PagerDuty for Claude Code brings production context directly into your development workflow. This risk scoring plugin analyzes uncommitted code changes against your incident history. When developers run /risk-score, Claude correlates their git diff with 90 days of PagerDuty incident data—identifying high-risk file types, change scope, and overlap with past incident areas—then delivers a risk score with actionable recommendations before code is committed. Learn more here .

Get full visibility and control over the memory artifacts SRE Agent maintains for each PagerDuty service. With this API, teams can view, edit, or redact information to ensure accurate, compliant, and context‑aware insights that drive faster, more precise incident resolution. Learn more .

Incident Workflows enable you to automate your incident response processes. These workflows can be triggered automatically through Conditional Triggers. The product limits for Conditional Triggers have been increased so that 100 Conditional Triggers (previously 20) can be associated with a given Technical Service and 50 Incident Workflows (previously 10) can have Conditional Triggers that apply to all technical services. Full details on Incident Workflows and Conditional Triggers can be found here.

PagerDuty is launching an MCP plug-in for Cursor. This plug-in allows Cursor to pull in PagerDuty data such as on-call lookups, service management, and more. Not only does this allow developers to resolve incidents faster, it can also help you prevent incidents in the first place, with the crucial information about your operational posture and historical context you need to make the best choice ahead of deploying new code.

Now available in Microsoft Teams, the SRE Agent automatically detects, triages, and diagnoses incidents, and recommends remediation steps. It also recalls incident history to generate playbooks that help prevent recurring issues. The result: shorter incidents, faster fixes, and fewer interruptions. Sign up for Early Access.

Connect PagerDuty to AWS using secure, credential-less authentication that eliminates the need for long-lived access keys. Automate AWS remediation actions through Incident Workflows with enterprise-grade security using AWS-recommended IAM role assumption, reducing the risk of major operational failures while accelerating incident resolution. Available now for all Incident Workflows customers - get started with the setup guide here.

Access a live, unified view of incidents across services. Quickly identify blast radius, service impact, and detect anomalies by visualizing incidents across time. Service Health Visualization enables faster decision-making and triage at scale by bridging the gap between observability and incident response. Now you can focus troubleshooting in one place with customizable filtering and contextual overlays. Early access available to all customers who have Operations Console.

This feature analyzes configured Incident Workflows and evaluates them against the real-time context of each incident. The SRE Agent then intelligently recommends the most relevant workflow to run, ensuring faster, more precise, and context-aware incident response. Sign up for Early Access.

Japanese conversations with SRE Agent in Slack can be enabled via user voice language settings from PagerDuty or via automatic language detection from Slack messages.

The latest MCP enhancements provide richer incident and alert context through expanded capabilities. Engineers can now:

• Retrieve detailed incident log entries with get_incident_log_entries
• Access additional incident data using enhanced query parameters in get_incident
• Inspect alert details using list_alerts_from_incident and get_alert_from_incident

Additionally, list_users now supports including contact method data, enabling responders to reach the right person faster. Learn more about PagerDuty MCP here .