Integration · Developer tools

Connect Claude & ChatGPT to ilert

Ask your AI who is on call or which alerts are still open, and it reads it from ilert. It can accept, reassign and resolve alerts, open a manual alert, and read an alert's timeline. It can also declare incidents, post status updates, schedule maintenance windows and look up services, schedules, teams and status pages.

Connect ilert free

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

Try asking

“Who is on call for the backend team right now?”
The AI lists the current on-calls for that schedule or escalation policy.
“Which high-priority alerts are still pending?”
It lists alerts with state PENDING and priority HIGH, with source and responders.
“Accept alert 48213, I'm on it.”
It accepts the alert so escalation stops.

What your AI can do

Alerts

List and count alerts by state, priority, source or service, read the timeline, and accept, assign, resolve or open alerts.

Incidents and status pages

Declare and update incidents, post status updates, and read status pages and services.

On-call and maintenance

See who is on call, read schedules, shifts, escalation policies, teams and users, and schedule maintenance windows.

“What happened with last night's database alert?”
It reads the alert and its log entries: notifications, accepts, escalations and comments.
“Declare an incident: checkout is slow, affecting the Payments service.”
It creates the incident with title, status, summary and the affected service. If it is published to status pages, subscribers may be notified.
“Schedule maintenance on the API service Sunday from 02:00 to 04:00.”
It creates a maintenance window for the service, and alerts from it are suppressed during that time.

29 tools for ilert

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

accept_alertVisible to othersAccept (acknowledge) an alert by `alert_id` so escalation stops.
add_incident_updateChanges dataPost a status update on an incident by `incident_id` with `status` and `message`. With `send_notification` true, subscribers are notified.
assign_alertChanges dataReassign an alert by `alert_id` to a `user`, escalation `policy` or `schedule`. The new assignee is notified.
count_alertsCount alerts matching the same filters as list_alerts (states, priorities, sources, services, time range).
create_alertChanges dataOpen a manual alert with a `summary` on an `alert_source` (id), with optional `details`, `priority` (HIGH or LOW) and assignee. On-call responders are notified.
create_incidentChanges dataDeclare an incident with a `title`, `status`, `summary` and `affected_services`. If it is published to status pages, subscribers may be notified.
create_maintenance_windowChanges dataSchedule a maintenance window from `start` to `end` with a `summary` for given `services` or `alert_sources`; alerts from them are suppressed during it.
get_alertGet one alert by `alert_id` with its source, state, priority and responders.
get_current_userGet the ilert user this connection acts as. Use to confirm the account and your user ID.
get_incidentGet one incident by `incident_id` with status, summary and affected services.
get_scheduleGet one on-call schedule by `schedule_id`.
get_serviceGet one service by `service_id` with its current status.
get_status_pageGet one status page by `page_id` with its services and current status.
get_userGet one user by `user_id` with name, email and role.
list_alert_log_entriesList the log entries (timeline) of an alert by `alert_id`: notifications, accepts, escalations and comments.
list_alert_sourcesList alert sources (monitoring integrations) with their IDs. Use to find the alert_source for create_alert.
list_alertsList alerts, filtered by `states` (PENDING, ACCEPTED, RESOLVED), `priorities`, `sources`, `services`, `responders`, `labels` or a `from`/`until` time range.
list_escalation_policiesList escalation policies with their IDs.
list_incidentsList incidents, filtered by `states`, `services`, `severity` or a `from`/`until` time range.
list_maintenance_windowsList maintenance windows, filtered by `state` (OPEN or CLOSED), services, alert sources or time range.
list_on_callsList who is on call now or in a `from`/`until` window, filtered by `schedules`, `policies` or `users`.
list_schedule_shiftsList the shifts of a schedule by `schedule_id` in a `from`/`until` window.
list_schedulesList on-call schedules.
list_servicesList services, optionally searching by `query` or `labels`. Use to find service IDs.
list_status_pagesList status pages.
list_teamsList teams, optionally only those with a given member.
list_usersList users in the ilert account.
resolve_alertVisible to othersResolve an alert by `alert_id`.
update_incidentChanges dataUpdate an incident by `incident_id`. Pass the full incident (`title` is required): status, summary, severity and affected services.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose ilert from the app list.
2
Paste your key
Paste an ilert API key. In the ilert web app open your Profile, go to API Keys and click Create API Key. Copy the key; it acts with your user's permissions.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in ilert?

The AI can list, count and read alerts and their log entries, and accept, assign, resolve or create alerts. It can create, read and update incidents and post incident updates, schedule and list maintenance windows, and read on-calls, schedules, shifts, services, status pages, escalation policies, teams and users.

Does the AI see my ilert credentials?

No. Your ilert credentials are encrypted at rest and never shown to the AI. After you save them, they are 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 start with only reading alerts and on-calls. Accepting, resolving and creating alerts, and creating or updating incidents, can require your approval before they run. 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 ilert account.

Will my team or customers get notified when the AI acts?

They can. A new alert notifies the on-call responders, and reassigning an alert notifies the new assignee. An incident published to status pages may notify subscribers, and an incident update notifies them if send_notification is on. The API key acts with your user's permissions, and you can require approval for these tools.