Articles.

If SentinelX is connected in Claude.ai, Claude Code picks it up on its own — no config file, no second login. The whole thing in 30 seconds.

SentinelX MCP gives your assistant a real, permissioned door into your machines — not a copy-paste loop. What it does, how it works, and how to wire it up in three steps.

Hermes, by Nous Research, is one of the most talked-about agents of 2026. How it resembles SentinelX, how it differs, and why with one you talk to the agent while with the other you talk to your own LLM.

Hermes, de Nous Research, es uno de los agentes más comentados de 2026. En qué se parece a SentinelX, en qué se diferencia, y por qué con uno le hablás al agente y con el otro le hablás a tu propio LLM.

I put a full infrastructure-control agent on an Android phone in an afternoon — and Android's own sandbox turned out to be a stronger security story than I expected.

A real SentinelX session shows the security model in action: Claude discovers the host's capabilities, works inside explicit boundaries, and still gets useful infrastructure work done.

Una sesión real de SentinelX muestra el modelo de seguridad en acción: Claude descubre las capacidades del host, trabaja dentro de límites explícitos y aun así puede operar infraestructura de forma útil.

One agent, three platforms. A clear, copy-paste walkthrough to get a host enrolled and answering to your LLM in a couple of minutes.

A practical field guide: managing a fleet of servers, editing sites, coding, resolving git merge conflicts, updating systems, and debugging incidents, all from a chat window.

Giving an AI agent a shell is easy. Building a capability-based control plane is a better long-term model.

An honest look at SentinelX, the MCP server that lets an AI touch real infrastructure without letting it do anything stupid.