mcp-system-monitor
If you are the rightful owner of mcp-system-monitor and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The MCP System Monitor Server is a cross-platform server designed to provide real-time system monitoring capabilities for LLMs, utilizing the Model Context Protocol (MCP).
The MCP System Monitor Server is a versatile and robust solution for real-time system monitoring across various platforms, including Windows, macOS, and Linux. It is built using FastMCP, ensuring seamless integration with Claude Desktop and other MCP-compatible clients. The server offers comprehensive monitoring features, including CPU, GPU, memory, disk, network, and process monitoring. It supports multi-vendor GPU monitoring, providing full metrics for NVIDIA GPUs and basic information for AMD, Intel, and Apple GPUs. The server's architecture is modular, with specialized collectors for each system component, ensuring efficient data collection and caching. This design minimizes system overhead and provides consistent data within specified time windows. The server is easy to install and configure, with optional dependencies for Windows-specific features. It also includes a suite of MCP tools and resources for interacting with the system monitor using natural language commands.
Features
- Real-time CPU, GPU, memory, disk, network, and process monitoring
- Multi-vendor GPU support with full metrics for NVIDIA GPUs
- Modular collector-based architecture with intelligent caching
- Seamless integration with Claude Desktop and other MCP clients
- Cross-platform support for Windows, macOS, and Linux
Tools
get_cpu_info
Get current CPU usage and statistics
get_gpu_info
Get GPU information for all detected GPUs
get_memory_info
Get RAM and swap usage
get_disk_info
Get disk usage for all mounted drives
get_system_snapshot
Get complete system state in one call
monitor_cpu_usage
Monitor CPU usage over a specified duration
get_top_processes
Get top processes by CPU or memory usage
get_network_stats
Get network interface statistics