Skip to content

Start building

Integration · Developer

AI agents for Healthchecks.io

Watch cron jobs and scheduled tasks in a Healthchecks.io project (or your own Healthchecks server).

Actions
10
Read
5
Write
5

Actions

What your agents can do in Healthchecks.io

Watch cron jobs and scheduled tasks in a Healthchecks.io project (or your own Healthchecks server): list checks and which are down, read a check's recent pings and status changes, create and update checks, pause, resume and delete them, with a project API key.

Read 5

Look things up. Nothing changes.

  • List checks

    Lists the project's checks, optionally only those with all the given tags or one slug.

  • Get a check

    Reads one check by its UUID (or its unique_key with a read-only key): status, last_ping, next_ping, n_pings, its schedule or period, grace, tags, desc, its integrations (channels) and ping_url.

  • List a check's pings

    Lists the pings a check received, newest first (up to 100 on free plans, 1,000 on paid).

  • List a check's status changes

    Lists when a check went down and came back up ("flips"), newest first, within the last seconds or between two Unix times, as result: each with its timestamp and up (1 up, 0 down).

  • List integrations

    Lists the project's integrations (where alerts go), as channels: each with its id, name and kind (email, slack, sms, webhook …).

Write 5

Create, change or send.

  • Create a check

    Creates a check and returns it with its uuid and ping_url (the job calls that address when it runs).

  • Update a check

    Changes a check's name, slug, tags, description, period or schedule, time zone, grace time or integrations; fields left out keep their values.

  • Pause a check

    Stops monitoring a check without deleting it (status paused), for planned downtime.

  • Resume a check

    Resumes monitoring of a paused check (status new until its next ping).

  • Delete a checkDeletes data

    Deletes a check for good, with its ping history; pings to its address stop being recorded.

A person can approve first

Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything. Actions that delete data ask first by default.

Connection

How it connects

Connect it once in the console, then give it to the agents and workflows that need it.

API key

Paste an API key from your Healthchecks.io account.

What you enter

  • API key

Settings

  • Healthchecks address

Kept safe

  • Credentials are stored encrypted with your organization's own keys.
  • They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
  • Calls go only to the tool's own servers.

How we protect your data

Ideas

Ideas to start with

Starting points made only from the actions above. Mix them with any other tool your agents can use.

  • 01

    Ask about your Healthchecks.io data

    Ask a question in plain words. The agent can list checks, get a check or list a check's pings in Healthchecks.io, then answers with what it found.

  • 02

    Let an agent update Healthchecks.io

    Have the agent create a check or update a check in Healthchecks.io as part of a larger task. Turn on approval and a person signs off on each change first.

  • 03

    Share what it finds in Slack

    Give one agent Healthchecks.io and Slack: it can list checks in Healthchecks.io and post a summary to a Slack channel in the same run.

FAQ

Healthchecks.io and MyDeepAgents

Can MyDeepAgents connect to Healthchecks.io?

Yes. The Healthchecks.io connector has 10 actions: 5 read and 5 make changes. Your agents can call them as tools, and your workflows can run them as steps.

How do I connect Healthchecks.io?

Paste an API key from your Healthchecks.io account. You'll need: API key. The connection also asks for: Healthchecks address. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.

Can an agent change data in Healthchecks.io without asking?

Only if you let it. Each of the 5 actions that change data can be set to wait for a person's approval before it runs, and the one that deletes data asks first by default.

Can I use Healthchecks.io in workflows as well as agents?

Yes. Every Healthchecks.io action also works as a step in a workflow, and the same connection serves your agents and your workflows.

Early access

Put Healthchecks.io to work

Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.