Site Qwality

npx add-mcp 'https://mcp.siteqwality.com/mcp'

Ask about your services in plain words.

The server is hosted, so there is nothing to install. Add the URL to your assistant, sign in, choose what it may do, and it works with your monitors, incidents, postmortems, on-call schedules, services, status pages, logs, metrics and traces. 39 of the 91 tools only read. See the full tool list.

Monitors and checks

See what is down and why, pause or resume monitors, acknowledge outages, and create HTTP, TCP port and ping monitors.

Incidents

Read incidents and their timelines, open one, post updates, acknowledge or resolve it, and publish it to a status page.

Postmortems and follow-ups

Start a postmortem drafted from the incident, take it through review, and track action items across every incident.

On-call and alert delivery

Ask who is on call now or next, read shifts and the on-call load, and check whether each alert arrived.

Services

Group monitors into services, see each one’s health and who is on call, and choose which monitors open incidents.

Status pages

Create pages, arrange their layout, add monitors and components, and set what a component shows.

Maintenance, subscribers and branding

Schedule maintenance, manage subscribers, change branding and serve a page on your own domain.

Logs, metrics and traces

Search logs, query metrics and open traces span by span, so the assistant can answer “what changed around 14:00?” from your own data.

The rest of the API

Two more tools reach the rest of the API, from notification channels to dashboards and RUM, within the access you grant.

Sign in, no keys to paste

Approve it once,revoke it any time.

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, switch on read-only or untick any area you would rather not grant, and approve.

• The assistant acts as you, and never with more access than your role allows
• A viewer's assistant is as read-only as the viewer, even if write access is approved
• Revoke it under AI assistants in your personal settings; it loses access within a minute

app.siteqwality.com / oauth / authorize

Approve access WaitingLIVE

VIEW 3 areas

CHANGE 1 area

EXPIRES on revoke

monitorsview

incidentsview

pagesview

monitorschange

Setup by client

Paste one URL.

Every client gets the same server URL, https://mcp.siteqwality.com/mcp. Clients that support OAuth open a browser to sign you in the first time. The setup guide has the full steps.

• Claude (web and Desktop): Customize, Connectors, Add custom connector, paste the URL, then Connect
• ChatGPT: add the URL as a custom MCP app with OAuth sign-in
• Claude Code, Cursor, VS Code and Codex CLI: use the snippets on this page

Claude Codeclaude mcp add --transport http siteqwality \
https://mcp.siteqwality.com/mcp
# then run /mcp in Claude Code and sign in

Cursor: ~/.cursor/mcp.json{
"mcpServers": {
"siteqwality": {
"url": "https://mcp.siteqwality.com/mcp"
}
}
}

VS Code:.vscode/mcp.json{
"servers": {
"siteqwality": {
"type": "http",
"url": "https://mcp.siteqwality.com/mcp"
}
}
}

Codex CLIcodex mcp add siteqwality \
--url https://mcp.siteqwality.com/mcp
codex mcp login siteqwality

Headless agents and CI

Or use anAPI key.

Agents that cannot open a browser use an API key instead, sent as a Bearer token. Create it under Settings, API keys with Full access. The key's scopes apply to every tool, exactly as they do on the REST API.

• Works with any client that speaks Streamable HTTP and can send a header
• Tick only the scopes the agent needs
• Its changes are audited as that key, marked as coming through MCP

Claude Code$ claude mcp add --transport http siteqwality \
https://mcp.siteqwality.com/mcp \
--header "Authorization: Bearer $SITEQWALITY_API_KEY"

Permissions

Read or change,area by area.

Grant read or write access area by area. The consent screen offers the first nine areas, and API keys can also take the last two.

• A tool outside the areas you granted is refused
• Changing integrations needs a separate permission, never offered at sign-in
• Session replay content and public dashboard share links are never available to an assistant

Area	Covers
Monitors	HTTP, TCP port, ping, SSL/TLS, domain expiry, cron and browser checks
Incidents	Incidents (including those on status pages), escalation policies, on-call schedules, maintenance windows
Notifications	Notification channels and groups, delivery history, and reading integrations
Status pages	Pages with their monitors, layout, maintenance, subscribers, branding and custom domain
Logs	Log search, parsers, saved views
Metrics	Metric queries and saved views
Traces	Trace search and detail
RUM	RUM applications and analytics
Dashboards	Dashboards, templates, version history, widget queries
Services (API key only)	Services and the escalation policy each one routes to
User notification settings (API key only)	Each user's contact methods and notification rules

Security

Every changeis on the record.

An assistant's changes go through the same API as the dashboard, so they land in your audit log under Settings, Audit log, with the assistant and the tool it used.

• Billing, team members, API keys, SSO and account security are off-limits to every tool
• The 13 tools that delete, remove or replace something are flagged destructive, so assistants that honor the flag ask you first
• Tools tell the assistant to treat monitor names and log lines as data, never as instructions

app.siteqwality.com / settings / audit-log

Audit log RecordedLIVE

ACTOR Claude

VIA MCP

KEPT 90 days

Paused a monitorcheckout-api

Acknowledged an incidentCheckout errors

Posted an updateCheckout errors

Resumed a monitorcheckout-api

91

tools for monitors, incidents, on-call, services, reports, status pages and telemetry, 39 of them read only

$0

MCP access on every plan, including free

9

areas the consent screen lets you grant read or write on, one by one

1 min

for a revoked assistant to lose access

FAQ

Yes. It works with any client that supports remote MCP servers over Streamable HTTP, with OAuth sign-in or an API key. The setup guide has steps for Claude (web and Desktop), Claude Code, ChatGPT, Cursor, VS Code and the Codex CLI. In Claude you add the URL under Customize, Connectors, Add custom connector; in Cursor you add it to mcp.json; in ChatGPT you add it as a custom MCP app.

Only if you allow it, and only what your own role allows. At sign-in you can switch on read-only or untick individual areas. 39 of the 91 tools only read. The other 52 can change things, for example pausing a monitor, acknowledging or resolving an incident, posting a status page update or scheduling maintenance. Billing, team membership, API keys, SSO and session replay content are withheld from the tools.

Yes. It is included on every plan, including the free tier, with no separate charge. Plan limits and usage quotas apply exactly as they do in the dashboard. Your AI assistant's subscription is separate.

In the dashboard under Settings, Audit log, for the last 90 days. Every change an assistant makes is recorded as the member who approved it, with the assistant's name and the tool it used, and connecting or disconnecting an assistant is recorded too. See the audit log docs.

Whatever the tools return for your account, limited to the areas you granted and to your role: monitor names, URLs and check results, incidents with their timelines and postmortems, on-call schedules, services, notification delivery history, status pages, and logs, metrics and traces if you grant those areas. It cannot see session replay content, billing, the team member list or API keys.

With an API key sent as Authorization: Bearer <key>. Create it under Settings, API keys, choose Full access, and tick only the scopes the agent needs. Its changes are audited as that key and marked as coming through MCP.

Yes, 300 requests a minute per API key or signed-in user. Plan limits and usage quotas apply as they do in the dashboard.

Several monitoring vendors publish one. Ours has 91 tools across monitors, incidents, on-call, status pages and telemetry, and is free on every plan. The comparison of monitoring tools with an MCP server lists each vendor from its own docs.

Revoke it on the AI assistants tab in your personal settings. It cannot sign in again without your approval, and the access it already had stops working within about a minute.