pagerduty-automation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

PagerDuty Automation via Rube MCP

通过Rube MCP实现PagerDuty自动化

Automate PagerDuty incident management and operations through Composio's PagerDuty toolkit via Rube MCP.

通过Composio的PagerDuty工具包，借助Rube MCP实现PagerDuty事件管理与运维自动化。

Prerequisites

前提条件

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active PagerDuty connection via
```
RUBE_MANAGE_CONNECTIONS
```
with toolkit
```
pagerduty
```
Always call
```
RUBE_SEARCH_TOOLS
```
first to get current tool schemas

必须已连接Rube MCP（需提供RUBE_SEARCH_TOOLS）
已通过
```
RUBE_MANAGE_CONNECTIONS
```
激活PagerDuty连接，工具包为
```
pagerduty
```
请务必先调用
```
RUBE_SEARCH_TOOLS
```
以获取最新的工具模式

Setup

设置步骤

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_TOOLS
```
responds
Call
```
RUBE_MANAGE_CONNECTIONS
```
with toolkit
```
pagerduty
```
If connection is not ACTIVE, follow the returned auth link to complete PagerDuty authentication
Confirm connection status shows ACTIVE before running any workflows

获取Rube MCP：在客户端配置中添加

https://rube.app/mcp

作为MCP服务器。无需API密钥——只需添加端点即可使用。

确认
```
RUBE_SEARCH_TOOLS
```
可响应，以此验证Rube MCP是否可用
调用
```
RUBE_MANAGE_CONNECTIONS
```
并指定工具包
```
pagerduty
```
若连接状态未显示为ACTIVE，请按照返回的认证链接完成PagerDuty认证
在运行任何工作流之前，确认连接状态为ACTIVE

Core Workflows

核心工作流

1. Manage Incidents

1. 事件管理

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 IDs
```
urgencies[]
```
: Filter by urgency ('high', 'low')
```
title
```
: Incident title (for creation)
```
service
```
: Service object with
```
id
```
and
```
type
```
(for creation)
```
status
```
: New status for update operations

Pitfalls:

Incident creation requires a
```
service
```
object with both
```
id
```
and
```
type: 'service_reference'
```
Status transitions follow: triggered -> acknowledged -> resolved
Cannot transition from resolved back to triggered directly
```
PAGERDUTY_UPDATE_INCIDENT_BY_ID
```
requires the incident ID as a path parameter
Snooze duration is in seconds; the incident re-triggers after the snooze period

适用场景：用户需要创建、更新、确认或解决事件

工具序列：

```
PAGERDUTY_FETCH_INCIDENT_LIST
```
- 按筛选条件列出事件 [必填]

PAGERDUTY_RETRIEVE_INCIDENT_BY_INCIDENT_ID

- 获取特定事件详情 [可选]

```
PAGERDUTY_CREATE_INCIDENT_RECORD
```
- 创建新事件 [可选]
```
PAGERDUTY_UPDATE_INCIDENT_BY_ID
```
- 更新事件状态或分配对象 [可选]
```
PAGERDUTY_POST_INCIDENT_NOTE_USING_ID
```
- 为事件添加备注 [可选]
```
PAGERDUTY_SNOOZE_INCIDENT_BY_DURATION
```
- 将事件暂停指定时长 [可选]

关键参数：

```
statuses[]
```
: 按状态筛选（'triggered', 'acknowledged', 'resolved'）
```
service_ids[]
```
: 按服务ID筛选
```
urgencies[]
```
: 按紧急程度筛选（'high', 'low'）
```
title
```
: 事件标题（用于创建事件）
```
service
```
: 包含
```
id
```
和
```
type
```
的服务对象（用于创建事件）
```
status
```
: 更新操作的新状态

注意事项：

创建事件时，
```
service
```
对象必须同时包含
```
id
```
和
```
type: 'service_reference'
```
状态转换流程：triggered -> acknowledged -> resolved
无法从resolved状态直接转换回triggered状态
```
PAGERDUTY_UPDATE_INCIDENT_BY_ID
```
需要将事件ID作为路径参数
暂停时长以秒为单位；暂停结束后事件将重新触发

2. Inspect Incident Alerts and Analytics

2. 查看事件告警与分析数据

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 ID
```
alert_id
```
: Specific alert ID within the incident
```
statuses[]
```
: 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

适用场景：用户需要查看事件内的告警或分析事件指标

工具序列：

```
PAGERDUTY_GET_ALERTS_BY_INCIDENT_ID
```
- 列出事件的所有告警 [必填]
```
PAGERDUTY_GET_INCIDENT_ALERT_DETAILS
```
- 获取特定告警的详情 [可选]
```
PAGERDUTY_FETCH_INCIDENT_ANALYTICS_BY_ID
```
- 获取事件分析/指标数据 [可选]

关键参数：

```
incident_id
```
: 事件ID
```
alert_id
```
: 事件内的特定告警ID
```
statuses[]
```
: 按状态筛选告警

注意事项：

一个事件可包含多个告警；每个告警有自己的状态
告警ID的作用域为所属事件
分析数据包含响应时间、参与指标和解决时间

3. Manage Services

3. 服务管理

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 name
```
escalation_policy
```
: Escalation policy object with
```
id
```
and
```
type
```
```
alert_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

适用场景：用户需要创建、更新或列出服务

工具序列：

```
PAGERDUTY_RETRIEVE_LIST_OF_SERVICES
```
- 列出所有服务 [必填]
```
PAGERDUTY_RETRIEVE_SERVICE_BY_ID
```
- 获取服务详情 [可选]
```
PAGERDUTY_CREATE_NEW_SERVICE
```
- 创建新的技术服务 [可选]
```
PAGERDUTY_UPDATE_SERVICE_BY_ID
```
- 更新服务配置 [可选]

PAGERDUTY_CREATE_INTEGRATION_FOR_SERVICE

- 为服务添加集成 [可选]

```
PAGERDUTY_CREATE_BUSINESS_SERVICE
```
- 创建业务服务 [可选]
```
PAGERDUTY_UPDATE_BUSINESS_SERVICE_BY_ID
```
- 更新业务服务 [可选]

关键参数：

```
name
```
: 服务名称
```
escalation_policy
```
: 包含
```
id
```
和
```
type
```
的升级策略对象
```
alert_creation
```
: 告警创建模式（'create_alerts_and_incidents' 或 'create_incidents'）
```
status
```
: 服务状态（'active', 'warning', 'critical', 'maintenance', 'disabled'）

注意事项：

创建服务需要已存在的升级策略
业务服务与技术服务不同；它们代表业务层面的分组
服务集成定义了告警的创建方式（邮件、API、事件）
禁用服务将停止该服务的所有事件创建

4. Manage Schedules and On-Call

4. 排班与随叫随到管理

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 identifier
```
time_zone
```
: Schedule timezone (e.g., 'America/New_York')
```
schedule_layers
```
: Array of rotation layer configurations
```
since
```
/
```
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
```
since
```
and
```
until
```
are 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

适用场景：用户需要查看或管理随叫随到排班与轮值

工具序列：

```
PAGERDUTY_GET_SCHEDULES
```
- 列出所有排班 [必填]
```
PAGERDUTY_RETRIEVE_SCHEDULE_BY_ID
```
- 获取特定排班详情 [可选]
```
PAGERDUTY_CREATE_NEW_SCHEDULE_LAYER
```
- 创建新排班 [可选]
```
PAGERDUTY_UPDATE_SCHEDULE_BY_ID
```
- 更新现有排班 [可选]
```
PAGERDUTY_RETRIEVE_ONCALL_LIST
```
- 查看当前随叫随到人员 [可选]

PAGERDUTY_CREATE_SCHEDULE_OVERRIDES_CONFIGURATION

- 创建临时覆盖规则 [可选]

PAGERDUTY_DELETE_SCHEDULE_OVERRIDE_BY_ID

- 删除覆盖规则 [可选]

```
PAGERDUTY_RETRIEVE_USERS_BY_SCHEDULE_ID
```
- 列出排班中的用户 [可选]
```
PAGERDUTY_PREVIEW_SCHEDULE_OBJECT
```
- 保存前预览排班变更 [可选]

关键参数：

```
schedule_id
```
: 排班ID
```
time_zone
```
: 排班时区（例如：'America/New_York'）
```
schedule_layers
```
: 轮值层配置数组
```
since
```
/
```
until
```
: 随叫随到查询的日期范围（ISO 8601格式）
```
override
```
: 包含用户、开始和结束时间的覆盖规则对象

注意事项：

排班层定义了轮值顺序；多个排班层可重叠
覆盖规则为临时规则，优先级高于正常排班
随叫随到查询需要
```
since
```
和
```
until
```
参数来限定时间范围
时区必须是有效的IANA时区字符串
保存复杂排班变更前，请先预览以验证正确性

5. Manage Escalation Policies

5. 升级策略管理

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 name
```
escalation_rules
```
: Array of escalation rule objects
```
num_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_minutes
```
defines how long before escalating to the next level
Setting
```
num_loops
```
to 0 means the policy runs once and stops
Deleting a policy fails if services still reference it

适用场景：用户需要创建或修改升级策略

工具序列：

```
PAGERDUTY_FETCH_ESCALATION_POLICES_LIST
```
- 列出所有升级策略 [必填]
```
PAGERDUTY_GET_ESCALATION_POLICY_BY_ID
```
- 获取策略详情 [可选]
```
PAGERDUTY_CREATE_ESCALATION_POLICY
```
- 创建新策略 [可选]

PAGERDUTY_UPDATE_ESCALATION_POLICY_BY_ID

- 更新现有策略 [可选]

PAGERDUTY_AUDIT_ESCALATION_POLICY_RECORDS

- 查看策略的审计日志 [可选]

关键参数：

```
name
```
: 策略名称
```
escalation_rules
```
: 升级规则对象数组
```
num_loops
```
: 规则循环次数（0表示不循环）
```
escalation_delay_in_minutes
```
: 各升级级别之间的延迟时间（分钟）

注意事项：

每个升级规则至少需要一个目标（用户、排班或团队）
```
escalation_delay_in_minutes
```
定义了升级到下一级别的等待时间
将
```
num_loops
```
设置为0表示策略仅运行一次后停止
若仍有服务引用该策略，则无法删除

6. Manage Teams

6. 团队管理

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 name
```
description
```
: Team description

Pitfalls:

Team names must be unique within the account
Teams are used to scope services, escalation policies, and schedules

适用场景：用户需要创建或管理PagerDuty团队

工具序列：

```
PAGERDUTY_CREATE_NEW_TEAM_WITH_DETAILS
```
- 创建新团队 [必填]

关键参数：

```
name
```
: 团队名称
```
description
```
: 团队描述

注意事项：

团队名称在账户内必须唯一
团队用于限定服务、升级策略和排班的作用域

Common Patterns

常见模式

ID Resolution

ID解析

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

服务名称 -> 服务ID：

1. 调用PAGERDUTY_RETRIEVE_LIST_OF_SERVICES
2. 在响应中按名称查找服务
3. 提取id字段

排班名称 -> 排班ID：

1. 调用PAGERDUTY_GET_SCHEDULES
2. 在响应中按名称查找排班
3. 提取id字段

Incident Lifecycle

事件生命周期

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'

1. 事件触发（通过API、集成或手动创建）
2. 根据升级策略通知随叫随到用户
3. 用户确认 -> 状态: 'acknowledged'
4. 用户解决 -> 状态: 'resolved'

Pagination

分页

PagerDuty uses offset-based pagination
Check response for
```
more
```
boolean field
Use
```
offset
```
and
```
limit
```
parameters
Continue until
```
more
```
is false

PagerDuty使用基于偏移量的分页
检查响应中的
```
more
```
布尔字段
使用
```
offset
```
和
```
limit
```
参数
持续请求直到
```
more
```
为false

Known Pitfalls

已知注意事项

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
```
data
```
or
```
data.data
```
Parse defensively with fallback patterns
Pagination uses
```
offset
```
/
```
limit
```
/
```
more
```
pattern

ID格式：

所有PagerDuty ID均为字母数字字符串（例如：'P1234AB'）
服务引用需要
```
type: 'service_reference'
```
用户引用需要
```
type: 'user_reference'
```

状态转换：

事件：triggered -> acknowledged -> resolved（仅正向转换）
服务：active, warning, critical, maintenance, disabled

速率限制：

PagerDuty API对每个账户实施速率限制
收到429响应时，请实现指数退避机制
批量操作应间隔执行

响应解析：

响应数据可能嵌套在
```
data
```
或
```
data.data
```
下
请使用防御性解析并设置回退模式
分页使用
```
offset
```
/
```
limit
```
/
```
more
```
模式

Quick Reference

快速参考

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

任务	工具标识	关键参数
列出事件	PAGERDUTY_FETCH_INCIDENT_LIST	statuses[], service_ids[]
获取事件详情	PAGERDUTY_RETRIEVE_INCIDENT_BY_INCIDENT_ID	incident_id
创建事件	PAGERDUTY_CREATE_INCIDENT_RECORD	title, service
更新事件	PAGERDUTY_UPDATE_INCIDENT_BY_ID	incident_id, status
添加事件备注	PAGERDUTY_POST_INCIDENT_NOTE_USING_ID	incident_id, content
暂停事件	PAGERDUTY_SNOOZE_INCIDENT_BY_DURATION	incident_id, duration
获取事件告警	PAGERDUTY_GET_ALERTS_BY_INCIDENT_ID	incident_id
事件分析	PAGERDUTY_FETCH_INCIDENT_ANALYTICS_BY_ID	incident_id
列出服务	PAGERDUTY_RETRIEVE_LIST_OF_SERVICES	无
获取服务详情	PAGERDUTY_RETRIEVE_SERVICE_BY_ID	service_id
创建服务	PAGERDUTY_CREATE_NEW_SERVICE	name, escalation_policy
更新服务	PAGERDUTY_UPDATE_SERVICE_BY_ID	service_id
列出排班	PAGERDUTY_GET_SCHEDULES	无
获取排班详情	PAGERDUTY_RETRIEVE_SCHEDULE_BY_ID	schedule_id
获取随叫随到人员	PAGERDUTY_RETRIEVE_ONCALL_LIST	since, until
创建排班覆盖规则	PAGERDUTY_CREATE_SCHEDULE_OVERRIDES_CONFIGURATION	schedule_id
列出升级策略	PAGERDUTY_FETCH_ESCALATION_POLICES_LIST	无
创建升级策略	PAGERDUTY_CREATE_ESCALATION_POLICY	name, escalation_rules
创建团队	PAGERDUTY_CREATE_NEW_TEAM_WITH_DETAILS	name, description