FireHydrant + Memtro

Only when you ask, and only what it has been granted: add a note to an incident, private to the organisation; add a task to an incident; declare an incident (your runbook automation may open a channel and page responders); update an incident's name, summary, description, impact, severity, priority or tags; resolve an incident; close an incident; archive an incident (hidden from lists and metrics); update an incident task's title, state, assignee or due date; edit the text of a note on an incident; assign an incident role to a user; attach a link to an incident. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.

A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.

Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.

API key. In FireHydrant open Settings → API Keys. Only an Owner can create a key, and it has Owner permissions by default, so make one just for Memtro that you can revoke.

Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in FireHydrant, choosing the same kinds; the tab shows FireHydrant's own steps. A job set to start "When an event arrives" then runs once for each matching event, with the event as its input. The run treats the event as outside data, never as instructions, and anything the run remembers is kept as unverified.