Typed tools, not a root shell
The assistant does not get open-ended access. It gets MCP servers — Model Context Protocol endpoints with clear jobs: write a file, commit, deploy, attach HTTPS. Power with boundaries.
Live · in production
kserpa is a control plane I designed and run myself. An AI assistant can ship websites, manage DNS, and operate the host through six dedicated tool servers — with the same discipline I use on high-stakes enterprise releases.
This page is not a mockup. It is a product of the platform: registered, built, and published through those tools.
Built like production software — not a weekend script glued to a chatbot.
The assistant does not get open-ended access. It gets MCP servers — Model Context Protocol endpoints with clear jobs: write a file, commit, deploy, attach HTTPS. Power with boundaries.
A failed git push or a broken build ends the run. The agent reports the failure and stops. That is intentional. Reliable systems refuse to paper over bad deploys.
Every app owns its GitHub repo, its container, and its hostname. Lab experiments stay separate from production. The architecture enforces that split.
The assistant calls these like APIs. Together they cover the full path from change to public site.
Server operations: git, health, deploy hooks, and verification probes.
Register products, write source, build images, and start containers.
Automatic HTTPS and routing so each app is reachable on its own domain.
Repositories and webhooks so a push can drive a real deploy.
DNS records so the world can resolve the new hostname.
Private access to the host when public entry is the wrong path.
Every public change follows this path — including updates to this page.
Two products on the same control plane. Click through — they are live.