NetClaw Adds PagerDuty Integration: AI-Powered Incident Management for Network Engineers

NetClaw now speaks incident management. We’re excited to announce full PagerDuty integration, bringing 4 new skills backed by 70 tools to the NetClaw ecosystem. Network engineers can now manage incidents, on-call schedules, services, and automation workflows through natural language.

Why PagerDuty?

When a network goes down at 3 AM, the last thing you want is to fumble through multiple dashboards. PagerDuty is the industry standard for incident response, and now NetClaw can:

Query active incidents across your infrastructure
Check who’s on-call for any service or escalation policy
Inspect service configurations and dependencies
Manage Event Orchestration rules and automations

The 4 New Skills

1. pagerduty-incidents

Manage the full incident lifecycle through conversation:

Show me all P1 incidents from the last 24 hours

What's the status of INC-12345?

List incidents affecting the core-network service

Who acknowledged the latest database incident?

Tools included: list_incidents, get_incident, create_incident, update_incident, merge_incidents, snooze_incident, list_incident_notes, create_incident_note, list_incident_alerts, manage_incident_alerts, list_responder_requests, list_notification_subscribers, list_incident_workflows

2. pagerduty-oncall

Never wonder who to contact during an outage:

Who's on-call for the network-operations team right now?

Show the on-call schedule for next week

List all escalation policies for infrastructure services

What's the rotation schedule for the NOC team?

Tools included: list_oncalls, list_schedules, get_schedule, list_schedule_users, list_escalation_policies, get_escalation_policy

3. pagerduty-services

Understand your service topology and health:

List all services in the network domain

Show dependencies for the edge-router service

What integrations does the firewall-alerts service have?

Get details on service SVC-ABC123

Tools included: list_services, get_service, list_service_integrations, list_service_dependencies, list_business_services, get_business_service, get_impacted_business_services, get_service_standards, get_standards_scores

4. pagerduty-orchestration

Automate incident response workflows:

List all Event Orchestration rules

Show the global orchestration configuration

What automation rules trigger for network alerts?

Get details on orchestration ORCH-12345

Tools included: list_event_orchestrations, get_event_orchestration, get_global_orchestration, list_automation_actions, get_automation_action, list_automation_runners

Quick Setup

1. Get Your API Key

Navigate to My Profile → User Settings → Create API User Token in PagerDuty.

2. Configure Environment

export PAGERDUTY_USER_API_KEY="your-api-key"
export PAGERDUTY_API_HOST="https://api.pagerduty.com"  # Optional

3. Start Using

netclaw: Show me all active P1 and P2 incidents

netclaw: Who's on-call for infrastructure right now?

netclaw: Create a P3 incident for "BGP session flapping on core-rtr-01"

Integration Architecture

NetClaw uses the official pagerduty-mcp package with write tools enabled:

{
  "pagerduty-mcp": {
    "command": "uvx",
    "args": ["pagerduty-mcp", "--enable-write-tools"],
    "env": {
      "PAGERDUTY_USER_API_KEY": "${PAGERDUTY_USER_API_KEY}"
    }
  }
}

The --enable-write-tools flag allows NetClaw to create incidents, add notes, and manage alerts—not just read data.

Real-World Workflow

Imagine this scenario:

Detection: Your monitoring detects BGP session drops
Query: "Show me active network incidents"
Context: "Who’s on-call for network-operations?"
Action: "Create a P2 incident for BGP instability on core-rtr-01 and assign to the on-call engineer"
Update: "Add a note to INC-12345: Root cause identified as fiber cut on provider link"
Resolution: "Resolve INC-12345 with resolution note: Provider restored connectivity"

All through natural language. No dashboard switching. No context loss.

What’s Next

This PagerDuty integration is part of a larger wave of observability and incident management capabilities coming to NetClaw. Combined with our existing integrations (Grafana, Prometheus, Datadog), network engineers now have a complete incident lifecycle toolkit at their fingertips.

NetClaw now supports 68 MCP servers with 124 skills. The network operations center is evolving, and natural language is the new CLI.

Ready to try it? Check out the NetClaw GitHub repository for installation instructions.

0 Shares