MCP System Monitor

Provides real-time system metrics via MCP, exposing CPU, memory, disk, network, host, and process data for MCP-compatible clients.

other

74

GitHub Stars

other

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "seekrays-mcp-monitor": {
      "command": "./mcp-monitor",
      "args": []
    }
  }
}

The MCP System Monitor exposes real-time system metrics through an MCP-compatible interface, enabling you to ask an autonomous agent about CPU, memory, disk, network, host, and process information and receive structured data in return.

How to use

You run the local MCP System Monitor binary and connect an MCP-capable client to query live system metrics. Request data such as current CPU usage, memory usage, disk statistics, network activity, host information, or detailed process lists. The server responds with structured data that you can use to monitor system health, build dashboards, or trigger alerts.

Typical usage patterns include asking for overall health snapshots, querying per-process details for a specific PID, or listing top CPU- or memory-consuming processes. You can also query disk usage for a particular path, or inspect network interfaces and traffic. Each tool is designed to provide a focused view of a specific subsystem, and you can combine multiple queries to build a comprehensive monitoring view.

How to install

Prerequisites: you need a buildable environment for the MCP project. Ensure you have a working shell and the necessary build tools installed on your system.

Step-by-step commands to install and run the MCP System Monitor locally:

Install and run the MCP System Monitor

git clone https://github.com/seekrays/mcp-monitor.git
cd mcp-monitor
make build
./mcp-monitor

Usage after start

When the server starts, it runs in stdio mode and is ready to communicate with an MCP-compatible client. Use your MCP client to send requests for CPU, memory, disk, network, host, and process information, and receive structured responses.

Notes

If you need to stop the server, send an interrupt signal (Ctrl+C) to the running process. The monitor exposes a range of information that helps you diagnose performance bottlenecks and understand system behavior in real time.

Available tools

get_cpu_info

Get CPU information and usage, with an option to return data per CPU core.

get_memory_info

Retrieve current virtual and swap memory usage.

get_disk_info

Query disk usage data, including partitions and I/O statistics, for a specified path.

get_network_info

Fetch network interface details, connections, and traffic statistics.

get_host_info

Get host system information such as uptime, boot time, and logged-in users.

get_process_info

Obtain a list of processes with options to filter by PID, limit results, and sort by various fields (cpu, memory, pid, name).