remotify-mcp
Related Servers
Alternatives to remotify-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceA self-hosted MCP server that gives AI coding assistants direct shell access to your local machine, enabling execution of arbitrary bash commands for development workflows.6,054 npmISC
- AlicenseAqualityCmaintenanceAn MCP server that lets an AI assistant run commands and transfer files over SSH without exposing connection details.5MIT
- AlicenseAqualityCmaintenanceAn MCP server that gives AI agents SSH access to remote machines through your local OpenSSH client, enabling remote command execution, file transfer, persistent shell sessions, and port forwarding.17319 PyPI38MIT
- AlicenseNot gradedqualityFmaintenanceA security-first MCP server that gives AI assistants controlled, safe access to manage remote servers via SSH with whitelisted operations and no generic command execution.MIT
- AlicenseNot gradedqualityDmaintenanceA secure MCP server that enables AI assistants to execute commands on remote servers via SSH, with cross-platform support and features like encrypted config storage, connection management, and security controls.1MIT
- AlicenseBqualityFmaintenanceAn MCP server that allows AI models to execute system commands on local machines or remote hosts via SSH, supporting persistent sessions and environment variables.143 npm28MIT
TDQS
Scored across 3 tools
The three tools target distinct intents: read session state (remote_session_info), run a command (remote_exec), and recover/rotate a session (remote_session_reset). There is some overlap because remote_exec's description absorbs most of the state-handling (pending/in-flight/busy/recovered) logic that conceptually belongs with remote_session_reset, so the boundary between 'just retry exec' and 'call reset' can be blurred. Still, an agent can tell the three apart.
remote_session_info and remote_session_reset follow a clean remote_session_<verb> pattern, while remote_exec shortens to remote_<verb>. All snake_case with a consistent remote_ prefix, so it reads predictably, but the session/exec split is a minor deviation rather than a fully uniform scheme.
Three tools is lean but appropriate for a deliberately minimal, security-bounded relay surface (info, execute, reset). Each tool earns its place, though the low count means a lot of lifecycle complexity is crammed into remote_exec's description instead of being expressed as tools.
The core lifecycle (connect/info, run, recover/rotate) is covered, but there is no way to cancel or interrupt an in-flight command, no separate status/output-poll tool, and no explicit teardown beyond reset. These gaps are workable via the marker protocol, but agents have no clean primitive for interrupting long operations other than dropping the whole session.