Monitors and checks
List monitors, see what needs attention, read recent check results and alert history, and create, update, pause or resume HTTP monitors.
Connect Claude, ChatGPT, Cursor, VS Code or any MCP client to Site Qwality. Ask what is down, what happened in last night's incident, or what the logs said, and let it take the everyday actions for you. Included on every plan, including free.
Site Qwality runs a hosted Model Context Protocol
server at https://mcp.siteqwality.com/mcp. Add it to your assistant,
sign in, choose what it may do, and it works with your monitors, incidents,
status pages, logs, metrics and traces.
List monitors, see what needs attention, read recent check results and alert history, and create, update, pause or resume HTTP monitors.
List and read incidents, open one, post updates, and acknowledge or resolve it from the conversation you are already in.
Search logs, query metrics and look up traces, so the assistant can answer "what changed around 14:00?" with your own data.
Two general tools find and call any documented API operation, so the assistant is not limited to the curated ones.
Grant read or write per area: monitors, incidents, notifications, status pages, logs, metrics, traces, RUM and dashboards. A read-only switch grants nothing that changes data.
Changes an assistant makes appear in your audit log as the person who approved it, with the assistant's name, the tool it used, and a mark that it came through MCP.
Add the server URL and your assistant sends you to Site Qwality to sign in. You see which assistant is asking and what it wants, untick anything you would rather not grant, and approve.
Agents that cannot open a browser use a scoped API key instead, sent as a Bearer token. The key's scopes apply to every tool, exactly as they do on the REST API.
tools for monitors, incidents, status pages and telemetry
MCP access on every plan, including free
areas you can grant read or write on, one by one
for a revoked assistant to lose access
Any client that supports remote MCP servers over Streamable HTTP. The setup guide has steps for Claude, Claude Code, ChatGPT, Cursor, VS Code and the Codex CLI.
No. The MCP server is included on every plan, including the free tier. Plan limits and usage quotas apply exactly as they do in the dashboard.
Only what you approve, and only what your own role allows. Tools that delete are marked as destructive, so assistants that honour the marking ask before running them. Billing, team members, API keys and SSO settings are not reachable through MCP at all.
Every change it makes is in your audit log, as you, with the assistant's name, the tool it used, and a mark that it came through MCP. Connecting and disconnecting an assistant are logged too.
Revoke it on the AI Assistants tab in your account settings. It cannot sign in again without your approval, and the access it already had stops working within a minute.
Uptime, Cron, Synthetic, Logs, RUM, Incidents und Statusseiten. Kostenlose Stufe bei jedem Produkt.