System Monitor

Provides system monitoring and management capabilities, exposing OS, hardware, resource usage, and process information for Claude CLI.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 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": {
    "praveert-cord": {
      "command": "/usr/bin/python3",
      "args": [
        "/path/to/system-monitor-mcp/server_standalone.py"
      ]
    }
  }
}

You can run a self-contained MCP server that exposes system monitoring and management capabilities. It lets you query OS and hardware details, watch resource usage, and manage processes from an MCP client like Claude CLI, giving you a centralized way to observe and control a host machine.

How to use

You interact with the System Monitor MCP Server through an MCP client. After you install and register the server, you can ask it for real-time system information, monitor CPU, memory, disk, and network usage, list and inspect processes, and terminate processes when needed. Use natural language prompts to request status, performance metrics, or specific process details.

How to install

Prerequisites: Python 3.7 or later and the psutil library. You will also need access to a command line where you can run Python and install dependencies.

Step 1: Obtain the server files by cloning or downloading the project directory.

Step 2: Install dependencies with Python’s package manager.

Step 3: Add the MCP server to your Claude CLI setup using one of the local runtime options shown.

cd system-monitor-mcp

pip install -r requirements.txt

# Add as a local MCP server (use server_standalone.py)
claude mcp add system-monitor python /path/to/system-monitor-mcp/server_standalone.py

# Or with a specific Python interpreter
claude mcp add system-monitor /usr/bin/python3 /path/to/system-monitor-mcp/server_standalone.py

Additional setup and notes

If you prefer using a specific Python interpreter, you can point to it when registering the MCP server. The essential idea is to run the standalone server script via your chosen Python executable.

Available tools

get_system_info

Retrieve OS and hardware information including OS details, CPU count, architecture, and boot time.

get_cpu_usage

Obtain real-time CPU usage statistics with optional interval and per-core breakdown.

get_memory_info

Report RAM and swap usage to monitor available memory and swap utilization.

get_disk_usage

Provide disk space information for all mounted partitions.

get_network_stats

Return statistics for network interfaces and connection counts.

list_processes

List running processes, with sorting options by CPU or memory usage and optional limit.

get_process_info

Fetch detailed information about a specific process by PID.

kill_process

Terminate a process by PID, with an optional force kill.