Linux MCP Server
<!-- mcp-name: io.github.rhel-lightspeed/linux-mcp-server -->
[](https://github.com/rhel-lightspeed/linux-mcp-server/actions/workflows/ci.yml)
[](https://codecov.io/gh/rhel-lightspeed/linux-mcp-server)
[](https://pypi.org/project/linux-mcp-server)
[](https://rhel-lightspeed.github.io/linux-mcp-server/)
# 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 [documentation].
[documentation]: https://rhel-lightspeed.github.io/linux-mcp-server/
TDQS
Scored across 23 tools
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.
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.
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.
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.