io.github.rhel-lightspeed/linux-mcp-server MCP Server
io.github.rhel-lightspeed/linux-mcp-server
Read-only Linux system diagnostics and troubleshooting via MCP with remote SSH support
What is the io.github.rhel-lightspeed/linux-mcp-server MCP server?
The Linux MCP Server is a Model Context Protocol server for read-only Linux system administration, diagnostics, and troubleshooting on RHEL-based systems. It enables safe remote system inspection via SSH with multi-host management capabilities and comprehensive diagnostic tools.
This server provides AI agents with safe, read-only access to Linux system information and diagnostics. It's designed for RHEL systems and supports remote SSH execution, making it useful for troubleshooting, monitoring, and analyzing system state across multiple hosts without risk of accidental modifications.
How to install io.github.rhel-lightspeed/linux-mcp-server
Copy-paste configuration for popular MCP clients.
LINUX_MCP_USERDefault username for SSH connections
LINUX_MCP_SSH_KEY_PATHPath to SSH private key
LINUX_MCP_KEY_PASSPHRASEsecretPassphrase for encrypted SSH key
LINUX_MCP_SEARCH_FOR_SSH_KEYAuto-discover keys in `~/.ssh`
LINUX_MCP_COMMAND_TIMEOUTSSH command timeout in seconds (default: 30)
LINUX_MCP_VERIFY_HOST_KEYSVerify remote host identity via known_hosts
LINUX_MCP_KNOWN_HOSTS_PATHCustom path to known_hosts file
LINUX_MCP_ALLOWED_LOG_PATHSComma-separated allowlist of log files
LINUX_MCP_LOG_DIRServer log directory
LINUX_MCP_LOG_LEVELLog verbosity (DEBUG, INFO, WARNING)
LINUX_MCP_LOG_RETENTION_DAYSDays to keep log files
Tools & capabilities
Tools this server exposes to the agent.
System Information— Retrieve system details and configuration informationService Management— Query systemd services and their statusProcess Inspection— Examine running processes and their detailsLog Access— Read system logs with configurable access controlNetwork Diagnostics— Inspect network configuration and connectivityStorage Analysis— Query disk usage and storage informationRemote SSH Execution— Execute read-only commands on remote systems via SSH with key-based authentication
Use cases
- Diagnose system issues and troubleshoot problems on RHEL servers
- Monitor service status and process behavior across multiple hosts
- Analyze logs and system events for root cause analysis
- Inspect network configuration and connectivity issues
- Check disk usage and storage capacity on remote systems
io.github.rhel-lightspeed/linux-mcp-server MCP server FAQ
It's an MCP server that gives AI agents read-only access to Linux system diagnostics and administration tools, optimized for RHEL-based systems with remote SSH support.
Yes, all operations are strictly read-only, so there's no risk of accidental system modifications.
Install via pip: `pip install linux-mcp-server`. See the official installation guide for uv and container-based deployments.
Yes, it supports remote SSH execution with key-based authentication and can manage multiple hosts in the same session.
It's optimized for Red Hat Enterprise Linux (RHEL) systems and uses systemd for service management.
Yes, log file access is configurable via environment variables for security and privacy control.
README (reference)
Source of truth, from the repository.
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
Installation and Usage
For detailed instructions on setting up and using the Linux MCP Server, please refer to our official documentation:
- Installation Guide: Detailed steps for
pip,uv, and container-based deployments. - Usage Guide: Information on running the server, configuring LLM clients, and troubleshooting.
- Cheatsheet: A reference for what prompts to use to invoke various tools.
Related MCP servers
Call Google's Antigravity CLI (agy) headlessly from non-TTY contexts (subprocess, MCP, CI).
AI cycling coach — training plans and beginner guidance via the Etapa API.
View repository →
RuleDrift
Test whether AI agents retain critical instructions as conversations grow.

Volante
Routes to the best predicted fit from configured metadata/evidence after hard-capability filtering.

Local document search over your folders: hybrid keyword+semantic, fully offline, read-only

io.github.ricardo-hdrn/mcp-await
Condition watcher for AI assistants — wait for ports, files, URLs, processes, and more
