# Gatus (Health Dashboard) MCP for AI Agents AI Agent Connect > Gatus (Health Dashboard) MCP lets you monitor your infrastructure's health directly through your AI agent. Instead of clicking through dashboards, you can list all your endpoints, check real-time status updates, and pull performance metrics or raw Prometheus data with simple questions. It turns your AI into a 24/7 SRE assistant for your service availability. ## Overview - **Category:** cloud-infrastructure - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_SZx7OyqfGelePhBmZTfpkK6YDYBS4FrcrFgcux0J/ai-agent-connect - **Tags:** service-health, uptime-monitoring, infrastructure-alerts, real-time-status, dashboard ## Description Gatus (Health Dashboard) MCP connects your infrastructure health data to your AI agent. Managing a complex infrastructure usually means having dozens of tabs open, each showing a different service's health. It's a constant cycle of refreshing pages and hunting for that one red light that indicates a failure. This Connector changes that by letting you ask about your system's status and get immediate answers. Whether you need to see if the core API is up or want to dig into the latency of a specific database, the information comes to you. You can quickly audit all monitored endpoints at once or grab raw metrics for deeper technical analysis without ever leaving your workspace. It's one of the many high-quality integrations found in the Vinkius catalog, designed to make sure you're always in the loop. You stop being a dashboard jumper and start being an informed operator who gets answers in seconds. This means you can handle incident response faster because the data is already at your fingertips. You don't have to worry about the friction of navigating a complex UI when a service goes down; you just need to know the status, and your agent provides it. It turns your monitoring into a conversation rather than a chore. Instead of manually copying data into reports or spreadsheets, you can just ask for a summary of the current performance. This keeps your focus on solving problems rather than searching for the data needed to understand them. ## Tools ### get_endpoint_health Get the current health status and recent results for a specific endpoint. It helps you see if a service is up and what the last check revealed. ### get_endpoint_stats Pull performance statistics for a specific endpoint. Use this to identify latency trends and reliability issues. ### list_endpoints List all monitored endpoints and their current status. This gives you a bird's-eye view of your entire infrastructure health. ### get_metrics Retrieve Prometheus-compatible metrics from Gatus. This is for when you need raw data for deep technical analysis or custom reporting. ## Prompt Examples **Prompt:** ``` List all monitored endpoints and their current status. ``` **Response:** ``` I've retrieved the status for 8 endpoints. 7 are 'Healthy' and 1 ('payment-gateway') is currently 'Unhealthy'. Would you like me to investigate the 'payment-gateway' results? ``` **Prompt:** ``` What is the health status of the 'core-api' endpoint? ``` **Response:** ``` The 'core-api' endpoint is currently Healthy. The last check was successful with a 200 OK response and a latency of 45ms. Recent history shows 100% uptime over the last 24 hours. ``` **Prompt:** ``` Show me the performance statistics for 'database-service'. ``` **Response:** ``` Fetching stats for 'database-service'... Average latency is 12ms, with a 99th percentile of 85ms. There have been 0 failures in the last 500 requests. ``` ## Capabilities ### List all monitored endpoints Get a bird's-eye view of every service's health in your infrastructure. ### Check specific endpoint health Retrieve the current status and latest check results for a single service. ### View performance statistics See latency trends and reliability data for specific endpoints. ### Export Prometheus metrics Pull raw data for deep technical analysis or custom reporting. ### Audit infrastructure availability Quickly verify that all services are running after a deployment. ### Analyze latency trends Identify performance regressions by pulling historical stats. ## Use Cases ### Deployment Verification A developer just pushed a new update and needs to confirm all services are green without checking five different URLs. They ask the agent to list all endpoints. ### Latency Investigation An alert shows the payment gateway is slow. An engineer asks for the specific performance stats to see the p99 latency for that specific endpoint. ### Executive Reporting A product manager needs a quick summary of system uptime for a weekly status update sent to stakeholders. They ask the agent for a high-level status report. ### Custom Analytics A data engineer needs to pull raw Prometheus metrics to build a custom Grafana dashboard for a specific internal team. They use the agent to fetch the raw data. ## Benefits - Stop manual dashboard jumping by using list_endpoints to see your entire system's status in one go. - Identify bottlenecks faster by pulling specific performance data with get_endpoint_stats. - Get instant answers on service availability using get_endpoint_health during active incidents. - Simplify technical reporting by pulling raw data with get_metrics for Prometheus-compatible analysis. - Reduce mean time to recovery by having your agent act as a 24/7 SRE assistant for your infrastructure. ## How It Works The bottom line is you get instant, conversational access to your entire infrastructure's health without switching tabs. 1. Subscribe to the Connector in your AI client 2. Enter your Gatus instance URL 3. Ask your agent for your system's health status ## Frequently Asked Questions **Can I use Gatus (Health Dashboard) MCP to check my uptime?** Yes. This Connector allows your AI agent to check the real-time status of all your monitored endpoints and report back on their availability instantly. **How does Gatus (Health Dashboard) MCP help with incident response?** It gives you immediate visibility. Instead of hunting for data, you can ask your agent which services are down and get the specific health results right away. **Can Gatus (Health Dashboard) MCP pull Prometheus metrics?** Yes, it can. You can ask your agent to retrieve Prometheus-compatible metrics for deep technical analysis or for use in your own custom reporting tools. **Does Gatus (Health Dashboard) MCP work with my existing dashboard?** It works with your existing Gatus instance. You just need to provide the instance URL to your AI agent to start pulling data. **Can I see the history of a specific endpoint with Gatus (Health Dashboard) MCP?** Yes, you can drill down into specific services to see recent results and status history through natural language queries. **Is Gatus (Health Dashboard) MCP good for non-technical stakeholders?** It's great for anyone who needs a quick status update. Product owners can ask for high-level summaries of system availability without needing to understand the underlying tech. **Can I see the status of all my services at once?** Yes! Use the `list_endpoints` tool to retrieve a complete list of all configured endpoints and their current health status across your Gatus instance. **How do I check the performance history of a specific service?** You can use `get_endpoint_stats` with the endpoint's slugified key to see detailed performance statistics, or `get_endpoint_health` for recent health check results. **Does this server provide raw metrics for analysis?** Yes, the `get_metrics` tool retrieves raw Prometheus-compatible metrics exported by Gatus, allowing your AI to perform deep technical analysis.