# Tingyun MCP for AI Agents AI Agent Connect > Tingyun is an APM and observability platform that lets your AI agent manage application health, performance metrics, and incident alerts. Instead of digging through complex dashboards, you can ask your agent to pull summaries, check active alerts, or audit infrastructure dependencies. It turns your observability stack into a conversational interface for faster troubleshooting and system auditing. ## Overview - **Category:** developer-tools - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_LYTPskntXjT3hDeJtLttKdaHELmt1TtQotKDAVf3/ai-agent-connect - **Tags:** apm, performance-metrics, incident-response, application-monitoring, real-time-alerts, digital-experience ## Description Imagine you're in the middle of a production incident. Usually, this means opening a dozen tabs, hunting for the right dashboard, and trying to correlate database lags with application errors. With Tingyun connected to your agent, that process changes completely. You just ask your agent what's wrong. It can instantly pull a health summary for your core services, list the active alerts currently firing, and check if your database dependencies are hanging. It acts like a site reliability assistant that knows your entire stack. You can audit your infrastructure, browse Real User Monitoring data to see what your customers are experiencing, and query specific metrics to find that one weird spike in traffic. It takes the manual labor out of observability. You can even use it to keep your team informed by checking alert policies or listing external service calls. When you use this through the Vinkius catalog, you're essentially giving your agent a seat in the command center. You stop hunting for data and start making decisions based on it. ## Tools ### list_alert_policies List alert policies. Use this to review your active monitoring rules. ### list_app_instances List application instances. This helps you see every running instance of your apps. ### list_applications List APM applications. Use this to see every application currently being monitored. ### list_browser_apps List RUM browser applications. This lets you audit frontend performance for users. ### list_databases List monitored databases. Use this to identify your database dependencies. ### list_external_services List external service calls. This shows which outside APIs your apps are calling. ### get_account_info Get your account metadata. This helps the agent understand your account context. ### get_app_summary Get an application summary. Use this to quickly see the health of a specific app. ### get_metrics Query metric data. This lets you pull specific data points for trend analysis. ### list_alerts List active alerts. Use this to see all current issues firing in your system. ## Prompt Examples **Prompt:** ``` What's the current status of our main payment service? ``` **Response:** ``` ### Payment Service Status | Metric | Value | | :--- | :--- | | **Status** | ✅ Healthy | | **Avg Latency** | 142ms | | **Error Rate** | 0.02% | | **Apdex Score** | 0.98 | Everything looks stable. Would you like to see the database dependencies for this service? ``` **Prompt:** ``` Are there any active alerts right now? ``` **Response:** ``` I've checked the system for active alerts. Here's what's currently firing: * **Critical**: High Latency on `Payment-Gateway` (Duration: 12m) * **Warning**: Disk Usage > 85% on `Auth-DB-01` (Duration: 45m) Should I pull the full alert details for the `Payment-Gateway` issue? ``` **Prompt:** ``` Show me the database dependencies for the user API. ``` **Response:** ``` The `User-API` is currently connected to the following monitored databases: * **Primary**: `User_DB_Prod_01` (PostgreSQL) * **Read-Replica**: `User_DB_Read_02` (PostgreSQL) It also makes frequent external calls to the `Session-Cache` service. ``` ## Capabilities ### Pull application health summaries Get a quick snapshot of how your apps are performing without opening a dashboard. ### List active system alerts See every active alert across your environment in a single list. ### Query performance metrics Retrieve specific data points to analyze trends or find anomalies. ### Audit database dependencies Identify which databases your applications are connected to. ### Browse RUM browser applications Check frontend performance data to see what your actual users are experiencing. ### List external service calls See which external APIs and services your applications are hitting. ### View alert policies Review your configured alert rules to ensure they're catching the right issues. ## Use Cases ### Emergency Triage An SRE asks the agent to find all critical alerts and then uses get_app_summary to see which service is failing. ### Dependency Mapping A dev wants to know what databases a service hits and asks the agent to list them using list_databases. ### Capacity Planning A manager asks the agent to pull metric data using get_metrics to see if they need to scale their infrastructure. ### Frontend Audit A product owner wants to check the RUM data for their web app using list_browser_apps to see how it's performing for users. ## Benefits - Faster incident response: Use list_alerts and list_alert_policies to identify and prioritize critical issues in seconds. - Easier infrastructure audits: Quickly see your entire stack by using list_databases and list_external_services to map dependencies. - Real-time health checks: Get an instant look at your system's status with get_app_summary instead of manual dashboard navigation. - Deep metric analysis: Use get_metrics to pull specific data points for trend analysis without writing complex queries. - Frontend performance visibility: Audit what your users see by browsing RUM browser applications with list_browser_apps. ## How It Works The bottom line is you get a conversational interface for your entire APM and observability stack. 1. Subscribe to the Tingyun MCP on Vinkius. 2. Input your Tingyun API Key and Secret Key into your AI client. 3. Ask your agent to check app statuses, pull metric data, or list active alerts. ## Frequently Asked Questions **Can Tingyun help me find the root cause of a production crash?** Yes, it can. Your agent can pull health summaries and active alerts instantly to help you identify which service is failing and why. **How does the Tingyun MCP work with my AI agent?** It connects your Tingyun account to your AI client. This allows your agent to read your metrics, alerts, and application data directly. **Can I use Tingyun to see how my website is performing for real users?** Yes, it includes Real User Monitoring (RUM) capabilities so your agent can audit frontend performance and browser application data. **Does Tingyun support checking my database connections?** Yes, the Connector can list your monitored databases and external service calls to help you map out your infrastructure dependencies. **Can I see my alert history using Tingyun?** You can use the Connector to list your active alert policies and current alerts to manage your monitoring rules and incident response. **Is Tingyun good for monitoring my external API calls?** Yes, it specifically allows your agent to list and monitor calls to external services, helping you spot bottlenecks outside your own stack. **How do I find my Tingyun API Key and Secret?** Log in to your Tingyun console, go to [Account Management] → [API], and you will find your unique API Key and Secret Key there. Ensure you have the necessary permissions enabled. **Can I query specific metric data through this server?** Yes. Use the `get_metrics` tool with the application ID and a comma-separated list of metric names. Your agent will retrieve the data points for the specified metrics. **Is it possible to monitor frontend performance?** Yes! Use the `list_browser_apps` tool to access performance data from Tingyun RUM (Real User Monitoring) for your web and browser applications.