pagerduty-automation
Automate PagerDuty tasks via Rube MCP (Composio): manage incidents, services, schedules, escalation policies, and on-call rotations. Always search tools first for current schemas.
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- pagerduty-automation
- category
- devops
- requires
- { "mcp": [ "rube" ] }
- description
- Automate PagerDuty tasks via Rube MCP (Composio): manage incidents, services, schedules, escalation policies, and on-call rotations. Always search tools first for current schemas.
03 SKILL.md 正文
PagerDuty Automation via Rube MCP
Automate PagerDuty incident management and operations through Composio's PagerDuty toolkit via Rube MCP.
Toolkit docs: composio.dev/toolkits/pagerduty
Prerequisites
- Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
- Active PagerDuty connection via
RUBE_MANAGE_CONNECTIONSwith toolkitpagerduty - Always call
RUBE_SEARCH_TOOLSfirst to get current tool schemas
Setup
Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.
- Verify Rube MCP is available by confirming
RUBE_SEARCH_TOOLSresponds - Call
RUBE_MANAGE_CONNECTIONSwith toolkitpagerduty - If connection is not ACTIVE, follow the returned auth link to complete PagerDuty authentication
- Confirm connection status shows ACTIVE before running any workflows
Core Workflows
1. Manage Incidents
When to use: User wants to create, update, acknowledge, or resolve incidents
Tool sequence:
PAGERDUTY_FETCH_INCIDENT_LIST- List incidents with filters [Required]PAGERDUTY_RETRIEVE_INCIDENT_BY_INCIDENT_ID- Get specific incident details [Optional]PAGERDUTY_CREATE_INCIDENT_RECORD- Create a new incident [Optional]PAGERDUTY_UPDATE_INCIDENT_BY_ID- Update incident status or assignment [Optional]PAGERDUTY_POST_INCIDENT_NOTE_USING_ID- Add a note to an incident [Optional]PAGERDUTY_SNOOZE_INCIDENT_BY_DURATION- Snooze an incident for a period [Optional]
Key parameters:
statuses[]: Filter by status ('triggered', 'acknowledged', 'resolved')service_ids[]: Filter by service IDsurgencies[]: Filter by urgency ('high', 'low')title: Incident title (for creation)service: Service object withidandtype(for creation)status: New status for update operations
Pitfalls:
- Incident creation requires a
serviceobject with bothidandtype: 'service_reference' - Status transitions follow: triggered -> acknowledged -> resolved
- Cannot transition from resolved back to triggered directly
PAGERDUTY_UPDATE_INCIDENT_BY_IDrequires the incident ID as a path parameter- Snooze duration is in seconds; the incident re-triggers after the snooze period
2. Inspect Incident Alerts and Analytics
When to use: User wants to review alerts within an incident or analyze incident metrics
Tool sequence:
PAGERDUTY_GET_ALERTS_BY_INCIDENT_ID- List alerts for an incident [Required]PAGERDUTY_GET_INCIDENT_ALERT_DETAILS- Get details of a specific alert [Optional]PAGERDUTY_FETCH_INCIDENT_ANALYTICS_BY_ID- Get incident analytics/metrics [Optional]
Key parameters:
incident_id: The incident IDalert_id: Specific alert ID within the incidentstatuses[]: Filter alerts by status
Pitfalls:
- An incident can have multiple alerts; each alert has its own status
- Alert IDs are scoped to the incident
- Analytics data includes response times, engagement metrics, and resolution times
3. Manage Services
When to use: User wants to create, update, or list services
Tool sequence:
PAGERDUTY_RETRIEVE_LIST_OF_SERVICES- List all services [Required]PAGERDUTY_RETRIEVE_SERVICE_BY_ID- Get service details [Optional]PAGERDUTY_CREATE_NEW_SERVICE- Create a new technical service [Optional]PAGERDUTY_UPDATE_SERVICE_BY_ID- Update service configuration [Optional]PAGERDUTY_CREATE_INTEGRATION_FOR_SERVICE- Add an integration to a service [Optional]PAGERDUTY_CREATE_BUSINESS_SERVICE- Create a business service [Optional]PAGERDUTY_UPDATE_BUSINESS_SERVICE_BY_ID- Update a business service [Optional]
Key parameters:
name: Service nameescalation_policy: Escalation policy object withidandtypealert_creation: Alert creation mode ('create_alerts_and_incidents' or 'create_incidents')status: Service status ('active', 'warning', 'critical', 'maintenance', 'disabled')
Pitfalls:
- Creating a service requires an existing escalation policy
- Business services are different from technical services; they represent business-level groupings
- Service integrations define how alerts are created (email, API, events)
- Disabling a service stops all incident creation for that service
4. Manage Schedules and On-Call
When to use: User wants to view or manage on-call schedules and rotations
Tool sequence:
PAGERDUTY_GET_SCHEDULES- List all schedules [Required]PAGERDUTY_RETRIEVE_SCHEDULE_BY_ID- Get specific schedule details [Optional]PAGERDUTY_CREATE_NEW_SCHEDULE_LAYER- Create a new schedule [Optional]PAGERDUTY_UPDATE_SCHEDULE_BY_ID- Update an existing schedule [Optional]PAGERDUTY_RETRIEVE_ONCALL_LIST- View who is currently on-call [Optional]PAGERDUTY_CREATE_SCHEDULE_OVERRIDES_CONFIGURATION- Create temporary overrides [Optional]PAGERDUTY_DELETE_SCHEDULE_OVERRIDE_BY_ID- Remove an override [Optional]PAGERDUTY_RETRIEVE_USERS_BY_SCHEDULE_ID- List users in a schedule [Optional]PAGERDUTY_PREVIEW_SCHEDULE_OBJECT- Preview schedule changes before saving [Optional]
Key parameters:
schedule_id: Schedule identifiertime_zone: Schedule timezone (e.g., 'America/New_York')schedule_layers: Array of rotation layer configurationssince/until: Date range for on-call queries (ISO 8601)override: Override object with user, start, and end times
Pitfalls:
- Schedule layers define rotation order; multiple layers can overlap
- Overrides are temporary and take precedence over the normal schedule
sinceanduntilare required for on-call queries to scope the time range- Time zones must be valid IANA timezone strings
- Preview before saving complex schedule changes to verify correctness
5. Manage Escalation Policies
When to use: User wants to create or modify escalation policies
Tool sequence:
PAGERDUTY_FETCH_ESCALATION_POLICES_LIST- List all escalation policies [Required]PAGERDUTY_GET_ESCALATION_POLICY_BY_ID- Get policy details [Optional]PAGERDUTY_CREATE_ESCALATION_POLICY- Create a new policy [Optional]PAGERDUTY_UPDATE_ESCALATION_POLICY_BY_ID- Update an existing policy [Optional]PAGERDUTY_AUDIT_ESCALATION_POLICY_RECORDS- View audit trail for a policy [Optional]
Key parameters:
name: Policy nameescalation_rules: Array of escalation rule objectsnum_loops: Number of times to loop through rules before stopping (0 = no loop)escalation_delay_in_minutes: Delay between escalation levels
Pitfalls:
- Each escalation rule requires at least one target (user, schedule, or team)
escalation_delay_in_minutesdefines how long before escalating to the next level- Setting
num_loopsto 0 means the policy runs once and stops - Deleting a policy fails if services still reference it
6. Manage Teams
When to use: User wants to create or manage PagerDuty teams
Tool sequence:
PAGERDUTY_CREATE_NEW_TEAM_WITH_DETAILS- Create a new team [Required]
Key parameters:
name: Team namedescription: Team description
Pitfalls:
- Team names must be unique within the account
- Teams are used to scope services, escalation policies, and schedules
Common Patterns
ID Resolution
Service name -> Service ID:
1. Call PAGERDUTY_RETRIEVE_LIST_OF_SERVICES
2. Find service by name in response
3. Extract id field
Schedule name -> Schedule ID:
1. Call PAGERDUTY_GET_SCHEDULES
2. Find schedule by name in response
3. Extract id field
Incident Lifecycle
1. Incident triggered (via API, integration, or manual creation)
2. On-call user notified per escalation policy
3. User acknowledges -> status: 'acknowledged'
4. User resolves -> status: 'resolved'
Pagination
- PagerDuty uses offset-based pagination
- Check response for
moreboolean field - Use
offsetandlimitparameters - Continue until
moreis false
Known Pitfalls
ID Formats:
- All PagerDuty IDs are alphanumeric strings (e.g., 'P1234AB')
- Service references require
type: 'service_reference' - User references require
type: 'user_reference'
Status Transitions:
- Incidents: triggered -> acknowledged -> resolved (forward only)
- Services: active, warning, critical, maintenance, disabled
Rate Limits:
- PagerDuty API enforces rate limits per account
- Implement exponential backoff on 429 responses
- Bulk operations should be spaced out
Response Parsing:
- Response data may be nested under
dataordata.data - Parse defensively with fallback patterns
- Pagination uses
offset/limit/morepattern
Quick Reference
| Task | Tool Slug | Key Params |
|---|---|---|
| List incidents | PAGERDUTY_FETCH_INCIDENT_LIST | statuses[], service_ids[] |
| Get incident | PAGERDUTY_RETRIEVE_INCIDENT_BY_INCIDENT_ID | incident_id |
| Create incident | PAGERDUTY_CREATE_INCIDENT_RECORD | title, service |
| Update incident | PAGERDUTY_UPDATE_INCIDENT_BY_ID | incident_id, status |
| Add incident note | PAGERDUTY_POST_INCIDENT_NOTE_USING_ID | incident_id, content |
| Snooze incident | PAGERDUTY_SNOOZE_INCIDENT_BY_DURATION | incident_id, duration |
| Get incident alerts | PAGERDUTY_GET_ALERTS_BY_INCIDENT_ID | incident_id |
| Incident analytics | PAGERDUTY_FETCH_INCIDENT_ANALYTICS_BY_ID | incident_id |
| List services | PAGERDUTY_RETRIEVE_LIST_OF_SERVICES | (none) |
| Get service | PAGERDUTY_RETRIEVE_SERVICE_BY_ID | service_id |
| Create service | PAGERDUTY_CREATE_NEW_SERVICE | name, escalation_policy |
| Update service | PAGERDUTY_UPDATE_SERVICE_BY_ID | service_id |
| List schedules | PAGERDUTY_GET_SCHEDULES | (none) |
| Get schedule | PAGERDUTY_RETRIEVE_SCHEDULE_BY_ID | schedule_id |
| Get on-call | PAGERDUTY_RETRIEVE_ONCALL_LIST | since, until |
| Create schedule override | PAGERDUTY_CREATE_SCHEDULE_OVERRIDES_CONFIGURATION | schedule_id |
| List escalation policies | PAGERDUTY_FETCH_ESCALATION_POLICES_LIST | (none) |
| Create escalation policy | PAGERDUTY_CREATE_ESCALATION_POLICY | name, escalation_rules |
| Create team | PAGERDUTY_CREATE_NEW_TEAM_WITH_DETAILS | name, description |
Powered by Composio
04 同仓库更多 Skills
vercel-sandbox
Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.
slack
Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include "check my Slack", "what channels have unreads", "send a message to", "search Slack for", "extract from Slack", "find who said", or any task requiring programmatic Slack interaction.
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include "automate Slack app", "control VS Code", "interact with Discord app", "test this Electron app", "connect to desktop app", or any task requiring automation of a native Electron application.
dogfood
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", "switch to --preset", and for building a design system or applying a DESIGN.md or brand spec to shadcn/ui.