Skip to content

Connectors · Observability & analytics

StatusCake MCP server for AI agents.

actionlake is an MCP gateway: one remote MCP server that connects Claude and other MCP clients to StatusCake and the rest of your systems. It gives your agent 36 StatusCake actions (18 reads, 12 writes and 6 that wait for a confirmation) and holds the StatusCake credential itself, so the agent never does. It paces StatusCake's limits and records every call.

100,000 free calls a month. No card, no email, no password: press Start a free sandbox on the next screen and keep the key it shows you.

claude mcp add --transport http actionlake https://connect.actionlake.com/mcp
the first call
do {  action: "statuscake.uptime_checks.list",  intent: "check which StatusCake account is connected"}# List uptime checks · read · 1 upstream call
  • 36actionsin one signed file
  • 18readlook, never change
  • 12writecreate and update
  • 6wait for a yesdestructive, confirmed first

Set up

Connect StatusCake in three steps.

  1. 01

    Add actionlake to Claude.

    Run the command once in Claude Code; its consent page can create a free sandbox: 100,000 calls a month, no card. In the Claude app, add a custom connector with the URL below and paste your key on the consent page. Creating a new sandbox from the Claude app is not yet tested by us.

    https://connect.actionlake.com/mcp
  2. 02

    Connect StatusCake.

    Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead. actionlake stores what you paste write-only, sealed under your tenant's key.

    • api_tokenStatusCake API token
    account { op: "connections.requirements", service: "statuscake" }
    # free: exactly what to paste, and what is found for you
  3. 03

    Make the first call. Check before a write.

    Ask in plain words; Claude picks the action. Before anything changes, check validates the call and prices it, for free.

    do    { action: "statuscake.uptime_checks.list" }# list uptime checks · read · 1 upstream callcheck { action: "statuscake.uptime_checks.create", input: { … } }# free: inputs, permissions, cost and confirmations, nothing sent

StatusCake at a glance

Sign-in
Bearer token. No consent screen: your agent can connect it for you, but the key then passes through your chat. To keep it out of the model's context, paste it in the console instead.
You provide
api_token
Limits we pace to
5 calls a second, per connection
API covered
StatusCake API v1 (Swagger 2.0)api.statuscake.com/v1
Built from
StatusCake's documentation, read 23 October 2026developers.statuscake.comdevelopers.statuscake.com
Service file
Version 1.0.0, signed (Ed25519)
Cached reads
18 of 18 reads, for up to an hour; a write clears what it affects
Shared entities
1, so ask can line StatusCake up with your other systems
Data
Processed and stored in Sydney, Australia. No US region yet

Capabilities

What an AI agent can do in StatusCake.

36 actions in 1 area. Every one carries its effect, so a key can allow the reads and hold the rest.

  • 18readlook, never change
  • 12writecreate and update
  • 6destructivewait for a confirmation
  1. Statuscake

    36

    18 read · 12 write · 6 destructive

    List uptime checks · Create an uptime check · Get an uptime check · Update an uptime check

Top actions

The StatusCake API, shaped for agents.

The ids your agent types, what each does, and the one name it shares with other systems. 6 of StatusCake's 6 action names are shared with at least one other connector, so an agent learns them once.

ActionWhat it doesEffectSame name in
statuscake.uptime_checks.listList uptime checksGet all uptime checks.readmonitoring.monitor.list32 connectors
statuscake.uptime_checks.createCreate an uptime checkCreate an uptime check.writemonitoring.monitor.create27 connectors
statuscake.uptime_checks.deleteDelete an uptime checkDelete an uptime check.destructivemonitoring.monitor.delete31 connectors
statuscake.uptime_check_alerts.listList an uptime check's alertsGet all uptime check alerts.readmonitoring.alert.list51 connectors
statuscake.ssl_checks.listList SSL checksGet all SSL checks.readthis connector
statuscake.ssl_checks.createCreate an SSL checkCreate an SSL check.writethis connector
statuscake.contact_groups.listList contact groupsGet all contact groups.readthis connector
statuscake.contact_groups.createCreate a contact groupCreate a contact group.writethis connector
statuscake.heartbeat_checks.listList heartbeat checksGet all heartbeat checks.readthis connector
statuscake.pagespeed_checks.listList pagespeed checksGet all pagespeed checks.readthis connector
statuscake.heartbeat_checks.createCreate a heartbeat checkCreate a heartbeat check.writethis connector
statuscake.pagespeed_checks.createCreate a pagespeed checkCreate a pagespeed check.writethis connector

Try it

Prompts to paste into Claude.

Each one names the StatusCake actions it will call, so you know what it reads and what it changes before you send it.

  1. Readread

    List uptime checks in StatusCake and tell me what stands out.

    callsstatuscake.uptime_checks.list

  2. Writewrite

    Create an uptime check in StatusCake. Show me exactly what you will send before you save it.

    callsstatuscake.uptime_checks.create

Governance for StatusCake

Destructive actions wait for a yes.

6 StatusCake actions are destructive. These are all of them:

  • Delete an uptime checkstatuscake.uptime_checks.delete
  • Delete an SSL checkstatuscake.ssl_checks.delete
  • Delete a contact groupstatuscake.contact_groups.delete
  • Delete a heartbeat checkstatuscake.heartbeat_checks.delete
  • Delete a pagespeed checkstatuscake.pagespeed_checks.delete
  • Delete a maintenance windowstatuscake.maintenance_windows.delete

A destructive action runs only with confirm: true. Under the human policy the agent cannot confirm for itself: the run stops until a named person approves, in the console or from a signed link in an email. The cap on a key is refused before the call is sent, never after.

dostatuscake.uptime_checks.deleteconfirm_policy: human

Delete an uptime check?

intent: the user asked me to delete an uptime check

run suspended · waiting for a named person · key statuscake-agent cannot confirm itself
In the console, or from an emailed signed link.
a key for this connector
account {  op: "keys.create", name: "statuscake-agent",  allowed_actions: ["statuscake.*"], cap_calls: 2000,  confirm_policy: "human_for_writes",  approval_rules: [    { match: "statuscake.uptime_checks.delete", approver: "[email protected]" },    { match: "statuscake.ssl_checks.delete", approver: "[email protected]" },    { match: "statuscake.contact_groups.delete", approver: "[email protected]" }  ]}
Illustrative. Scoped to StatusCake only, capped at 2,000 upstream calls, every write confirmed, and the destructive ones approved by a named person.

Cost

What StatusCake costs on actionlake.

Every StatusCake action is one upstream call, the only thing actionlake bills. Searching, check, cost, account and any call StatusCake refused with 401, 403, 429 or a 5xx are free. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

  • 1upstream call per actionall 36 StatusCake actions
  • 36actions pageeach page of a long list is one call
  • 18reads can be cacheda cache hit costs nothing
  • 100,000calls a month, freepaid plans from US$49 a month for 250,000

See pricing

Action index

Every StatusCake action.

36 actions by area: the id your agent calls, what it does, and its effect.

Statuscake36
  • statuscake.contact_groups.createCreate a contact groupwrite
  • statuscake.contact_groups.deleteDelete a contact groupdestructive
  • statuscake.contact_groups.getGet a contact groupread
  • statuscake.contact_groups.listList contact groupsread
  • statuscake.contact_groups.updateUpdate a contact groupwrite
  • statuscake.heartbeat_checks.createCreate a heartbeat checkwrite
  • statuscake.heartbeat_checks.deleteDelete a heartbeat checkdestructive
  • statuscake.heartbeat_checks.getGet a heartbeat checkread
  • statuscake.heartbeat_checks.listList heartbeat checksread
  • statuscake.heartbeat_checks.updateUpdate a heartbeat checkwrite
  • statuscake.maintenance_windows.createCreate a maintenance windowwrite
  • statuscake.maintenance_windows.deleteDelete a maintenance windowdestructive
  • statuscake.maintenance_windows.getGet a maintenance windowread
  • statuscake.maintenance_windows.listList maintenance windowsread
  • statuscake.maintenance_windows.updateUpdate a maintenance windowwrite
  • statuscake.pagespeed_check_history.listList a pagespeed check's historyread
  • statuscake.pagespeed_checks.createCreate a pagespeed checkwrite
  • statuscake.pagespeed_checks.deleteDelete a pagespeed checkdestructive
  • statuscake.pagespeed_checks.getGet a pagespeed checkread
  • statuscake.pagespeed_checks.listList pagespeed checksread
  • statuscake.pagespeed_checks.updateUpdate a pagespeed checkwrite
  • statuscake.pagespeed_locations.listList pagespeed monitoring locationsread
  • statuscake.ssl_checks.createCreate an SSL checkwrite
  • statuscake.ssl_checks.deleteDelete an SSL checkdestructive
  • statuscake.ssl_checks.getGet an SSL checkread
  • statuscake.ssl_checks.listList SSL checksread
  • statuscake.ssl_checks.updateUpdate an SSL checkwrite
  • statuscake.uptime_check_alerts.listList an uptime check's alertsread
  • statuscake.uptime_check_history.listList an uptime check's historyread
  • statuscake.uptime_check_periods.listList an uptime check's up/down periodsread
  • statuscake.uptime_checks.createCreate an uptime checkwrite
  • statuscake.uptime_checks.deleteDelete an uptime checkdestructive
  • statuscake.uptime_checks.getGet an uptime checkread
  • statuscake.uptime_checks.listList uptime checksread
  • statuscake.uptime_checks.updateUpdate an uptime checkwrite
  • statuscake.uptime_locations.listList uptime monitoring locationsread

Questions

The StatusCake MCP server, answered.

Is there a StatusCake MCP server for Claude?

Yes. actionlake is an MCP gateway: a remote MCP server that gives Claude, or another MCP client, 36 StatusCake actions, through the same eight tools it uses for every other connector. actionlake is independent; it is not made or endorsed by StatusCake.

What do I need to connect StatusCake?

StatusCake API token. The free call account { op: "connections.requirements", service: "statuscake" } lists exactly what to paste.

Can an AI agent delete or change things in StatusCake?

Only if its key allows it, and only with an explicit confirmation. 6 StatusCake actions are destructive, including delete an uptime check, delete an SSL check and delete a contact group. Each runs only with confirm: true. Under the human confirm policy, or an approval rule on the key, the run waits until a named person approves it.

Will an AI agent use up my StatusCake API limit?

actionlake paces every call to the limits in the StatusCake service file: 5 calls a second per connection. Repeated reads are answered from cache (18 StatusCake actions can be), which never reaches StatusCake.

What does a StatusCake action cost?

One upstream call, the only unit actionlake bills. A list that pages bills one call per page (36 StatusCake actions page). Cache hits, searches, dry runs and calls StatusCake refused with 401, 403, 429 or a 5xx are free. The Free plan includes 100,000 calls a month with no card. Paid plans start at US$49 a month for 250,000 calls, with overage from US$0.30 down to US$0.18 per 1,000.

Which StatusCake API does it cover?

The StatusCake API v1 (Swagger 2.0) at api.statuscake.com/v1. It is built from StatusCake's documentation as read on 23 October 2026. 36 actions in 1 area, each one in the signed service file (version 1.0.0).

Does actionlake keep my StatusCake data, and where?

actionlake processes and stores data in Sydney, Australia; there is no US region yet. Reads may be cached for up to an hour, and a write clears the reads it affects. Each run's request and response is kept, sealed, for your plan's trace window: 1 day on Free, 3 days on Starter, 7 days on Pro, 14 days on Team, 30 days on Business and 30 days on Enterprise. Your StatusCake credential is sealed under your tenant's key, never logged and never returned. Your traffic is not used to train models.

Which AI clients can use it?

Claude Code, tested by us end to end, and the Claude app as a custom connector, tested by us with an existing key. Other MCP clients that support remote servers over Streamable HTTP (MCP revisions 2025-06-18 and 2025-11-25) and OAuth dynamic client registration, or a bearer header, should connect the same way; we have not tested them. Or plain REST, under the same action names.

Give your agent StatusCake today.

Start free - 100,000 calls/month, no card. No signup. Hard caps on every key. Cached answers are free.