Asking a person

One of the fourteen tools does something nothing can undo: delete_check. It asks a person first.

Not a confirm: true argument the model can set. Not a token the model reads out of its own previous result. A dialog, raised through MCP elicitation, that goes to the client and is shown to whoever is sitting there.

The specification says a client should keep a human in the loop:

there SHOULD always be a human in the loop with the ability to deny tool invocations

This server does not rely on that. It raises the question itself, and until an answer comes back, nothing happens.

What asks, and when

Tool	When it asks
delete_check	always
everything else	never

pause_check used to be on that list and is not any more. Pausing switches alerting off, which is quiet rather than loud — but resume_check puts it back and nothing is lost in between. A dialog in front of a reversible state change is how people learn to tick without reading, and that attention is what delete_check needs. What pausing costs is stated in the tool's description instead: while paused, a job that stops running goes unnoticed.

The parameter went with the guard. pause_check no longer declares confirm_token at all, so a caller that still sends one is told rather than quietly ignored.

What the dialog contains

The check's UUID and what deleting it costs. Never its name, description or tags — those are free text this server does not control, and the prompt is read by a model at the exact moment it is deciding.

This will delete check 5a2d…

The UUID cannot be recovered and no new check can take it, so everything still
pinging that URL breaks. pause_check is the reversible alternative.

The approval is bound to its target, so one obtained for a call cannot be replayed against another. For a set of targets the binding is a fingerprint of the exact list: an approval for ["a"] does not execute ["a", "b"].

Clients that cannot show a dialog

Not every MCP client implements elicitation, and a stateless gateway may not be able to speak for the one it is currently serving. Rather than refuse to work — which pushes people towards switching the guard off entirely — the tool falls back to a two-call token: the first call returns a random string, the second has to quote it back.

Be clear about what that proves, because this server is:

the token proves the call was made twice with the same arguments, and nothing more.

A model can read the token out of the first result and call again in the same turn without anybody seeing it. It catches a widened target set; it does not catch a model that was talked into the whole thing. The fallback text says so rather than implying somebody approved.

Switching the dialog off

ELICITATION=false

Default is true. false does not remove the guard — it takes the fallback path above, which means the token. There is no setting in which a guarded call goes unannounced.

Use it where a dialog is the wrong shape rather than an unwanted one: a scheduled job, a test harness, a client whose dialog interrupts something else.

It is deliberately not prefixed

ELICITATION has no HEALTHCHECKS_ in front of it, so one export ELICITATION=false — or one -e ELICITATION=false in a compose file — reaches every MCP server in that environment, not just this one. That is the point of it and also its risk.

Two things make it visible rather than silent:

• a server started with it off prints one line at startup, in the log of every server it actually reached:

  healthchecks-mcp: ELICITATION=false — guarded tools fall back to the two-call token

• the fallback text names the server that did not ask, instead of blaming a client that was working fine. :::

Anything other than true or false — 1, off, yes — stops the server with exit code 1 and a message naming both valid values. This is the only variable in this family that defaults to on: a typo that fell back to the default would leave the dialog running while the operator believed it was off, and there would be nothing to tell them.

Annotations are the other half, and they are only a hint

Every tool of this server declares all four MCP tool annotations — readOnlyHint, destructiveHint, idempotentHint, openWorldHint — so a client can tell before it calls what a call would do. See Tools.

They are advice, and the specification says so:

clients MUST consider tool annotations to be untrusted unless they come from trusted servers

An annotation is something a client may ignore. The dialog is not: it is enforced here, on the server side, and no answer means no change. The two are different claims — the annotation says what a call does, the dialog decides whether it happens — which is why a tool can be marked destructive without being guarded. update_check is exactly that case: channels replaces the integration list rather than adding to it, which is destructive, and it is not asked about.

Behind a gateway

Both protocol revisions are handled from one code path. On 2025-11-25 the question is pushed to the client; on 2026-07-28 there is no server→client channel at all, so the call returns input_required, ends, and the client retries carrying the answer.

That answer arrives as ordinary request content, which the SDK does not validate — so the state that ties an answer to its question is sealed (HMAC). A reply whose seal does not open, or opens onto a different target, counts as no answer and produces a fresh question rather than an error. The likeliest cause is not an attack: it is a gateway that put the server to sleep while the person was reading.

If you run this behind mcp-hub, the hub passes elicitation through in both directions; see its elicitation guide.