The read side turns a fleet into something you can interrogate — rank servers by disk usage, pull the notes off the last three incidents, generate a month of uptime. The write tools make the same key able to resolve an incident or pause a server, so point it at a client that asks for approval before running a tool, and issue a dedicated key so the activity is easy to trace.
A hosted endpoint over your Xitoring monitoring account — servers, uptime and SSL checks, incidents, metrics, status pages and reports — with over 60 tools spanning reads, reports and a curated set of write actions.
- Live and historical metrics per server — CPU, load average, memory, disk usage, disk IO, network — and the top processes on any host
- Every check type listed and inspected, with response time, overall uptime and average latency across regions
- Ongoing and historical incidents, their notes, and the trigger and notification-role routing behind them
- Uptime and SSL uptime reports, subscription details and ticket lists
- Account, Xitogent and notification history for troubleshooting and compliance
- Write actions: resolve incidents, add notes, send test notifications, pause and unpause checks or servers, create HTTP, ping, SSL and heartbeat checks, schedule maintenance windows, open tickets and invite contacts
A Xitoring account with at least one server, uptime check or integration configured, plus an API key generated under Dashboard → Account → API Access. The key travels as an Authorization bearer header to the streamable HTTP endpoint; clients that only speak stdio bridge through mcp-remote.
One command plus a key — npx -y mcp-remote https://app.xitoring.com/mcp, then supply credentials