Sign in Book a demo
Back to Tools
Developer Tools OAuth
Build Your Agent View PagerDuty Docs
pagerduty logo

PagerDuty MCP Tools for AI Agents

Let an agent find incidents, inspect activity, check on-call coverage, and acknowledge, resolve, or reassign them.

Available Tools

17 tools available in this integration

Pagerduty.AssignIncident

Reassign an incident to a specific user without changing its status.

Pagerduty.GetEscalationPolicy

Get a single escalation policy by ID.

Pagerduty.GetIncident

Get a single incident by ID.

Pagerduty.GetService

Get a single service by ID.

Pagerduty.GetTeam

Get a single team by ID including members and linked resources.

Pagerduty.ListEscalationPolicies

List escalation policies.

Pagerduty.ListIncidents

List incidents with optional status, urgency, service, team, and time filters.

Pagerduty.ListLogEntries

List log entries (activity feed) showing recent incident events.

Pagerduty.ListOncalls

List on-call entries with optional filters.

Pagerduty.ListSchedules

List schedules.

Pagerduty.ListServices

List services with optional name search.

Pagerduty.ListTeams

List teams.

Pagerduty.ListUsers

List users.

Pagerduty.ReassignIncident

Reassign an incident to a specific user without changing its status.

Pagerduty.SearchUsers

Search users using local fuzzy matching on name/email.

Pagerduty.UpdateIncidentStatus

Update an incident's status (acknowledge, resolve/close, or reopen).

Pagerduty.WhoAmI

Get the authenticated PagerDuty user's profile with contact and notification summaries.

Working directly against the raw API? 374 more tools in the PagerDuty API server →

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find the urgent incidents for the payments service and reassign them to the current on-call engineer." Arcade picks the right PagerDuty tools without guessing incident IDs, service IDs, or user IDs.

Up to 100x fewer tokens

PagerDuty list and search tools return lightweight incident, user, and service metadata by default and fetch full records only when asked, so the agent can act without loading entire incident histories.

Complete the workflow end to end

Find the active incident, inspect its activity, identify the on-call responder, reassign it, and resolve it through one toolkit designed around the complete incident-response task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing PagerDuty

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For PagerDuty, you can implement some of these policies:

Access when tools are listed for a user
  • Hide Pagerduty.UpdateIncidentStatus from agents unless the roles your IDP marks as incident commanders or service owners are active, so an agent cannot resolve or reopen incidents outside its authority.
  • Restrict Pagerduty.ReassignIncident to agents operating under your incident-management role, so an agent cannot move incidents to another responder without the right operational authority.
  • Hide Pagerduty.AssignIncident from agents unless the roles your IDP marks as incident commanders or service owners are active, so an agent cannot redirect an incident to a responder without operational authority.
Pre-execution before each tool call
  • Require human approval before Pagerduty.UpdateIncidentStatus resolves or reopens an incident, so an agent cannot close an active incident or revive a closed one without review.
  • Block Pagerduty.ReassignIncident when the target user is not assigned to the incident's service team, so an agent cannot route an incident to an unrelated responder.
  • Require human approval before Pagerduty.AssignIncident runs, so an agent cannot assign an incident to another responder without review.
Post-execution after the tool returns
  • Redact incident descriptions, response notes, and embedded email addresses from Pagerduty.GetIncident before they reach the model, so private customer or infrastructure details are not exposed in context.
  • Strip personal email addresses and phone numbers from Pagerduty.GetTeam results, leaving team membership and linked resources without private contact details.
  • Redact personal contact details and notification preferences from Pagerduty.WhoAmI before they reach the model, so the agent does not receive private account information it does not need.

How to use PagerDuty with your agent

Connect PagerDuty to your MCP client and follow the setup from authorization to your first incident query.

Your questions, answered

A PagerDuty MCP server exposes PagerDuty operations as structured tools that an AI agent can call through the Model Context Protocol. After a user authorizes their PagerDuty account, the agent can inspect incidents, on-call schedules, services, teams, escalation policies, and perform permitted incident updates.

Arcade's PagerDuty integration is an Arcade-hosted MCP endpoint with per-user OAuth, agent-optimized actions, and runtime controls for approval, redaction, and tool visibility. It gives teams one governed way to reach PagerDuty from supported agents and clients.

Arcade agents can list and inspect incidents, activity logs, on-call entries, schedules, services, teams, users, and escalation policies. They can also search for users, identify the authorized user, reassign incidents, acknowledge or resolve incidents, and reopen them.

PagerDuty actions use the permissions granted through each user's OAuth authorization. Read-only incident and account workflows need read access, while reassigning incidents or changing incident status requires the corresponding write permissions; grant only the access your workflow needs.

Yes. Each user authorizes their own PagerDuty account through OAuth. Actions run under that user's authorization, so the agent can access only the PagerDuty data and actions that user has approved.

Yes. Contextual Access policies can require human approval before consequential PagerDuty actions such as reassigning an incident, acknowledging it, resolving it, or reopening it. The call proceeds only after the policy's conditions have been satisfied.

Arcade proxies PagerDuty API calls and does not persist PagerDuty content as part of normal tool execution. Credentials are brokered and stored encrypted at rest, and the model never receives them.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the user's PagerDuty authorization remains valid. If it is revoked, rotated, or can no longer be refreshed, PagerDuty calls stop until the user reconnects their account.

PagerDuty's API rate limits and account-level quotas still apply to calls made through Arcade. The available details do not specify a separate PagerDuty limit for these actions, so high-volume agents should handle throttling and retries.

Ready to actually ship your agent?

Connect your agent to PagerDuty with managed OAuth, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the PagerDuty Quickstart