Statuscake for AI agents

StatusCake is a website monitoring service that tracks uptime, page speed, and SSL certificate health for websites and APIs, alerting teams to outages. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

DevOps and monitoringAPI keyMCP + RESTstatuscake.com
AUDIT LOG · STATUSCAKEPOLICY: acme-support
09:41:07 · claude · u_8f2read
statuscake.list_uptime_test_alerts
List Uptime Test Alerts✓ allowed · 212ms
09:41:08 · claude · u_8f2read
statuscake.get_all_tests
Get All Tests✓ allowed · 164ms
09:41:09 · claude · u_8f2write
statuscake.create_uptime_test
Create Uptime Test✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
statuscake.delete_test
Delete Test✕ blocked · policy: deny
EVERY STATUSCAKE CALL, ON THE RECORD
01 · USE CASES

What agents do in Statuscake.

01

Check uptime test history

Pull the uptime history for a monitored site to see when outages or slowdowns happened last month.

02

Create a new uptime test

Set up an uptime test on a new domain so the team gets alerted the moment it goes down.

03

Delete a test only with approval

Remove an SSL or uptime test only after confirming with the user that the monitored site is being retired.

02 · ACTIONS

30 Statuscake actions, graded by risk.

Every Statuscake action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

16

Look things up. Allowed by default.

  • statuscake.get_all_tests
    Get All Tests
  • statuscake.get_ssl_checks
    Get SSL Checks
  • statuscake.get_uptime_test
    Get Uptime Test
  • statuscake.get_all_locations
    Get All Monitoring Locations
  • statuscake.get_heartbeat_test
    Get Heartbeat Test
  • statuscake.get_pagespeed_test
    Get Pagespeed Test
  • statuscake.get_heartbeat_checks
    Get Heartbeat Checks
  • statuscake.get_ssl_check_details
    Get SSL Check Details
  • statuscake.get_all_contact_groups
    Get All Contact Groups
  • statuscake.get_all_pagespeed_tests
    Get All PageSpeed Tests
  • statuscake.list_uptime_test_alerts
    List Uptime Test Alerts
  • statuscake.list_uptime_test_history
    List Uptime Test History
  • statuscake.list_uptime_test_periods
    List Uptime Test Periods
  • statuscake.get_contact_group_details
    Get Contact Group Details
  • statuscake.list_pagespeed_test_history
    List Pagespeed Test History
  • statuscake.list_pagespeed_monitoring_locations
    List PageSpeed Monitoring Locations

write

9

Create and change things. Allow, or ask the user first.

  • statuscake.update_ssl_test
    Update SSL Test
  • statuscake.create_uptime_test
    Create Uptime Test
  • statuscake.update_uptime_test
    Update Uptime Test
  • statuscake.create_contact_group
    Create Contact Group
  • statuscake.update_contact_group
    Update Contact Group
  • statuscake.create_heartbeat_test
    Create Heartbeat Test
  • statuscake.create_pagespeed_test
    Create PageSpeed Test
  • statuscake.update_heartbeat_test
    Update Heartbeat Test
  • statuscake.update_pagespeed_test
    Update Pagespeed Test

destructive

5

Delete, cancel or archive. Ask first, or deny outright.

  • statuscake.delete_test
    Delete Test
  • statuscake.delete_ssl_test
    Delete SSL Test
  • statuscake.delete_contact_group
    Delete Contact Group
  • statuscake.delete_heartbeat_test
    Delete Heartbeat Test
  • statuscake.delete_pagespeed_test
    Delete PageSpeed Test
03 · HOW IT WORKS

Statuscake in three steps.

  1. 01Your users connect StatuscakeThey add their Statuscake api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Uptime Test” can wait for the user, and “delete Test” can be denied outright.
  3. 03Any agent can actYour agent calls Statuscake through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('statuscake', {
  read: 'allow',
  write: 'ask',        // create_uptime_test
  destructive: 'deny',  // delete_test
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Statuscake connects.

Users add their Statuscake api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Statuscake connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Statuscake from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Statuscake and Arc0, answered.

Q01

Can I use Statuscake with Claude, ChatGPT or Cursor?

Yes. Connect Statuscake to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Statuscake actions you allow.

Q02

How do users connect Statuscake?

Users add their Statuscake api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Statuscake actions can my agent take?

30 in total: 16 read, 9 write and 5 destructive, such as “create Uptime Test”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Statuscake?

Yes. Actions like “delete Test” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Statuscake too?

Yes. The same Statuscake connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Statuscake into your agent.

Your users connect Statuscake once, under your brand. Your agent gets 30 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan