# Better Stack MCP for AI Agents AI Agent Connect > Better Stack MCP. Monitor uptime and incidents directly from your AI agent. List monitors, heartbeats, and on-call schedules without switching tabs. Get real-time updates on active incidents, manage your status pages, and verify your cron job heartbeats through natural conversation. It's the fastest way to keep your infrastructure oversight organized. ## Overview - **Category:** ship-it - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_QAa4ho1S8q5tWsBBJcqMpbW32eNjsNQvGSQMv2ng/ai-agent-connect - **Tags:** uptime-monitoring, incident-response, sre, alerting, heartbeat-monitoring, infrastructure-monitoring ## Description Managing infrastructure usually means jumping between dashboards, checking Slack for alerts, and digging through logs to see who's on call. This Connector changes that by bringing your Better Stack data directly into your AI client. Instead of hunting for a specific monitor's status or searching for an incident report, you just ask your agent. You can check if your cron jobs are hitting their heartbeats, see who's handling the current rotation, or grab the latest updates on an ongoing outage. It's about having your monitoring data available exactly where you're already writing code or coordinating responses. If you're looking for a way to keep your infrastructure oversight organized, you'll find this Connector in the Vinkius catalog. It cuts out the manual navigation and lets you focus on fixing the actual problem. ## Tools ### list_heartbeats See all heartbeat monitors to track recurring tasks and cron jobs. This helps you confirm that your background processes are still healthy. ### list_incidents See a list of recent uptime incidents to track historical outages. This helps you quickly review what happened during past service disruptions. ### create_monitor Set up a new uptime monitor for a new service or endpoint. You can tell your agent to add a new URL to your monitoring list instantly. ### delete_monitor Remove a monitor that is no longer needed from your account. This keeps your list clean by getting rid of decommissioned services. ### get_incident Get the specific details and status of a single, active incident. Use this to pull the exact error messages or timestamps you need for triage. ### get_monitor Pull the full configuration and status of a specific monitor. This is the best way to see the exact settings for a single service. ### list_monitors Get a full list of all your current uptime monitors in one view. You can use this to see every service your account is currently tracking. ### list_on_calls Check who is currently on-call and see the upcoming rotation schedule. This is useful for knowing who to contact during an emergency. ### list_status_pages View all your public-facing status pages to see what users see. Use this to verify that your public updates are accurate. ### update_monitor Change the configuration of an existing monitor quickly. This lets you adjust check intervals or endpoints without opening a browser. ## Prompt Examples **Prompt:** ``` Which monitors are currently failing? ``` **Response:** ``` I've checked your monitors. Currently, 2 services are down: | Service | ID | Status | | :--- | :--- | :--- | | Primary API | mon_123 | Down | | Auth Gateway | mon_456 | Down | Would you like to see the incident details for these? ``` **Prompt:** ``` Who's on call for the core infra rotation? ``` **Response:** ``` Retrieving on-call data... For the **Core Infrastructure** rotation, **Sarah Miller** is on-call until Friday, and **John Doe** will take over for the weekend. ``` **Prompt:** ``` Show me the last 3 incidents for the auth service. ``` **Response:** ``` Here are the 3 most recent incidents for the **Auth Service**: * **Incident #882**: Connection Timeout (2 hours ago) * **Incident #881**: High Latency (1 day ago) * **Incident #880**: Database Lock (3 days ago) Would you like to pull the full report for any of these? ``` ## Capabilities ### List all uptime monitors Get a full list of every service your account is currently tracking in one view. ### Create new uptime monitors Tell your agent to add a new URL or service to your monitoring list instantly. ### Delete existing monitors Remove decommissioned services from your monitoring list to keep your workspace clean. ### Update monitor settings Adjust check intervals or endpoints for existing monitors without opening a browser. ### Retrieve incident details Pull specific error messages or timestamps from an active incident for quick triage. ### List recent incidents Review a history of recent uptime incidents to understand past service disruptions. ### Check on-call rotations Identify the right person to contact during an emergency by viewing current schedules. ### Monitor cron job heartbeats Confirm that your background processes and recurring tasks are still running healthy. ### View public status pages Verify that your public-facing status updates are accurate and visible to customers. ### Get specific monitor details See the exact configuration and current status of a single service in one go. ## Use Cases ### Outage Triage An SRE asks 'What's the status of the auth gateway?' and uses get_incident to see the current error logs and status. ### Cron Job Audit A backend dev asks 'Are the daily backups running?' and the agent uses list_heartbeats to check the last ping for all tasks. ### New Service Launch A dev wants to monitor a new API and uses create_monitor to set up an HTTP check instantly without leaving their editor. ### Shift Handover A manager asks 'Who is on call this weekend?' and the agent pulls the rotation from list_on_calls to confirm coverage. ## Benefits - Faster incident response by using list_incidents to see what's broken immediately without opening a browser. - Easier cron job tracking with list_heartbeats to ensure your background tasks are actually running. - Clearer ownership during outages by using list_on_calls to identify the right person to contact. - Quicker monitor setup by using create_monitor to add new services to your uptime checks. - Quick post-mortems by using get_incident to pull specific data for your reports. - Better status page management by using list_status_pages to verify public-facing info. ## How It Works The bottom line is you get your entire infrastructure monitoring suite accessible through a single chat interface. 1. Subscribe to the Better Stack MCP on Vinkius. 2. Provide your Better Stack API Token in your client settings. 3. Ask your agent to check monitor statuses or list recent incidents. ## Frequently Asked Questions **Can I use the Better Stack MCP to see who is on call?** Yes. You can ask your agent to pull the current rotation so you know exactly who is responsible for the system at any time. **Does the Better Stack MCP work for my cron jobs?** Yes. It can list all your heartbeat monitors so you can check if recurring tasks are running correctly. **Can I create new monitors with this Connector?** Yes. You can tell your agent to set up a new uptime monitor for any URL or service you need to track. **How do I see my public status pages?** You can ask your agent to list all your public status pages to verify that your public updates are accurate. **Can I get details on a specific outage?** Yes. Your agent can pull the specific details of an active incident, which is helpful for quick triage and post-mortems. **Is this Connector good for SRE teams?** Yes. It helps SREs quickly access incident history and on-call schedules without needing to navigate complex dashboards during high-pressure events. **Can I check if a specific website is down using the agent?** Yes! Use the `list_monitors` tool to see the status of all your monitored URLs. You can also use `get_monitor` with a specific ID to see its current status and last checked timestamp. **How do I see who is currently on-call?** Simply ask the agent to `list_on_calls`. It will retrieve the current schedules and rotations, showing you who is responsible for incident response right now. **Does the integration allow me to create a new heartbeat monitor?** Currently, the toolset focuses on managing monitors and retrieving incident/on-call data. You can list and inspect heartbeats, but for creating new monitors with complex notification rules, we recommend using the Better Stack dashboard.