Side-by-side comparison of two Model Context Protocol servers — install paths, tools, quality signals, and directory engagement so you can pick the right one for Claude, Cursor, and other MCP clients.
Terminal MCP server for AI coding agents with persistent PTY sessions, ring-buffer incremental reads, headless xterm screen capture, multi-agent orchestration, and a real-time web dashboard.
Safe, read-only SSH diagnostics for Linux/Docker servers: a fixed 38-command whitelist (no arbitrary execution), secret redaction, per-command timeouts. Collects evidence; your model does the reasoning. npx @rootpilot/mcp-ssh-diagnose