Skip to main content
Glama
Sign In
Linux MCP Server

Linux MCP Server

by rhel-lightspeed
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

CI Coverage PyPI Docs

Linux MCP Server

A Model Context Protocol (MCP) server for read-only Linux system administration, diagnostics, and troubleshooting on RHEL-based systems.

Features

  • Read-Only Operations: All tools are strictly read-only for safe diagnostics

  • Remote SSH Execution: Execute commands on remote systems via SSH with key-based authentication

  • Multi-Host Management: Connect to different remote hosts in the same session

  • Comprehensive Diagnostics: System info, services, processes, logs, network, and storage

  • Configurable Log Access: Control which log files can be accessed via environment variables

  • RHEL/systemd Focused: Optimized for Red Hat Enterprise Linux systems

Related MCP server: Linux Diagnostics MCP Server

Installation and Usage

For detailed instructions on setting up and using the Linux MCP Server, please refer to our documentation.

Available Tools

23 tools
get_cpu_informationGet CPU informationC
Read-only

Get CPU information.

Inputs: host (required). Returns: Parsed CPU information.

get_disk_usageGet disk usageA
Read-only

Get detailed disk space information including size, mount points, and utilization.

Inputs: host (required). Returns: Disk usage information from findmnt --df --json.

get_hardware_informationGet hardware informationB
Read-only

Get hardware information such as CPU details, PCI devices, USB devices, and hardware information from DMI.

Inputs: host (required). Returns: object

get_journal_logsGet journal logsC
Read-only

Get systemd journal logs.

Inputs: host (required), unit, since, priority, +3 more. Returns: path, unit, entries, lines_count

get_listening_portsGet listening portsB
Read-only

Get details on listening port, protocols, and services.

Inputs: host (required). Returns: result

get_memory_informationGet memory informationB
Read-only

Get detailed memory including physical and swap.

Inputs: host (required). Returns: Combined memory and swap information.

get_network_connectionsGet network connectionsB
Read-only

Get detailed information about active network connections.

Inputs: host (required). Returns: result

get_network_interfacesGet network interfacesB
Read-only

Get detailed information about network interfaces including address and traffic statistics.

Inputs: host (required). Returns: result

get_process_infoProcess detailsB
Read-only

Get information about a specific process.

Inputs: pid (required), host (required). Returns: result

get_service_logsGet service logsB
Read-only

Get recent logs for a specific systemd service.

Inputs: host (required), service_name (required), lines. Returns: result

get_service_statusGet service statusA
Read-only

Get detailed status of a specific systemd service.

Inputs: host (required), service_name (required). Returns: result

get_system_informationGet system informationA
Read-only

Get basic system information, including operating system, distribution, kernel version, uptime, last boot time, PCP installation and service status, and historical PCP time ranges.

Inputs: host (required). Returns: Parsed system information.

list_block_devicesList block devicesC
Read-only

List block devices on the system

Inputs: host (required). Returns: total, blockdevices

list_directoriesList directoriesC
Read-only

List directories under a specified path with various sorting options.

Inputs: host (required), path (required), sort, top_n, +1 more. Returns: nodes, total

list_filesList filesC
Read-only

List files under a specified path with various sorting options.

Inputs: host (required), path (required), sort, top_n, +1 more. Returns: nodes, total

list_processesList processesC
Read-only

List running processes

Inputs: host (required). Returns: result

list_servicesList servicesA
Read-only

List all systemd services.

Inputs: host (required). Returns: result

pcp_guideRead the PCP metrics guideA
Read-only

Returns the PCP metrics guide: a catalog of the metric names recorded on a typical Linux system, and how to read the values the other PCP tools return. Read it before investigating performance with PCP, and take metric names from it rather than from memory.

Inputs: host (required). Returns: result

pcp_list_metricsList available PCP metricsA
Read-only

Browses the PCP metric namespace. Lists the metrics under 'prefix' with their descriptions, collapsing any large sub-namespace to one line giving its name and how many metrics it holds; call again with that name as the prefix to see inside it. Only metrics this system's pmlogger records are listed, so everything listed can be passed to pcp_query_metrics. The pcp_guide tool already names the commonly needed metrics, so reach for this when you need a subsystem the guide does not cover. Use only if get_system_information() indicates PCP is available.

Inputs: host (required), prefix. Returns: result

pcp_performance_summaryGet PCP performance summaryA
Read-only

Produces a condensed snapshot of CPU, memory, disk, network, and process information using pcp xsos. Can summarize the live system or a particular time in the past. Use only if get_system_information() indicates PCP is available.

Inputs: host (required), timestamp. Returns: result

pcp_query_metricsQuery PCP historical metricsA
Read-only

Retrieves historical metric data from PCP archives as JSON samples. When start_time, end_time, or interval is omitted, reasonable defaults are chosen, targeting one hour or about 20 samples. Call pcp_guide first for the metric catalog and how to read the values; do not guess metric names. Use only if get_system_information() indicates PCP is available.

Inputs: host (required), metrics (required), end_time, interval, +1 more. Returns: result

read_fileRead fileB
Read-only

Read the contents of a text file up to a safe size limit.

Inputs: host (required), path (required). Returns: result

read_log_fileRead log fileC
Read-only

Read a specific log file.

Inputs: host (required), log_path (required), last_lines, first_lines. Returns: path, unit, entries, lines_count

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.2/5.0

    Scored across 23 tools

    Disambiguation4/5

    Most tools have clearly distinct targets (network, disk, processes, services, files, PCP metrics). Minor overlap exists: get_hardware_information explicitly includes CPU details while get_cpu_information is separate, and get_service_logs / get_journal_logs / read_log_file all retrieve logs, though descriptions differentiate the sources.

    Naming Consistency5/5

    All tools follow a strict snake_case verb_noun pattern (get_*, list_*, read_*), with a consistent pcp_* prefix grouping the PCP subsystem tools. No mixing of conventions or casing.

    Tool Count4/5

    23 tools is on the heavier side but the domain (comprehensive Linux system diagnostics) legitimately spans many subsystems. Nearly every tool earns its place, though a few informational getters (CPU, memory, hardware, system) could plausibly be consolidated.

    Completeness4/5

    Broad read-oriented coverage across CPU, memory, disk, network, processes, services, logs, files, and PCP performance with sensible PCP gating. Gaps are limited to write/action operations (e.g. restart service, kill process, file search), which is acceptable if the server is intentionally read-only.

    Maintenance

    ActivityActive
    ResponsivenessMixed handling

    Resources

    Related MCP Connectors

    Related MCP Servers

    • Linux MCP Server

      narmaku
      A
      license
      A
      quality
      D
      maintenance
      Enables read-only Linux system diagnostics and troubleshooting on local and remote RHEL-based systems via SSH, including services, processes, logs, network, and storage analysis.
      20
      MIT

    • Linux Diagnostics MCP Server

      alonf
      A
      license
      Not graded
      quality
      D
      maintenance
      This MCP server provides read-only Linux system diagnostics tools for inspecting system information, processes, and log snapshots. It enables AI models to analyze Linux system health, troubleshoot issues, and review security through workflow prompts and HTTP transport with API key authentication.
      MIT

    • mcp-ssh

      zhouxiangjing
      A
      license
      A
      quality
      D
      maintenance
      MCP server for remote Linux/Unix server management via SSH, enabling command execution, system monitoring, file operations, and diagnostics through natural language.
      34
      1
      MIT

    • ssh-remote-mcp

      yongxiaodong
      A
      license
      Not graded
      quality
      D
      maintenance
      A secure SSH-based MCP server for diagnosing remote servers. It allows AI agents to execute read-only commands and read files automatically, while requiring user confirmation for write operations.
      MIT

    Appeared in Searches