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.
Full SSH access for AI agents with secret-safe environment injection and automatic output redaction. Persistent sessions, structured execution, SFTP, port forwarding — secrets are fed via stdin (invisible to ps) and scrubbed from all tool responses before reaching the LLM. uvx mcp-remote-ssh
Administer a Linux server from an MCP client such as Cursor or VS Code: read files and tail logs, check/reload/restart systemd services, manage cron jobs inside a dedicated crontab section, run read-only MySQL queries, drive WP-CLI on WordPress sites, run safe Git commands, and execute sandboxed Python. Directories, services and WordPress sites are allowlisted in config.json, and every tool returns a uniform {success, data, error, meta} response. Runs as a systemd service over HTTP.
Quality signal
45/100 (Fair)
44/100 (Fair)
Install path
uvx · high
uvx · low
Engagement
3 0 0 6
0 0 0 2
Tools
Password, key, or agent-based SSH authenticationSecret-safe environment variable injection from local filesAutomatic redaction of secret values in all tool outputsPersistent interactive shell sessions preserving stateSupport for SFTP file transfers and SSH port forwardingStructured command execution with exit codes
