How to Connect Better Stack to Microsoft Copilot 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 + Microsoft Copilot

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 Microsoft Copilot

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.

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Better Stack tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

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

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse