Rootly connector for AI agents

Tools your incident agent reaches for on Rootly, scoped per user.

CALL ANY TOOL

110 tools for incident management in Rootly: create and resolve incidents, handle alerts, read on-call schedules and shifts, update retrospectives, and post status page events.

rootly_acknowledge_alert

Acknowledge alert

Acknowledge an alert. Returns the alert record with id, type and attributes (short_id, noise, source, status, summary, description). Use it to apply this state change to an existing record by id.

Parameters

Name

Type

Required

Description

string

Required

The UUID or slug of the target record, as returned by the matching list tool. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

actor

object

Optional

The user to record as performing this action. Only available when actor attribution is enabled for the organization; otherwise it is ignored. Only supported with Global and Team API keys; with a Team API key the user must belong to one of the key's teams. When omitted or null, the action is attributed to the API key. Otherwise provide either `email` or `user_id`, not both. Provide as a JSON object. Example: {"key": "value"}

rootly_add_incident_subscribers

Add incident subscribers

rootly_cancel_incident

Cancel incident

rootly_create_alert

Create alert

Create an alert. Returns the alert record with id, type and attributes (short_id, noise, source, status, summary, description). Use it to add a new record; use the matching update tool to change an existing one.

Parameters

Name

Type

Required

Description

summary

string

Required

The summary of the alert. Example: Elevated p99 latency on the checkout API.

actor

object

Optional

alert_field_values_attributes

array

Optional

Custom alert field values to create with the alert. Example: [{"key": "value"}]

alert_urgency_id

string

Optional

The ID of the alert urgency. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

data

object

Optional

Additional data. Provide as a JSON object. Example: {"key": "value"}

deduplication_key

string

Optional

Alerts sharing the same deduplication key are treated as a single alert. Example: OPS-123.

description

string

Optional

The description of the alert. Example: Elevated p99 latency on the checkout API.

ended_at

string

Optional

Alert end datetime. Example: 2025-01-15T14:30:00Z.

environment_ids

array

Optional

The Environment IDs to attach to the alert. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

external_id

string

Optional

External ID. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

external_url

string

Optional

External Url. Example: https://example.com/runbook.

functionality_ids

array

Optional

The Functionality IDs to attach to the alert. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

group_ids

array

Optional

The Group IDs to attach to the alert. If your organization has On-Call enabled and your notification target is a Group. This field will be automatically set for you. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

labels

array

Optional

The labels value. Example: [{"key": "value"}]

noise

string

Optional

Whether the alert is marked as noise. One of: noise, not_noise. Example: noise. One of: `noise`, `not_noise`.

notification_target_id

string

Optional

Only available for organizations with Rootly On-Call enabled. The _identifier_ of the notification target object. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

notification_target_type

string

Optional

Only available for organizations with Rootly On-Call enabled. Can be one of Group, Service, EscalationPolicy, Functionality, User. Please contact support if you encounter issues using `Functionality` as a notification target type. One of: User, Group, EscalationPolicy, Service, Functionality. Example: User. One of: `User`, `Group`, `EscalationPolicy`, `Service`, `Functionality`.

notification_targets

array

Optional

Only available for organizations with Rootly On-Call enabled. Page multiple destinations (any combination of Group, Service, EscalationPolicy, Functionality, or User) in a single request. `Functionality` targets require the `enable_paging_functionalities` feature; a request that includes one while it is disabled is rejected. Applies to alert creation only. When provided, this takes precedence over the singular `notification_target_type` / `notification_target_id` fields. Example: [{"key": "value"}]

service_ids

array

Optional

The Service IDs to attach to the alert. If your organization has On-Call enabled and your notification target is a Service. This field will be automatically set for you. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

source

string

Optional

Deprecated. Accepted for backwards compatibility; new clients should omit. Defaults to `api`. Example: Example source.

started_at

string

Optional

Alert start datetime. Example: 2025-01-15T14:30:00Z.

status

string

Optional

Only available for organizations with Rootly On-Call enabled. Can be one of open, triggered. One of: open, triggered. Example: open. One of: `open`, `triggered`.

rootly_create_incident

Create incident

Create an incident. Returns the incident record with id, type and attributes (sequential_id, title, kind, slug, parent_incident_id, duplicate_incident_id). Use it to add a new record; use the matching update tool to change an existing one.

Parameters

Name

Type

Required

Description

acknowledged_at

string

Optional

Date of acknowledgment. Example: 2025-01-15T14:30:00Z.

alert_ids

array

Optional

The Alert IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

cancelled_at

string

Optional

Date of cancellation. Example: 2025-01-15T14:30:00Z.

cause_ids

array

Optional

The Cause IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

closed_at

string

Optional

Date of closure. Example: 2025-01-15T14:30:00Z.

detected_at

string

Optional

Date of detection. Example: 2025-01-15T14:30:00Z.

duplicate_incident_id

string

Optional

ID of duplicated incident. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

environment_ids

array

Optional

The Environment IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

functionality_ids

array

Optional

The Functionality IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

google_drive_parent_id

string

Optional

Google Drive parent folder ID. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

google_drive_url

string

Optional

Google Drive URL. Example: https://example.com/runbook.

group_ids

array

Optional

The Team IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

in_triage_at

string

Optional

Date of triage. Example: 2025-01-15T14:30:00Z.

incident_type_ids

array

Optional

The Incident Type IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

jira_issue_id

string

Optional

Jira issue ID. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

jira_issue_key

string

Optional

Jira issue key. Example: OPS-123.

jira_issue_url

string

Optional

Jira issue URL. Example: https://example.com/runbook.

kind

string

Optional

The kind of the incident. One of: test, test_sub, example, example_sub, normal, normal_sub, backfilled, scheduled, scheduled_sub. Example: test. One of: `test`, `test_sub`, `example`, `example_sub`, `normal`, `normal_sub`, `backfilled`, `scheduled`, `scheduled_sub`.

labels

object

Optional

Labels to attach to the incidents. eg: {"platform":"osx", "version": "1.29"}. Provide as a JSON object. Example: {"key": "value"}

linear_issue_id

string

Optional

Linear issue ID. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

linear_issue_key

string

Optional

Linear issue key. Example: OPS-123.

linear_issue_url

string

Optional

Linear issue URL. Example: https://example.com/runbook.

mitigated_at

string

Optional

Date of mitigation. Example: 2025-01-15T14:30:00Z.

muted_service_ids

array

Optional

The Service IDs to mute alerts for during maintenance. Alerts for these services will still be triggered and attached to the incident, but won't page responders. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

notify_emails

array

Optional

Emails you want to notify. Example: ["example"]

parent_incident_id

string

Optional

ID of parent incident. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

private

boolean

Optional

Create an incident as private. Once an incident is made as private it cannot be undone. Example: true.

public_title

string

Optional

The public title of the incident. Example: Checkout API latency.

resolved_at

string

Optional

Date of resolution. Example: 2025-01-15T14:30:00Z.

scheduled_for

string

Optional

Date of when the maintenance begins. Example: Example scheduled for.

scheduled_until

string

Optional

Date of when the maintenance ends. Example: Example scheduled until.

service_ids

array

Optional

The Service IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

severity_id

string

Optional

The Severity ID to attach to the incident. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

slack_channel_archived

boolean

Optional

Whether the Slack channel is archived. Example: true.

slack_channel_id

string

Optional

Slack channel id. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

slack_channel_name

string

Optional

Slack channel name. Example: Example slack channel name.

slack_channel_url

string

Optional

Slack channel url. Example: https://example.com/runbook.

started_at

string

Optional

Date of start. Example: 2025-01-15T14:30:00Z.

status

string

Optional

The status of the incident. One of: in_triage, started, detected, acknowledged, mitigated, resolved, closed, cancelled, scheduled, in_progress, completed. Example: in_triage. One of: `in_triage`, `started`, `detected`, `acknowledged`, `mitigated`, `resolved`, `closed`, `cancelled`, `scheduled`, `in_progress`, `completed`.

summary

string

Optional

The summary of the incident. Example: Elevated p99 latency on the checkout API.

title

string

Optional

The title of the incident. We will autogenerate one if null. Example: Checkout API latency.

url

string

Optional

The url to the incident. Example: https://example.com/runbook.

user_id

string

Optional

User ID of the creator of the incident. Default to the user attached to the Api Key. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

rootly_create_incident_status_page_event

Create incident status page event

rootly_create_service

Create service

Create a service. Returns the service record with id, type and attributes (name, slug, managed_by, description, public_description, notify_emails). Use it to add a new record; use the matching update tool to change an existing one.

Parameters

Name

Type

Required

Description

name

string

Required

The name of the service. Example: Checkout API latency.

alert_broadcast_channel

object

Optional

Slack channel to broadcast alerts to. Provide as a JSON object. Example: {"key": "value"}

alert_broadcast_enabled

boolean

Optional

Enable alerts to be broadcasted to a specific channel. Example: true.

alert_urgency_id

string

Optional

The alert urgency id of the service. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

alerts_email_enabled

boolean

Optional

Enable alerts through email. Example: oncall@example.com.

backstage_id

string

Optional

The Backstage entity id associated to this service. eg: :namespace/:kind/:entity_name. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

color

string

Optional

The hex color of the service. Example: #6D55BD.

cortex_id

string

Optional

The Cortex group id associated to this service. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

description

string

Optional

The description of the service. Example: Elevated p99 latency on the checkout API.

environment_ids

array

Optional

Environments associated with this service. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

escalation_policy_id

string

Optional

The escalation policy id of the service. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

external_id

string

Optional

The external id associated to this service. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

github_repository_branch

string

Optional

The GitHub repository branch associated to this service. eg: main. Example: Example github repository branch.

github_repository_name

string

Optional

The GitHub repository name associated to this service. eg: rootlyhq/my-service. Example: Example github repository name.

gitlab_repository_branch

string

Optional

The GitLab repository branch associated to this service. eg: main. Example: Example gitlab repository branch.

gitlab_repository_name

string

Optional

The GitLab repository name associated to this service. eg: rootlyhq/my-service. Example: Example gitlab repository name.

incident_broadcast_channel

object

Optional

Slack channel to broadcast incidents to. Provide as a JSON object. Example: {"key": "value"}

incident_broadcast_enabled

boolean

Optional

Enable incidents to be broadcasted to a specific channel. Example: true.

kubernetes_deployment_name

string

Optional

The Kubernetes deployment name associated to this service. eg: namespace/deployment-name. Example: Example kubernetes deployment name.

notify_emails

array

Optional

Emails to attach to the service. Example: ["example"]

opsgenie_id

string

Optional

The Opsgenie service id associated to this service. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

opsgenie_team_id

string

Optional

The Opsgenie team id associated to this service. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

owner_group_ids

array

Optional

Owner Teams associated with this service. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

owner_user_ids

array

Optional

Owner Users associated with this service. Example: [{"key": "value"}]

pagerduty_id

string

Optional

The PagerDuty service id associated to this service. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

position

integer

Optional

Position of the service. Example: 10.

properties

array

Optional

Array of property values for this service. Example: [{"key": "value"}]

public_description

string

Optional

The status page description of the service. Example: Elevated p99 latency on the checkout API.

service_ids

array

Optional

Services dependent on this service. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

service_now_ci_sys_id

string

Optional

The Service Now CI sys id associated to this service. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

show_uptime

boolean

Optional

Show uptime. Example: 2025-01-15T14:30:00Z.

show_uptime_last_days

integer

Optional

Show uptime over x days. Example: 2025-01-15T14:30:00Z.

slack_aliases

array

Optional

Slack Aliases associated with this service. Example: [{"key": "value"}]

slack_channels

array

Optional

Slack Channels associated with this service. Example: [{"key": "value"}]

slug

string

Optional

Deprecated. `slug` is derived from `name`; any submitted value is ignored. This property will be removed from the request schema in a future version. Example: database-primary.

rootly_delete_action_item

Delete action item

rootly_get_action_item

Get action item

rootly_get_alert_route

Get alert route

rootly_get_catalog_entity

Get catalog entity

rootly_get_environment

Get environment

rootly_get_incident_event

Get incident event

rootly_get_post_mortem

Get post mortem

rootly_get_schedule

Get schedule

rootly_get_status_page_event

Get status page event

rootly_list_action_items

List action items

rootly_list_alert_sources

List alert sources

rootly_list_catalog_entities

List catalog entities

rootly_list_escalation_policies

List escalation policies

rootly_list_incident_events

List incident events

rootly_list_incident_types

List incident types

rootly_list_playbooks

List playbooks

rootly_list_schedule_override_shifts

List schedule override shifts

rootly_list_shifts

List shifts

rootly_list_statuses

List statuses

rootly_move_incident_to_triage

Move incident to triage

rootly_update_action_item

Update action item

rootly_update_incident

Update incident

Update an incident. Returns the incident record with id, type and attributes (sequential_id, title, kind, slug, parent_incident_id, duplicate_incident_id). Use it to change an existing record by id; only the fields you supply are changed.

Parameters

Name

Type

Required

Description

string

Required

The UUID or slug of the target record, as returned by the matching list tool. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

acknowledged_at

string

Optional

Date of acknowledgment. Example: 2025-01-15T14:30:00Z.

alert_ids

array

Optional

The Alert IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

cancellation_message

string

Optional

Why was the incident cancelled?. Example: Elevated p99 latency on the checkout API.

cancelled_at

string

Optional

Date of cancellation. Example: 2025-01-15T14:30:00Z.

cause_ids

array

Optional

The Cause IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

closed_at

string

Optional

Date of closure. Example: 2025-01-15T14:30:00Z.

detected_at

string

Optional

Date of detection. Example: 2025-01-15T14:30:00Z.

duplicate_incident_id

string

Optional

ID of duplicated incident. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

environment_ids

array

Optional

The Environment IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

functionality_ids

array

Optional

The Functionality IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

google_drive_parent_id

string

Optional

Google Drive parent folder ID. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

google_drive_url

string

Optional

Google Drive URL. Example: https://example.com/runbook.

group_ids

array

Optional

The Team IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

in_triage_at

string

Optional

Date of triage. Example: 2025-01-15T14:30:00Z.

incident_type_ids

array

Optional

The Incident Type IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

jira_issue_id

string

Optional

Jira issue ID. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

jira_issue_key

string

Optional

Jira issue key. Example: OPS-123.

jira_issue_url

string

Optional

Jira issue URL. Example: https://example.com/runbook.

kind

string

Optional

labels

object

Optional

Labels to attach to the incidents. eg: {"platform":"osx", "version": "1.29"}. Provide as a JSON object. Example: {"key": "value"}

linear_issue_id

string

Optional

Linear issue ID. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

linear_issue_key

string

Optional

Linear issue key. Example: OPS-123.

linear_issue_url

string

Optional

Linear issue URL. Example: https://example.com/runbook.

mitigated_at

string

Optional

Date of mitigation. Example: 2025-01-15T14:30:00Z.

mitigation_message

string

Optional

How was the incident mitigated?. Example: Elevated p99 latency on the checkout API.

muted_service_ids

array

Optional

parent_incident_id

string

Optional

ID of parent incident. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

private

boolean

Optional

Convert the incident as private. Once an incident is updated as private it cannot be undone. Example: true.

public_title

string

Optional

The public title of the incident. Example: Checkout API latency.

resolution_message

string

Optional

How was the incident resolved?. Example: Elevated p99 latency on the checkout API.

resolved_at

string

Optional

Date of resolution. Example: 2025-01-15T14:30:00Z.

scheduled_for

string

Optional

Date of when the maintenance begins. Example: Example scheduled for.

scheduled_until

string

Optional

Date of when the maintenance ends. Example: Example scheduled until.

service_ids

array

Optional

The Service IDs to attach to the incident. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

severity_id

string

Optional

The Severity ID to attach to the incident. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

slack_channel_archived

boolean

Optional

Whether the Slack channel is archived. Example: true.

slack_channel_id

string

Optional

Slack channel id. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

slack_channel_name

string

Optional

Slack channel name. Example: Example slack channel name.

slack_channel_url

string

Optional

Slack channel url. Example: https://example.com/runbook.

started_at

string

Optional

Date of start. Example: 2025-01-15T14:30:00Z.

status

string

Optional

summary

string

Optional

The summary of the incident. Example: Elevated p99 latency on the checkout API.

title

string

Optional

The title of the incident. Example: Checkout API latency.

rootly_update_post_mortem

Update post mortem

Update an incident retrospective. Returns the incident_post_mortem record with id, type and attributes (title, content, status, started_at, mitigated_at, resolved_at). Use it to change an existing record by id; only the fields you supply are changed.

Parameters

Name

Type

Required

Description

string

Required

The UUID or slug of the target record, as returned by the matching list tool. Example: a1b2c3d4-e5f6-4789-a012-3456789abcde.

cause_ids

array

Optional

The Cause IDs to attach to the incident retrospective. Example: ["a1b2c3d4-e5f6-4789-a012-3456789abcde"]

content

string

Optional

The content (body) of the incident retrospective, as HTML. Rejected with a 409 once the retrospective has been opened in the collaborative editor. Example: Elevated p99 latency on the checkout API.

mitigated_at

string

Optional

Date of mitigation. Example: 2025-01-15T14:30:00Z.

resolved_at

string

Optional

Date of resolution. Example: 2025-01-15T14:30:00Z.

show_action_items

boolean

Optional

Show action items (follow-ups) in the incident retrospective. Example: true.

show_alerts_attached

boolean

Optional

Show alerts attached to the incident. Example: true.

show_functionalities_impacted

boolean

Optional

Show services impacted of the incident retrospective. Example: true.

show_groups_impacted

boolean

Optional

Show groups impacted of the incident retrospective. Example: true.

show_services_impacted

boolean

Optional

Show functionalities impacted of the incident retrospective. Example: true.

show_timeline

boolean

Optional

Show events timeline of the incident retrospective. Example: 2025-01-15T14:30:00Z.

show_timeline_action_items

boolean

Optional

Show action items in the timeline of the incident retrospective. Example: 2025-01-15T14:30:00Z.

show_timeline_genius

boolean

Optional

Show workflow events in the timeline of the incident retrospective. Example: 2025-01-15T14:30:00Z.

show_timeline_tasks

boolean

Optional

Show tasks in the timeline of the incident retrospective. Example: 2025-01-15T14:30:00Z.

show_timeline_trail

boolean

Optional

Show trail events in the timeline of the incident retrospective. Example: 2025-01-15T14:30:00Z.

started_at

string

Optional

Date of started at. Example: 2025-01-15T14:30:00Z.

status

string

Optional

The status of the incident retrospective. One of: draft, published. Example: draft. One of: `draft`, `published`.

title

string

Optional

The title of the incident retrospective. Example: Checkout API latency.

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Rootly tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["rootly"], toolNames: [
    "rootly_list_oncalls",
    "rootly_create_incident",
    "rootly_create_incident_status_page_event"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Create a SEV1 incident for the payments outage and post it on the status page" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["rootly"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Create a SEV1 incident for the payments outage and post it on the status page" }],
  tools,
});

// Execute the tool call with the user's vaulted Rootly access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["rootly"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Create a SEV1 incident for the payments outage and post it on the status page" }],
  tools,
});

// Tool call runs with the user's vaulted Rootly access token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["rootly"] }, pageSize: 100,
});

const agent = new Agent({
  name: "incident_agent",
  model: "gemini-2.5-pro",
  instruction: "Rootly tools scoped to this user",
  tools,
});

await agent.run("Create a SEV1 incident for the payments outage and post it on the status page");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Rootly tool. Click to copy, paste into your agent, done.

Incidents

Copy the prompt

Copied

Create a SEV1 incident for the payments outage.

Copy the prompt

Copied

Mitigate the checkout incident and add a timeline event.

Copy the prompt

Copied

Assign Priya as commander on the payments incident.

Alerts and on-call

Copy the prompt

Copied

Acknowledge the latest alert for the API service.

Copy the prompt

Copied

Who is on call this weekend?

Copy the prompt

Copied

Add an override shift for Dana tonight from 6pm to midnight.

Follow-through

Copy the prompt

Copied

List open action items from last week's incidents.

Copy the prompt

Copied

Update the payments retrospective with the root cause.

Copy the prompt

Copied

Post a status page update that the payments fix is deployed.

SEE HOW AUTH WORKS

Each user connects their own Rootly access token once, and Scalekit sends it with every call. Tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Rootly

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Rootly

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Rootly

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Rootly

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other monitoring and developer tools connectors.

Engineering Teams

DevOps assistant agent

Polls GitHub for failing checks and stale PRs, opens Linear issues for the ones that need work, and posts a daily digest to Slack. It acts as the engineer, not a shared service account.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Rootly access token looks fine in a demo. In production every incident update and alert acknowledgement looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Rootly today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Rootly as the user or through a shared token?

As the user. Each user connects their own Rootly access token once, and Scalekit sends it with every call. Audit logs attribute every incident change and alert action to that user, not a shared service account.

Where is the Rootly access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Rootly?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example the read tools without rootly_delete_incident or rootly_escalate_alert. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Rootly access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

What can the agent do with Rootly alerts?

List and read alerts and alert groups, create alerts, and acknowledge, snooze, escalate, or resolve them with rootly_acknowledge_alert, rootly_snooze_alert, rootly_escalate_alert, and rootly_resolve_alert. Alert routes, sources, and urgencies are readable for context.