Provides management and monitoring for Docker containers, including access to logs, performance statistics, environment configurations, and network topology.
Enables comprehensive read-only monitoring of Linux servers, covering process tracking, disk I/O, network connections, system logs, and security auditing.
Assists in debugging and monitoring NGINX instances through network connectivity checks and log analysis.
Supports health monitoring and troubleshooting for Plex Media Server instances, including container status and crash analysis.
Provides server monitoring tools compatible with Proxmox environments for system diagnostics and VM management.
Enables core system diagnostic and monitoring tools on TrueNAS storage platforms.
Offers specialized tools for Unraid systems, including storage array health monitoring, parity checks, SMART disk data, and mover log analysis.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP SSH SREAnalyze my system logs and tell me why the database container is failing."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP SSH SRE
An MCP server providing read-only server monitoring tools to AI assistants. Runs predefined diagnostic commands over SSH and passes only the results to the LLM - your server credentials and shell are never exposed.
Quick Start (Docker)
Pre-built images available on GitHub Container Registry.
Then add to your MCP client:
See DEPLOYMENT.md for Docker Compose, local installation, authentication setup, and security configuration.
Why Use This?
Managing a Linux server involves SSH-ing in, running commands, correlating logs, and interpreting metrics. This MCP server lets AI assistants do that work using natural language.
Ask questions like:
"Why is my Plex container crashing?"
"Is my array healthy and are there any drives showing signs of failure?"
"Which containers are consuming the most resources?"
"Help me debug network connectivity between my nginx and database containers"
Instead of manually running docker logs, smartctl, docker inspect, and correlating outputs, your AI assistant does it in seconds.
Supported Platforms
Platform | Status | Tools |
Unraid | Full support | 12 modules (10 core + 2 Unraid-specific) |
Generic Linux | Full support | 10 core modules |
TrueNAS | Untested (PRs welcome) | Core tools should work |
Proxmox | Untested (PRs welcome) | Core tools should work |
The server auto-detects your platform at startup and loads appropriate tools.
Features
12 tool modules with 79+ actions for comprehensive server management
Dual transport - Stdio (local) or HTTP/SSE (network-accessible)
Read-only by design - Zero risk of accidental modifications
Docker management - Logs, stats, environment, ports, network topology
Storage & array - Parity checks, SMART data, temperatures, mover logs (Unraid)
Health diagnostics - Aggregated status with automatic issue detection
System monitoring - Processes, disk I/O, network connections
Log analysis - Search across containers and system logs
VM management - List, inspect, VNC details, libvirt logs
Security auditing - Port scanning, login monitoring, permission audits
Why SSH Instead of Platform APIs?
Feature | APIs | SSH |
Docker container logs | ❌ | ✅ |
SMART disk health data | ❌ | ✅ |
Real-time CPU/load averages | ❌ | ✅ |
Network bandwidth monitoring | ❌ | ✅ |
Process monitoring (ps/top) | ❌ | ✅ |
Log file analysis | ❌ | ✅ |
SSH provides unrestricted access to system tools without API rate limiting.
Architecture
Adding New Platforms
Create
src/platforms/<platform>/index.tsimplementingPlatformAdd detection logic
Create platform-specific tool modules
Register in
src/platforms/index.ts
Development
License
ISC
Support
For issues and questions, open an issue on the GitHub repository.