Integration · Developer tools

Connect Claude & ChatGPT to Spike.sh

Ask your AI which Spike.sh incidents are still unacknowledged, who is on call right now, or what happened during last night's outage. It can list and read incidents, services, on-call schedules, escalation policies and integrations. It can also acknowledge, escalate and resolve incidents, set priority and severity, add responders and overrides, and post updates on your status pages.

Connect Spike.sh free

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

Try asking

“Which incidents are triggered and not yet acknowledged?”
The AI lists triggered incidents for your team, with the service, priority and severity of each.
“Who is on call right now, and who is next?”
It lists everyone currently on call across the team's schedules and finds the next person in the schedule you pick.
“Acknowledge incident 312 and set it to p1.”
It acknowledges the incident, which stops further escalation, and sets its priority to p1.

What your AI can do

Incident response

List triggered and acknowledged incidents, read an incident and its activity log, and acknowledge, escalate or resolve incidents.

On-call and escalation

See who is on call now and next, read schedules and escalation policies, add overrides and add responders to incidents.

Services and status pages

List services and the ones affected by open incidents, search past occurrences, and post incidents and updates on status pages.

“What happened in incident 305?”
It reads the incident's timeline with alerts, acknowledgements, escalations and notes.
“Post on our status page that the API is degraded and we are investigating.”
It creates a status page incident with title, description, severity and affected components. It is visible to the public and subscribers.
“Cover Sara's on-call shift on Saturday with Jonas.”
It adds an override to the on-call schedule so Jonas covers the shift from start to end.

30 tools for Spike.sh

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

acknowledge_incidentsChanges dataAcknowledge one or more incidents by their `ids`. Stops further escalation.
add_incident_responderChanges dataAdd a responder `user` to incidents by `ids` and `team_id`. The user is notified.
add_on_call_overrideChanges dataAdd an override to an on-call schedule by `oncall_id` so `user` covers the shift from `start` to `end`, with optional `timezone` and note.
add_status_page_incident_updateChanges dataAdd a status update (for example investigating or resolved) to a status page incident by `status_page_id` and `incident_id`, with `title`, `status` and component statuses. Visible to the public.
create_incidentChanges dataCreate an incident on an integration with `team_id`, `integration_webhook` (from list_integrations), `title`, `message`, and optional `priority` (p1-p5) and `severity` (sev1-sev3). This alerts the on-call responders.
create_status_page_incidentChanges dataPost a new incident on a public status page by `status_page_id` with `title`, `desc`, `severity` and affected `component_status`. Visible to the public and subscribers.
escalate_incidentsChanges dataEscalate one or more incidents by their `ids` to the next level of the escalation policy. Notifies the next responders.
get_incidentGet one incident by its number `counter_id` and `team_id`, including status, service, priority and severity.
get_incident_activity_logGet the timeline of an incident (alerts, acknowledgements, escalations, notes) by `counter_id` and `team_id`.
get_next_on_callFind who is on call next in an on-call schedule by `oncall_id`.
get_on_callGet one on-call schedule by `oncall_id` and `team_id`, showing shifts from the `from` date.
get_org_infoGet your Spike organization's details. Use to confirm which account you are working in.
get_serviceGet one service and its incidents by `counter_id` and `team_id`.
get_userGet one user by `user_id`.
list_acknowledged_incidentsList incidents that are acknowledged but not yet resolved for a team by `team_id`.
list_active_on_call_shiftsList everyone currently on call across a team's schedules by `team_id`.
list_affected_servicesList the services currently affected by open incidents for a team by `team_id`.
list_escalation_policiesList the escalation policies of a team by `team_id`.
list_incidentsList recent incidents for a team by `team_id`.
list_integrationsList the alert integrations of a team by `team_id`, including each integration's webhook.
list_on_callsList the on-call schedules of a team by `team_id`.
list_servicesList all services of a team by `team_id`.
list_status_pagesList all your status pages with their IDs.
list_teamsList all teams in your Spike organization with their 24-character team _id. Most other tools need this `team_id`.
list_triggered_incidentsList incidents that are triggered and not yet acknowledged for a team by `team_id`.
list_usersList all users in your Spike organization with their IDs.
resolve_incidentsChanges dataResolve one or more incidents by their `ids`.
search_incident_occurrencesSearch all incident occurrences between `start` and `end` dates, optionally filtered by `teams`, `status`, `service` or `integration`. Results are paginated with `page` and `limit`.
set_incident_priorityChanges dataSet the `priority` (p1-p5) on incidents by `ids` and `team_id`.
set_incident_severityChanges dataSet the `severity` (sev1-sev3) on incidents by `ids` and `team_id`.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Spike.sh from the app list.
2
Paste your key
Paste your Spike API key and your team ID. In Spike, open app.spike.sh/api (Settings › API) and generate an API key. The team ID is your team's 24-character _id, not the short slug shown in URLs. You can get it with the list_teams tool.
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 Spike.sh?

It can read your organization, teams, users, services, incidents, incident activity logs, on-call schedules, escalation policies, integrations and status pages, and search incident occurrences by date. It can create, acknowledge, escalate and resolve incidents, set priority and severity, add responders and on-call overrides, and post incidents and updates on status pages.

Does the AI see my Spike.sh credentials?

No. Your API key and team ID 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 lookups only. Creating or escalating an incident alerts responders, and status page posts are public, so those tools can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT, open Settings › Apps & Connectors › Advanced, turn on Developer mode and 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 Spike.sh account.

Where do I find my Spike team ID?

Most Spike tools need your team's _id, a 24-character ID. It is not the short slug you see in Spike URLs. The list_teams tool returns every team in your organization with its _id, so the AI can look it up for you.