mcp-ssh-sre

docker run -d \ -p 3000:3000 \ -e SSH_HOST=server.local \ -e SSH_USERNAME=mcp-readonly \ -e SSH_KEY_PATH=/keys/id_ed25519 \ -v ~/.ssh/id_ed25519_mcp:/keys/id_ed25519:ro \ ghcr.io/jeprecated/mcp-ssh-sre:latest

{ "mcpServers": { "ssh-sre": { "url": "http://your-server:3000/mcp" } } }

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.

- "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 runningdocker logs,smartctl,docker inspect, and correlating outputs, your AI assistant does it in seconds.

The server auto-detects your platform at startup and loads appropriate tools.

- 12 tool modules with 79+ actionsfor 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

SSH provides unrestricted access to system tools without API rate limiting.

src/ ├── platforms/ │ ├── linux/ # Generic Linux (baseline) │ └── unraid/ # Unraid-specific tools ├── tools/core/ # 10 core tool modules ├── index.ts # Stdio transport └── http-server.ts # HTTP transport

- Createsrc/platforms/<platform>/index.tsimplementingPlatform
- Add detection logic
- Create platform-specific tool modules
- Register insrc/platforms/index.ts

npm run dev # Development with auto-reload npm test # Run tests npm run build # Build for production

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

MCP server for Claude Code, Cursor, Windsurf, and other MCP clients. Connect AI assistants to PostgreSQL, filesystems, GitHub, Slack, SSH etc

Connect to, configure, and monitor Cisco network devices like routers and switches via SSH.

Production-ready MCP server for AI-driven console automation and monitoring. 40+ tools for session management, SSH, testing, and background jobs.

Hetzner Cloud MCP Server — (Cloud API + SSH)

Hetzner Cloud MCP Server — two management layers (Cloud API + SSH) with 60 tools. Manage server power, snapshots, firewalls, DNS, plus SSH into servers for service control, log viewing, Nginx management, MySQL queries, and system monitoring. Self-hosted PHP, MIT licensed.

Provides remote machine control capabilities, eliminating SSH overhead for token-efficient system operations.

Orchestrates remote server tasks via SSH and SFTP with a persistent queue. Ideal for DevOps and AI agents.

Securely execute remote commands and perform file operations over SSH, with support for both password and key-based authentication.

Native macOS SSH client with 26 local MCP tools for visible terminals, SFTP, SSH keys, connections, and read-only observability.

MCP server that exposes an SSH server list from a TOML config file