Connect your Better Stack account to enable CloudThinker agents to monitor uptime, triage incidents, view on-call schedules, and search logs across your observability stack. Better Stack uses OAuth, so there are no API keys to create or paste. You authorize CloudThinker once from inside Better Stack, scoped to your account’s access.Documentation Index
Fetch the complete documentation index at: https://docs.cloudthinker.io/llms.txt
Use this file to discover all available pages before exploring further.
Supported Services
CloudThinker connects to the official Better Stack MCP server, spanning two surfaces:| Service | What it covers |
|---|---|
| Uptime | Monitors, heartbeats, incidents, on-call schedules, escalation policies, status pages |
| Telemetry | Log and metric queries, sources, dashboards, charts, alerts, error tracking |
Prerequisites
- A Better Stack account with access to the team you want to connect.
- Permission to authorize third-party apps for that team.
OAuth scopes the connection to what your Better Stack user can already see. Connect with the least-privileged user that works.
Setup
Required Permissions
CloudThinker inherits the authorizing user’s visibility within the connected team.- Read operations (monitors, incidents, on-call, logs, metrics) work with standard member access.
- Write operations (acknowledging incidents, publishing reports, editing dashboards or alerts) need matching Better Stack permissions and explicit approval in CloudThinker.
Agent Capabilities
Once connected, agents have broad read access and approval-gated write access.Read Capabilities
| Category | What the agent can do |
|---|---|
| Monitors | List monitors, inspect availability % and response times over a window |
| Heartbeats | Inspect cron/scheduled-job heartbeats and hit-rate |
| Incidents | List and inspect incidents, timelines, comments, and escalation options |
| On-Call | View on-call schedules, current rotations, and shift events |
| Escalations | Inspect escalation policies and severity definitions |
| Status Pages | List status pages, tracked components, and past reports |
| Logs (Telemetry) | Search logs scoped to a source, inspect source fields and config |
| Metrics | Query metrics and inspect cardinality |
| Dashboards & Charts | List and inspect dashboards, charts, and templates |
| Alerts | List and inspect chart alerts |
| Errors | List recent errors and inspect error groups |
Write Capabilities
| Category | What the agent can do |
|---|---|
| Incidents | Acknowledge, resolve, reopen, escalate, comment, or create incidents |
| Status Pages | Publish status page reports and updates |
| Dashboards & Charts | Create, edit, rename, or remove dashboards and charts |
| Alerts | Create, edit, delete, or pause chart alerts |
| Errors | Update error state (resolve / ignore) |
Example Prompts
Log search is scoped per source, so there’s no global search. Name the source (e.g.
api-gateway) so the agent can resolve it before querying.Troubleshooting
Connection fails with 401 Unauthorized
Connection fails with 401 Unauthorized
A resource returns 404 Not Found
A resource returns 404 Not Found
The resource belongs to a different team or was deleted. Re-list it in the connected team to get current IDs.
Requests fail with 429 Too Many Requests
Requests fail with 429 Too Many Requests
You’ve hit Better Stack’s rate limit. Agents back off and retry automatically.
Log query returns a syntax error
Log query returns a syntax error
Better Stack uses Live Tail syntax. Ask the agent to load the query instructions for the source, then refine.
Security Best Practices
- Least-privilege user - Authorize with only the access CloudThinker needs
- Approval for writes - Keep writes approval-gated so incident and status-page changes stay deliberate
- Scoped teams - Limit the authorizing user’s team membership to what CloudThinker should see
- Revoke when unused - Remove the authorization in Better Stack if you stop using it
Related
Datadog Connection
Observability and monitoring
PagerDuty Connection
Incident alerting and on-call