PagerDuty helps teams respond to incidents quickly so services stay reliable. This integration lets you pull incident data, manage on-call schedules, and manage real-time alerts directly inside your Gumloop workflows.
Get instant access to every incident, service, and on-call schedule in your PagerDuty account so you can automate response workflows.

What is PagerDuty MCP?

A PagerDuty MCP node gives Gumloop’s AI direct, conversational access to the PagerDuty API. Provide a plain-language prompt, and the node returns structured data you can pass to any other node in your workflow.

What Can It Do for You?

  • Retrieve current incidents, services, and on-call rotations in seconds
  • Create or update schedules automatically to keep coverage up to date
  • Pull detailed user information for routing alerts or escalations
  • List notifications and on-call entries to analyze responsiveness

Available Tools

ToolWhat It DoesExample Use
Get UserFetch details for an existing PagerDuty user”Using user email, get user details and return name, id, and role”
List IncidentsList incidents in your PagerDuty account”List open incidents since start date and return incident id, title, and status”
List ServicesRetrieve all services configured in PagerDuty”List services and return name, id, and escalation_policy”
List SchedulesGet all on-call schedules”List schedules and return schedule id, name, and time_zone”
Create ScheduleCreate a new on-call schedule”Create schedule named schedule name starting start date in time zone and return schedule id”
Get ScheduleGet details of an existing schedule”Using schedule id, get schedule details and return name, time_zone, and users”
Delete ScheduleRemove an on-call schedule”Delete schedule with schedule id and return confirmation”
List OncallsList current on-call entries”List on-call entries for schedule id and return user name, start, and end times”
List NotificationsList recent PagerDuty notifications”List notifications for user id within the last hours hours and return type and created_at”

How to Use

1

Create Your PagerDuty MCP Node

Go to your node library, search for PagerDuty, and click “Create a node with AI”
2

Add Your Prompt

Drag the PagerDuty MCP node to your canvas and add your prompt in the text box.
3

Test Your Node

Run the node to see the results. If it works as expected, you’re all set. If you need tweaks, check the troubleshooting tips below.
4

Save and Reuse

Once your PagerDuty MCP node is working, save it to your library. You can now use this customized node in any workflow.

Example Prompts

Here are some prompts that work well with PagerDuty MCP: Incident Overview
List incidents with priority `priority level` that started after `start date` and return incident id, title, priority, and status as structured data
On-Call Coverage
List on-call entries for schedule `schedule id` and return user names and shift start/end times as structured data
Schedule Creation
Create a new on-call schedule called `schedule name` starting `start date` ending `end date` in `time zone` and return schedule id and url as structured data
User Lookup
Using `user email`, get user details and return user id, name, and time_zone as structured data
Start with a clear, single action (like “list incidents” or “create schedule”) before chaining multiple nodes together. This keeps workflows fast and easy to debug.

Troubleshooting

If your PagerDuty MCP node isn’t working as expected, try these best practices:

Keep Prompts Simple and Specific

  • Good: “List on-call entries for schedule id and return user names and start times”
  • Bad: “List on-call entries for schedule id, create a new schedule for next week, and email it to managers”
For better results, focus each prompt on one action. PagerDuty MCP works best with focused, single-action prompts.

Match What PagerDuty Can Do

  • Good: “Create an on-call schedule named schedule name starting start date with timezone time zone
  • Bad: “Create an on-call schedule and send a Slack message in the same prompt”
PagerDuty MCP excels at incident management and scheduling. For communication tasks like Slack messages, combine it with the Slack Message Sender node.

Break Complex Tasks Into Steps

Instead of trying to do everything in one prompt (which might cause timeouts or incomplete responses):
Search for all incidents with priority `priority level`, find on-call users, create a schedule override, and send email notifications with `message body`
Break this into smaller, focused nodes that each handle one task:
1

Step 1: Get Incidents

List incidents with priority priority level and return incident ids
2

Step 2: Find On-Call Users

Using incident ids, list on-call entries and return user ids and user emails
3

Step 3: Send Notifications via a Gmail Sender Node

Using Using the user emails from the previous node, draft email notifications and send via the 'Gmail Sender' node
In your workflow, connect these nodes sequentially. The incident ids output from Step 1 become the input for Step 2, and the user emails from Step 2 feed into Step 3.

Focus on Data Retrieval

PagerDuty MCP is great at getting information from PagerDuty. For analysis or content creation, connect it to other nodes. Example:
  • Good prompt: “List services and return name, id, and escalation_policy”
  • Bad prompt: “List services, analyze their escalation policies, and draft a report”
Use PagerDuty MCP for retrieval, then pass structured data to Ask AI for analysis and reporting.

Troubleshooting Node Creation

Need More Help?