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.
Stateful, structured, auditable shell sessions for AI agents over local, SSH, and Docker. Secret redaction, output budgeting, SSH host-key verification, and a loopback read-only browser viewer that streams the live transcript.
Manage multiple SSH servers from one MCP: command execution, file transfer/rsync, database dump/import/query (MySQL/PostgreSQL/MongoDB), backups & restore, health monitoring, persistent sessions, tunnels, ProxyJump/bastion, and opt-in per-server security modes (readonly/restricted) with audit log. Linux, macOS & Windows OpenSSH.
Quality signal
44/100 (Fair)
52/100 (Fair)
Install path
pip · high
npx · high
Engagement
3 0 0 7
3 0 0 405
Tools
Persistent sessions with stateful working directory and environmentStructured ExecResult with stdout, stderr, exit code, duration, and cwdPolicy fence to allow or deny commands before executionSecret redaction and output size bounding to prevent data leaks and floodingSupport for local, SSH, and Docker transports with uniform APISession checkpoint and restore for undoing remote workspace changes
Per-server SSH agent forwarding (ForwardAgent) supportOpt-in readonly and restricted security modes with audit loggingSupport for ProxyJump/bastion hosts and SSH tunnelsShell-quoted arguments to prevent command injectionCross-platform compatibility with Linux, macOS, and Windows OpenSSH