Integration · Developer tools

Connect Claude & ChatGPT to Better Stack

Ask your AI which Better Stack monitors are down, what your uptime was last month, or who is on call. It can read incidents with their timeline and comments, acknowledge and resolve them, and check heartbeats, response times and your status pages. You get the state of your services in the chat without opening the dashboard.

Connect Better Stack Uptime free

Free plan, no credit card. Takes about a minute.

Try asking

“Are any of my monitors down right now?”
The AI lists your uptime monitors with their status and shows the ones that are down or paused, with URL and check settings.
“What was the uptime of the checkout monitor, and how slow has it been?”
It reads the monitor's availability and downtime summary and its recent response times per region.
“What happened in the latest incident?”
It finds the newest incident and reads its cause, timeline and comments: alerts, notifications, acknowledgement and resolution.

What your AI can do

Monitors and heartbeats

List monitors, monitor groups and heartbeats with their status, and read availability, downtime and response times per region.

Incidents and on-call

List incidents, read their timeline and comments, acknowledge and resolve them, and see on-call calendars, escalation policies and team members.

Status pages

Read your status pages, the monitors and components they show, and the incident and maintenance reports posted on them.

“Acknowledge the open incident on the API monitor.”
It finds the incident and acknowledges it, so escalation stops.
“Did the nightly backup cron job check in?”
It finds the heartbeat and reads its status, expected period and availability.
“Who is on call, and what does our public status page show?”
It reads the default on-call calendar with who is on call now, and the status page's current state and latest reports.

24 tools for Better Stack Uptime

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

acknowledge_incidentChanges dataAcknowledge an incident so escalation stops. Pass incident_id.
get_current_on_callGet the default on-call calendar including who is on call right now.
get_heartbeatGet one heartbeat monitor by heartbeat_id with its status and expected period.
get_heartbeat_availabilityGet a heartbeat's availability (uptime percentage) summary. Pass heartbeat_id.
get_incidentGet one incident by incident_id with its cause, status and who acknowledged or resolved it.
get_incident_timelineGet the timeline of an incident: alerts, notifications, acknowledgements and resolution. Pass incident_id.
get_monitorGet one uptime monitor by monitor_id with its current status and configuration.
get_monitor_availabilityGet a monitor's availability (uptime percentage) and downtime summary. Pass monitor_id.
get_monitor_response_timesGet recent response times for a monitor, per region. Pass monitor_id.
get_status_pageGet one status page by status_page_id with its settings and current aggregate state.
get_status_page_reportGet one status report from a status page. Pass status_page_id and status_report_id.
list_escalation_policiesList escalation policies that decide who gets alerted and when.
list_heartbeatsList heartbeat (cron job) monitors and their status.
list_incident_commentsList the comments on an incident. Pass incident_id.
list_incidentsList incidents (outages and alerts), newest first.
list_monitor_group_monitorsList the monitors in one monitor group. Pass monitor_group_id.
list_monitor_groupsList the groups monitors are organised in.
list_monitorsList uptime monitors with their URL, status (up, down, paused) and check settings. Paginated.
list_on_call_calendarsList on-call calendars.
list_status_page_reportsList the incident and maintenance reports posted on a status page. Pass status_page_id.
list_status_page_resourcesList the monitors and components shown on a status page. Pass status_page_id.
list_status_pagesList your public status pages.
list_team_membersList the members of your Better Stack team.
resolve_incidentChanges dataMark an incident as resolved. Pass incident_id.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Better Stack Uptime from the app list.
2
Paste your key
Paste a Better Stack Uptime API token. In Better Stack, open API tokens. Under Team-based tokens, pick your team and copy or create a token in the Uptime API tokens section. You can also use a Global API token.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
Click your name, then Settings › Connectors › Add custom connector. Paste your link as the Remote MCP server URL. Switch it on from the + menu in a chat.

Questions

What can the AI do in Better Stack?

The AI can read monitors, monitor groups, heartbeats, availability, response times, incidents with timelines and comments, on-call calendars, escalation policies, team members and status pages with their reports. It can acknowledge and resolve incidents.

Does the AI see my Better Stack API token?

No. Your Better Stack API token is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can keep it read-only. Acknowledging or resolving an incident can require your approval before it runs. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Better Stack account.

Can the AI create or change monitors?

No. The AI reads your monitors, heartbeats and status pages but does not create, edit or pause them. The only changes it can make are acknowledging and resolving incidents.