Better Stack

Better Stack MCP Connector for Claude

A+

Automate incident management via Better Stack — monitor uptime, manage incidents, and control on-call schedules securely from your AI agent.

10 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your Better Stack (Better Uptime) account to any AI agent and empower it to act as your Level 1 Site Reliability Engineer (SRE). Let your AI diagnose incidents, manage escalations, and audit monitoring configs securely via conversation.

What you can do

  • Incident Response — Rapidly list firing incidents, inspect technical downtime payloads, acknowledge alerts, and force resolve states inline
  • Uptime Monitors — Fetch exact definitions of active HTTP endpoint pings, DNS probes, and latency constraints across your fleet
  • Cron Heartbeats — Investigate passive tracking endpoints validating background workers and server limits
  • On-Call Management — Expose active shifts and team schedules to determine explicitly who is getting paged in real-time
  • Status Pages — Read configured public dashboards tracking your global infrastructure

How it works

  1. Subscribe to this server
  2. Enter your Better Stack API Token
  3. Empower Claude, Cursor, or your preferred agent to respond to alerts interactively

Stop switching context between your terminal and incident dashboards during critical outages.

Who is this for?

  • DevOps & SREs — audit on-call matrices safely, track firing pages, and orchestrate initial debugging workflows without leaving chat
  • Engineering Managers — review recent downtime timelines and resolve dormant alerts quickly
  • Backend Developers — rapidly debug failing cron heartbeats while simultaneously patching code
incident-managementon-call-schedulingdowntime-alertsescalation-chainssre-automation

10 tools expose this connector's capabilities to your AI agent.

list_monitors

List all monitors on Better Stack (Better Uptime)

get_monitor

Get full details of a specific Better Stack monitor

list_incidents

List all explicit incidents on Better Stack

get_incident

Retrieve the native timeline payload of an explicit incident

acknowledge_incident

Acknowledge an ongoing explicit incident halting paging

resolve_incident

Force resolve a specific incident

list_heartbeats

List all configured cron heartbeats securely

get_heartbeat

Get explicit details of a passive heartbeat node

list_status_pages

List all explicit Status Pages

list_on_call

List exact On-Call routing calendars

See how to talk to your AI agent using Better Stack.

List any active unresolved incidents going on right now.

I found 1 active incident firing: ID #651239 (Critical API Down). It started 4 minutes ago and is currently escalating via phone call. Would you like me to acknowledge it locally?

Who is currently on-call for the main engineering shift?

Looking at the calendar mapping, 'Core Backend Rotation' dictates John Doe is actively on call right now as Level 1, backed up formally by Jane Smith if escalation bypasses 10 minutes unconditionally.

Check the detailed root cause of passed Incident #8012.

Fetching incident #8012. The log dump points to a 502 Bad Gateway response received structurally from your Nginx server physically hosted in the EU region during the ping interval causing manual threshold failures.

Yes! Running the `acknowledge_incident` capability pushes a verified API command halting escalation cycles (like SMS and phone calls) natively while you debug.

Related Connectors