Statuspage connector for AI agents

Tools your on-call agent reaches for on Statuspage, scoped per tenant.

CALL ANY TOOL

Incident comms end to end: create and update incidents, flip component status, manage component groups, subscribers, and uptime metrics from one vaulted API key.

statuspage_component_create

Create component

Create a new component (a service or part of your infrastructure) on a Statuspage page, with a display name, status, description, and optional group assignment.

Parameters

Name

Type

Required

Description

name

string

Required

Display name for the component, e.g. 'API' or 'Website'.

page_id

string

Required

The identifier of the Statuspage page to create the component on

description

string

Optional

More detailed description for the component.

group_id

string

Optional

Identifier of the component group to add this component to.

only_show_if_degraded

boolean

Optional

Whether to only show this component if it is degraded. Requires a special feature flag to be enabled on your account.

showcase

boolean

Optional

Whether this component should be showcased on the status page.

start_date

string

Optional

The date this component started being used, in YYYY-MM-DD format.

status

string

Optional

Status of the component. Valid values: operational, under_maintenance, degraded_performance, partial_outage, major_outage.

statuspage_component_delete

Delete component

statuspage_component_get

Get component

statuspage_component_group_update

Update component group

statuspage_component_groups_list

List component groups

statuspage_component_page_access_groups_add

Add component page access groups

statuspage_component_page_access_groups_remove

Remove component page access groups

statuspage_component_uptime_get

Get component uptime

statuspage_incident_postmortem_create

Create incident postmortem

statuspage_incident_postmortem_delete

Delete incident postmortem

statuspage_incident_postmortem_publish

Publish incident postmortem

statuspage_incident_postmortem_revert

Incident postmortem revert

statuspage_incident_subscriber_get

Get incident subscriber

statuspage_incident_update_edit

Incident update edit

statuspage_incidents_list_scheduled

Incidents list scheduled

statuspage_metric_data_reset

Reset metric data

statuspage_metric_provider_metric_create

Create metric provider metric

statuspage_metrics_data_add_batch

Batch metrics data add

statuspage_metrics_list

List metrics

statuspage_page_access_group_component_remove

Remove page access group component

statuspage_page_access_group_components_delete

Delete page access group components

statuspage_page_access_group_update

Update page access group

statuspage_page_access_user_get

Get page access user

statuspage_page_access_user_metric_delete

Delete page access user metric

statuspage_page_access_user_metrics_replace

Page access user metrics replace

statuspage_page_access_users_list

List page access users

statuspage_status_embed_config_update

Update status embed config

statuspage_subscriber_create

Create subscriber

statuspage_subscriber_get

Get subscriber

statuspage_subscribers_reactivate_bulk

Subscribers reactivate bulk

For more tools, view docs.

Build your Agent

Drop the toolkit in, point it at the tenant, and your agent can open an incident and post updates from the first run.

import { ScalekitClient } from "@scalekit-sdk/node";
import { DynamicStructuredTool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { z } from "zod";

const sk = new ScalekitClient(envUrl, clientId, clientSecret);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["statuspage"], toolNames: ["statuspage_incidents_list", "statuspage_incident_create", "statuspage_component_update"] },
  pageSize: 100,
});

const lcTools = tools.map((t) => new DynamicStructuredTool({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  schema: z.object({}).passthrough(),
  func: async (args) => {
    const { data } = await sk.tools.executeTool({
      toolName: t.tool.definition.name,
      identifier: "user_123",
      params: args,
    });
    return JSON.stringify(data);
  },
}));

const agent = createReactAgent({ llm, tools: lcTools });

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["statuspage"], toolNames: ["statuspage_incidents_list", "statuspage_incident_create", "statuspage_component_update"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  type: "function",
  function: {
    name: t.tool.definition.name,
    description: t.tool.definition.description,
    parameters: t.tool.definition.input_schema,
  },
}));

const resp = await openai.responses.create({
  model: "gpt-4o", input: prompt, tools: llmTools,
});

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

const sk = new ScalekitClient(envUrl, clientId, clientSecret);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["statuspage"], toolNames: ["statuspage_incidents_list", "statuspage_incident_create", "statuspage_component_update"] },
  pageSize: 100,
});

const llmTools = tools.map((t) => ({
  name: t.tool.definition.name,
  description: t.tool.definition.description,
  input_schema: t.tool.definition.input_schema,
}));

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6", max_tokens: 1024,
  tools: llmTools,
  messages: [{ role: "user", content: prompt }],
});

import { Agent } from "@google/adk/agents";
import {
  MCPToolset, StreamableHTTPConnectionParams,
} from "@google/adk/tools/mcp";

const toolset = new MCPToolset({
  connectionParams: new StreamableHTTPConnectionParams({
    url: "https://mcp.scalekit.com/statuspage",
    headers: { Authorization: `Bearer ${userScopedToken}` },
  }),
});

const agent = new Agent({
  name: "agent", model: "gemini-2.0-flash",
  tools: await toolset.getTools(),
});

Try these prompts

Paste any prompt into your agent to start running Statuspage incident comms from your workflows.

Incident response

Copy the prompt

Copied

Open a partial outage on [component] and post an investigating update.

Copy the prompt

Copied

Move incident [inc_id] to identified and add the root cause we found.

Copy the prompt

Copied

Resolve [inc_id] and post the final summary.

Status hygiene

Copy the prompt

Copied

List components whose status is not operational right now.

Copy the prompt

Copied

Show uptime for [component_group] over the last 30 days.

Copy the prompt

Copied

Which components are missing from every component group?

Subscribers

Copy the prompt

Copied

How many subscribers are on [page_id] and by which channel?

Copy the prompt

Copied

List subscribers who signed up in the last 7 days.

Copy the prompt

Copied

Remove unconfirmed email subscribers older than 90 days.

SEE HOW AUTH WORKS

Your users connect once. Their Statuspage credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

Statuspage

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

Statuspage

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

Statuspage

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

Statuspage

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 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.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Statuspage today. Others 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 Statuspage as the user or as a shared key?

As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Statuspage API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Statuspage?

Yes. Pass a tool name filter to listScopedTools so the on-call agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Statuspage.

What happens when a user revokes Statuspage 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.

Can the agent publish to our public status page by accident?

Not unless you expose the write tools. Incident create, update, and component status live in separate tools from the list and get tools, so a reporting agent stays read only. Every publish is scope-checked before the Statuspage call and logged with the acting user.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit