How to Connect Better Stack to Claude via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Better Stack, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Better Stack + Claude

Better Stack uptime monitoring and incident management: monitors and heartbeats with availability and response times, incidents with acknowledge, escalate and resolve, on-call calendars, escalation policies, status pages and status reports, and the configured integrations.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

BETTER_STACK_API_TOKEN

Step 1 — Get credentials

Setting up takes about 2 minutes. The connector uses the Better Stack Incidents API (formerly Better Uptime, https://incidents.betterstack.com/api).

1. Open https://betterstack.com/settings/api-tokens/0, pick your team and copy or create a token under Incidents API tokens. This team-scoped token is the simplest choice.
2. A global API token (https://betterstack.com/settings/global-api-tokens) also works and reaches every team. With it the AI passes team_name to filter lists, and it is required when creating monitors, heartbeats or incidents.
3. Paste the token into BETTER_STACK_API_TOKEN. Writes need a token with write access.
4. Install the connector and run better_stack_list_monitors to check the token.

What it reads:

• Uptime monitors with status (up, down, paused, validating, maintenance), URL, type, frequency, regions and last check, one monitor's full configuration, its availability (SLA) for a date range and its response times per region over the last 24 hours. Monitor groups and the monitors in a group.
• Heartbeats for cron jobs and background tasks with their ping URL, period, grace and status, their availability, and heartbeat groups.
• Incidents, newest first, with cause, status, start, acknowledge and resolve times and who did it, filtered by date range, monitor, heartbeat, resolved or acknowledged; one incident with the failing response; its timeline of alerts, acknowledgements, escalations, comments and status page updates; and its comments.
• Who is on call: on-call calendars with the person on call now, a calendar at a given moment (default for the team's default calendar), and the shifts in a time window. Escalation policies with their steps and the severities with their alert channels.
• Status pages, the resources they show with availability and daily history, status reports and their updates.
• Configuration: incoming and outgoing webhooks, Slack integrations and metadata records such as service owner or environment.

What it writes: monitors (better_stack_create_monitor, better_stack_update_monitor, better_stack_pause_monitor and better_stack_resume_monitor around planned work); heartbeats (better_stack_create_heartbeat returns the ping URL the job must call after each run, better_stack_update_heartbeat); incidents (better_stack_create_incident, better_stack_acknowledge_incident, better_stack_escalate_incident, better_stack_resolve_incident, better_stack_reopen_incident, better_stack_add_incident_comment); status pages (better_stack_create_status_report, better_stack_add_status_update as things change, better_stack_update_status_report to change the title or reschedule a maintenance).

Every tool is on at install, the writing ones included. Creating an incident, escalating it and publishing a status report alert real people or public subscribers, so the AI confirms with you first; notify_subscribers: false keeps a status report quiet. Resolving an incident of a monitor that still fails opens a new incident on its next check. A status report is closed by an update that sets every affected resource to resolved.

Data formats: answers follow JSON:API: data (one object or a list) with id, type, attributes and relationships; related users and status updates come in included. Ids are numeric strings. Times are ISO 8601 in UTC; date filters (from, to) take YYYY-MM-DD. Availability is a percentage (99.98); downtime, incident lengths and response times are in seconds. Incident status is Started, Acknowledged or Resolved. Monitor passwords, Playwright environment variables and policy incident tokens are left out of the answers.

Paging: lists return pagination.next, a URL that is null on the last page; the AI calls again with page set to the page number in that URL. per_page is 50 by default and up to 250; incidents default to 10 and allow 50.

Common errors: 401 means a wrong or revoked token, or a Telemetry token instead of an Incidents one. 403 is a token without write access, 404 an unknown id or an id of another team, 422 a validation error whose errors names the field, 429 the rate limit.

The connector does not cover Better Stack Telemetry (logs, metrics, dashboards) and does not delete monitors, heartbeats, incidents or status pages.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Claude

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Recommended path: works on claude.ai web without editing any config file.

1. In Claude, open Customize → Connectors.
2. Click +, then Add custom connector.
3. Enter a name, e.g. Better Stack, and the remote MCP server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID, then click Add.
4. Click Connect and sign in to AnythingMCP (OAuth) to allow access.

All tools below appear in your chat: start typing prompts.

Available tools

Example prompts

• "Is anything down right now? List the monitors that are down with their URL and last check."
• "What was the availability of the monitor for https://shop.example.com last month, and what was the longest incident?"
• "Who is on call on the default calendar this Saturday at 22:00?"
• "Show the open incidents with their cause and timeline, then acknowledge the one on the payments API."
• "Post a planned maintenance on our status page for Sunday 02:00 to 03:00 UTC affecting the API, without notifying subscribers. Show me the text first."

FAQ

Does it work with Claude Code as well as Claude Desktop? Yes, point both at https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID.

Next steps

• Connector landing page
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse
• Connect to Microsoft Copilot