tests use mocked dependencies for consistent, fast execution across different environments.

Performance Considerations

• Caching: Intelligent caching reduces system calls and improves response times

• Configurable intervals: Adjust cache TTL based on your needs

• Lazy loading: Temperature sensors and other optional features load only when needed

• Async support: Built on FastMCP for efficient async operations

Security Features

• Read-only operations: No system modification capabilities

• Sensitive data filtering: Command-line arguments are filtered for passwords, tokens, etc.

• Input validation: All parameters are validated before processing

• Error isolation: Failures in one tool don't affect others

Platform Support

• macOS - Full support including temperature sensors on supported hardware

• Linux - Full support with hardware-dependent sensor availability

• Windows - Full support with platform-specific optimizations

Troubleshooting

Common Issues

1. Permission errors: Some system information may require elevated privileges

2. Missing sensors: Temperature/fan data availability varies by hardware

3. Performance impact: Reduce cache TTL or limit process counts for better performance

Debug Mode

Enable debug logging for troubleshooting:

Verifying Installation

Test that tools work correctly:

Contributing

1. Fork the repository

2. Create a feature branch

3. Make your changes with tests

4. Run the full test suite

5. Submit a pull request

Code Standards

• Follow PEP 8 style guidelines

• Add type hints to all functions

• Write tests for new functionality

• Update documentation as needed

License

[Add your license information here]

Support

[Add support information here]