Asking a person

Five of the sixteen tools change something that FreshRSS keeps no record of undoing. All five ask 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
mark_all_as_read	always
unsubscribe_feed	always
delete_category_or_label	always
import_opml	always
mark_articles	only when it is about to mark something read
everything else	never

The mark_articles line is the one worth explaining. Starring, unstarring, labelling and marking unread all set a field that can be set back, and asking about a star toggle would be how people learn to tick without reading. Marking read destroys which of those articles were unread, and FreshRSS keeps no record of that — the same reason mark_all_as_read is guarded, over a caller-named list instead of a whole stream.

Its description used to say the opposite in so many words: “All changes are reversible by calling this tool again with the opposite value.” Three of the four are.

What the dialog contains

Ids and counts. Never a feed title, an article headline or a category name.

That is not a formatting preference. Everything FreshRSS hands back was written by a stranger who can publish to a feed, and the prompt is read by a model at the exact moment it is deciding whether to do something irreversible. Even the description of a category resolves to the constant “the selected category” rather than its name.

This will mark 12 article(s) as read.

FreshRSS keeps no record of which of them were unread, so this cannot be undone.
The other changes in the same call — stars and labels — can be set back.

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 FRESHRSS_ 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:

  freshrss-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_feed and rename_category_or_label are exactly that case: they replace a name somebody chose, and they are 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. A state is also single-use: it carries a nonce that is spent on the first answer, so the same approved answer cannot be presented a second time for the same call.

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