Diagnose my server
diagnose_my_serverDiagnoses performance on the customer's own VPS from the server's telemetry — CPU load relative to their plan's vCPU count, memory pressure, and disk fullness — and explains in plain language what is wrong. Use for "why is my site slow?", "is my server struggling?", "do I need a bigger plan?", "is my disk full?".
This is server-side and VPS-only. For shared hosting it returns not_applicable — say so rather than guessing. For whether a site is REACHABLE use check_uptime; for uptime HISTORY use get_my_site_health.
IMPORTANT: lead with summary, then the individual findings detail lines. If agentReporting is false, the server is NOT confirmed healthy — we simply cannot see it; say that plainly. Only raise upgrading when upgradeSuggested is true; when it is false and the box is healthy, say the bottleneck is above the server (application, plugins, queries) rather than selling a bigger plan.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "diagnose_my_server"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| domain | No | Which of the customer's own sites to diagnose. Optional when they have exactly one. |