# PagerDuty MCP for AI Agents AI Agent Connect > PagerDuty MCP. Manage incidents, services, on-call schedules, and escalation policies from any AI agent. Trigger, acknowledge, and resolve alerts without leaving your workspace. ## Overview - **Category:** industry-titans - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_UeCWwWxqx7aZZue1T0HK7vi7AgO8v9VtsWaLEvhs/ai-agent-connect - **Tags:** incident-management, on-call-scheduling, alerting, service-monitoring, escalation-policy, devops ## Description This Connector lets you take control of your PagerDuty incident management through a simple conversation with your AI agent. You can pull up active alerts, see who's currently on-call, or get the full configuration of a monitored service without ever opening a new browser tab. It handles the repetitive tasks of looking up user profiles, listing schedules, and checking escalation policies so you can stay focused on fixing the actual problem. Because it's part of the Vinkius catalog, you can get it running in minutes and start using it across any of your favorite AI clients. It turns your AI into a functional dashboard that responds to your specific commands for triaging and resolving production issues. Instead of hunting through nested menus while a production system is down, you get a direct way to query your status. You can ask your agent to summarize the current situation, find the right person to contact, or update an incident's status with a single command. This takes the friction out of your response workflow and lets you handle high-pressure situations with much less overhead. It's about getting the information you need exactly when you need it, without the constant context switching between your terminal and your management dashboard. ## Tools ### list_schedules List every on-call rotation schedule in your account. You can use this to see coverage windows and handoff times. ### list_services See a list of every monitored service in your account. It's the fastest way to browse your entire service inventory. ### list_users Get a list of all users in your PagerDuty account. Use this for auditing your team members or checking permissions. ### update_incident Change an incident's status to acknowledged, resolved, or escalated. This allows you to manage the lifecycle of an alert programmatically. ### create_incident Create a new incident on a specific service. You just need to provide the service ID, title, and your user email. ### get_incident Pull up all the details for a specific incident. This is useful for seeing the full history and current status of an alert. ### get_service View the configuration of a specific service. It shows you the integrations, health status, and other settings. ### get_user Pull the profile for a specific user. You can see their contact methods and notification rules in one place. ### list_escalation_policies See all the escalation chains for your teams. It helps you understand how incidents route through different groups. ### list_incidents Pull a list of all incidents across your services. You can even filter them by status like triggered or acknowledged. ### list_oncalls See who is currently on-call across all your schedules. This helps you quickly identify the right person to contact. ## Prompt Examples **Prompt:** ``` Show me all triggered incidents right now. ``` **Response:** ``` There are 3 triggered incidents: | ID | Status | Service | Title | | --- | --- | --- | --- | | **P8K2LMN** | 🔴 Triggered | Production API | Database connection pool exhausted | | **P3J9FGH** | 🔴 Triggered | CDN Edge | SSL certificate expires in 24h | | **P1A4BCD** | 🟡 Warning | Background Jobs | High memory usage on worker-03 | Would you like me to acknowledge any of these? ``` **Prompt:** ``` Who is on-call for the Platform team right now? ``` **Response:** ``` Current on-call for Platform: - **Level 1**: sarah.chen@company.com (until Apr 7, 9:00 AM UTC) - **Level 2**: marcus.ops@company.com (until Apr 14, 9:00 AM UTC) **Escalation Policy**: Platform Critical (30 min timeout per level). ``` **Prompt:** ``` Acknowledge incident P8K2LMN and show me the service details. ``` **Response:** ``` ✅ Incident **P8K2LMN** acknowledged successfully. **Service: Production API** - **Status**: Active (Critical) - **Escalation**: Platform Critical (3 levels) - **Integrations**: Datadog, Sentry, Slack - **Auto-resolve**: 4 hours Would you like me to investigate the root cause or resolve this incident? ``` ## Capabilities ### Acknowledge and resolve incidents Update the status of active alerts to move them through your workflow. ### List all triggered alerts Get a full view of every active incident across your services instantly. ### Identify who is currently on-call See exactly who is responsible for active alerts across all schedules. ### Browse all monitored services Inspect the health and configuration of every service in your account. ### Inspect escalation policy chains Understand how alerts route through your teams and who gets notified. ### Retrieve specific user profiles Get contact methods and notification rules for any team member. ## Use Cases ### Emergency Triage An SRE asks for all triggered incidents and then acknowledges the most critical one to start the fix. ### Shift Handover A manager asks who is on-call for the Platform team to see who needs to be looped in during a shift change. ### Service Auditing A DevOps lead lists all services to check if a new integration is active and correctly configured. ### Incident Resolution An engineer gets a service's details and then resolves the incident once the fix is live in production. ## Benefits - Stay in your editor while managing alerts. Use list_incidents to see what needs attention without leaving your workspace. - Acknowledge production issues instantly. Use update_incident to claim an alert in seconds through your AI client. - Identify the right contact person quickly. Use list_oncalls to see who's active across all your schedules. - Check service health on demand. Use get_service to see integration details and status without clicking through menus. - Audit your team members easily. Use list_users and get_user to see notification rules and contact info. - Map out your alert routing. Use list_escalation_policies to see exactly how incidents move through your teams. ## How It Works The bottom line is you get a direct line to your incident management platform inside your favorite AI client. 1. Subscribe to the PagerDuty MCP on Vinkius. 2. Add your PagerDuty REST API Key to the configuration. 3. Ask your AI agent to list incidents or check on-call schedules. ## Frequently Asked Questions **Can I use PagerDuty MCP to acknowledge alerts?** Yes, you can acknowledge, resolve, or escalate incidents directly through your AI client. This helps you manage the alert lifecycle without leaving your current workspace. **Does PagerDuty MCP show who is on-call?** Yes, you can see who is currently on-call across all your schedules. It's a fast way to find the right person to contact during an outage. **How do I connect PagerDuty to my AI agent?** You just need to subscribe to this Connector on Vinkius and add your PagerDuty REST API Key from your account settings. Once connected, your agent can access your data. **Can I see my escalation policies?** Yes, you can list all escalation policies to see how incidents route through your teams. This gives you a clear picture of your alert routing. **Is PagerDuty MCP good for SRE teams?** Yes, it's designed for SREs and DevOps teams who need to triage and resolve incidents quickly. It helps reduce the time spent on manual dashboard navigation. **Can I create new incidents with this?** Yes, you can create new incidents on specific services by providing the title and your user email. This makes it easy to log new issues as they arise. **Can I see my service configurations?** Yes, you can view the detailed configuration and health status of any monitored service. This is helpful for checking integrations and other settings. **Can I acknowledge and resolve incidents directly from my AI agent?** Yes! Use the `update_incident` tool with the incident ID and your PagerDuty email. Set status to `acknowledged` or `resolved` to change the incident state instantly without opening the PagerDuty dashboard. **How do I find out who is on-call right now?** Run the `list_oncalls` tool. It returns every user currently on-call across all schedules and escalation levels, showing their name, escalation policy, and coverage window. **Can I create incidents programmatically for testing or escalation?** Absolutely. Use `create_incident` with your PagerDuty email, the target service ID, a descriptive title, and optionally set urgency to `high` or `low`. The incident will immediately trigger according to the service's escalation policy.