Skip to main content

PagerDuty MCP server

PagerDuty is the leading incident management platform that helps teams detect and respond to infrastructure and application issues with real-time alerting and on-call management. With this MCP server, AI agents can manage incidents, orchestrate on-call schedules, configure escalation policies, and track incident metrics through natural language commands.

Setting up an MCP server

This article covers the standard steps for creating an MCP server in AI Gateway and connecting it to an AI client. The steps are the same for every integration — application-specific details (API credentials, OAuth endpoints, and scopes) are covered in the individual application pages.

Before you begin​

You'll need:

  • Access to AI Gateway with permission to create MCP servers
  • API credentials for the application you're connecting (see the relevant application page for what to collect)

Create an MCP server​

Find the API in the catalog​

  1. Sign in to AI Gateway and select MCP Servers from the left navigation.
  2. Select New MCP Server.
  3. Search for the application you want to connect, then select it from the catalog.

Configure the server​

  1. Enter a Name for your server — something descriptive that identifies both the application and its purpose (for example, "Zendesk Support — Prod").
  2. Enter a Description so your team knows what the server is for.
  3. Set the Timeout value. 30 seconds works for most APIs; increase to 60 seconds for APIs that return large payloads.
  4. Toggle Production mode on if this server will be used in a live workflow.
  5. Select Next.

Configure authentication​

Enter the authentication details for the application. This varies by service — see the Authentication section of the relevant application page for the specific credentials, OAuth URLs, and scopes to use.

Configure security​

  1. Set any Rate limits appropriate for your use case and the API's own limits.
  2. Enable Logging if you want AI Gateway to record requests and responses for auditing.
  3. Select Next.

Deploy​

Review the summary, then select Deploy. AI Gateway provisions the server and provides a server URL you'll use when configuring your AI client.

Connect to an AI client​

Once your server is deployed, you'll need to add it to the AI client your team uses. Select your client for setup instructions:

Tips​

  • You can create multiple MCP servers for the same application — for example, a read-only server for reporting agents and a read-write server for automation workflows.
  • If you're unsure which OAuth scopes to request, start with the minimum read-only set and add write scopes only when needed. Most application pages include scope recommendations.
  • You can edit a server's name, description, timeout, and security settings after deployment without redeploying.

Authentication​

PagerDuty uses OAuth 2.0 for API authentication. Create an OAuth application in PagerDuty to obtain credentials.

  • Authorization URL: https://app.pagerduty.com/oauth/authorize
  • Token URL: https://app.pagerduty.com/oauth/token
  • Client ID: Generated from API application settings
  • Client Secret: Generated from API application settings
  • Scopes: Configure based on needed permissions (incidents, schedules, escalation_policies, users, teams)

Available tools​

The PagerDuty MCP server exposes incident management, on-call scheduling, escalation policy configuration, event ingestion, and analytics APIs.

ToolPurpose
Incident ManagementCreate, update, acknowledge, and resolve incidents; add notes; assign responders; bulk operations
On-Call SchedulingCreate and manage schedules; configure rotations; handle overrides; swap shifts
Escalation PoliciesDefine escalation paths; configure how escalations route to users and teams
Event ProcessingIngest alerts from monitoring tools; correlate related events; automate incident creation
Service ManagementMonitor service health; view dependencies; configure notification rules
Analytics & ReportingTrack MTTR and incident metrics; generate team analytics; analyze on-call workload
User & Team ManagementCreate and manage users; organize teams; configure team-level settings

Tips​

Create policies that match your on-call organization.

Use time-based escalations to account for unavailable team members.

Test escalations thoroughly before production.

Document escalation paths clearly.

Rotate on-call responsibilities fairly.

Account for timezone differences in global teams.

Plan coverage for holidays in advance.

Use overrides for vacation and sick leave.

Configure intelligent grouping to reduce alert noise.

Route alerts to appropriate teams by service.

Adjust thresholds to minimize false positives.

Leverage PagerDuty's alert suppression during maintenance windows.

Use incident notes to document investigation steps.

Assign responders based on expertise.

Configure post-incident reviews for lessons learned.

Track incident timelines.

Connect monitoring tools directly to PagerDuty for automatic incident creation.

Use webhooks to send incident updates back to communication platforms.

Test integrations with test alerts.