home / mcp / system information mcp server

System Information MCP Server

System Information MCP Server - Real-time system metrics through Model Context Protocol

Installation
Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "dknell-mcp-system-info": {
      "url": "http://localhost:8001/mcp",
      "headers": {
        "SYSINFO_CACHE_TTL": "10",
        "SYSINFO_LOG_LEVEL": "DEBUG",
        "SYSINFO_ENABLE_TEMP": "true",
        "SYSINFO_MAX_PROCESSES": "100"
      }
    }
  }
}

You get a real-time MCP server that exposes key system metrics such as CPU, memory, disk usage, network status, processes, uptime, and temperatures. It is designed for fast, cached access to system data across platforms, with secure defaults and easy integration into MCP clients.

How to use

Connect to the System Information MCP server from your MCP client to start querying live system data. You can use the server to pull a comprehensive overview of the current system state, or request focused metrics like the top processes by memory usage, disk space, or uptime.

How to install

Prerequisites: you need Python installed on your machine and the MCP runtime tools available (uv or uvx). Follow the steps below to get the server up and running.

1) Install the MCP server using the recommended installer.

2) Start the server in stdio mode for local development. This uses the container’s standard input/output interfaces.

uv run mcp-system-info

Configuration and runtime options

Configure caching, limits, and transport to suit your environment. The server supports a set of environment variables to control behavior, including cache TTL, maximum processes returned, temperature Sensor enablement, and logging level.

Transport options let you expose data via stdio (default), Server-Sent Events (SSE) over HTTP, or a streamable HTTP interface. You can choose the transport that fits your client setup and networkrequirements.

Example environment variables include cache TTL, max processes, temperature enablement, and log level. You can adjust these at start time to tune performance and verbosity.

Connecting from Claude Desktop (example client)

To connect from an MCP client like Claude Desktop, configure the MCP server entry in your client with the appropriate command and environment variables. The following shows a typical setup using the recommended installer and transport options.

{
  "mcpServers": {
    "system_info": {
      "command": "uvx",
      "args": ["mcp-system-info"],
      "env": {
        "SYSINFO_CACHE_TTL": "10",
        "SYSINFO_LOG_LEVEL": "INFO"
      }
    }
  }
}

Environment variables you can set

Core settings control caching, processes, temperature sensors, and logging. You can customize these when starting the server.

Example core settings to consider:

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)

Testing and development

Run the full test suite during development and verify the server behaves as expected. Use verbose output if you need details about failures.

uv run pytest

Notes on security and reliability

The server performs read-only operations for safety. Sensitive data is filtered and parameters are validated to prevent misuse. Failures in one tool do not affect others, and the system uses caching to optimize performance without compromising up-to-date data.

Troubleshooting

If you run into permission or sensor issues, adjust your environment accordingly. Temperature data may depend on hardware capabilities and drivers.

Enable debug logging to diagnose problems during startup.

SYSINFO_LOG_LEVEL=DEBUG uv run mcp-system-info

What you can query

The server exposes tools to obtain comprehensive system information such as CPU, memory, disk, network, process lists, uptime, and temperature data. Use these endpoints to build dashboards, automate monitoring, or analyze system health in real time.

A note on availability and platform support

The MCP System Information server provides cross-platform support, with configurations designed to work on Windows, macOS, and Linux. Temperature sensors and hardware availability may vary by platform and hardware.

Available tools

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)