Deleting things — point the user to the console
Deletions aren't MCP tools; tell the user the exact console screen and button instead.
Deletions are deliberately not exposed as tools — they are irreversible, and from a conversation you usually can't tell whether an agent or knowledge base is still used by something else. So when the user asks you to delete something, don't attempt it — tell them exactly where to do it in the console at console.agent4.io, and offer to help with the safe parts (finding the item, listing what depends on it) first.
| To delete… | Where in the console |
|---|---|
| An agent | Agents → open the agent → top-right ⋯ / Delete |
| A knowledge base (and all its documents) | Knowledge → open the base → Delete |
| One document in a knowledge base | Knowledge → the base → Documents tab → the row → Delete |
| A skill | Skills → the skill → Delete (agents referencing it stop loading its guidance) |
| A user, space, or session | Users → the row → Delete |
| Revoke / re-issue an API key | Settings → Security → Revoke (then create a new one) |
| Change privacy mode / BYOK | Settings (this shifts compliance responsibility — confirm before changing) |
Before you send them off, it helps to surface what would be affected: e.g. list the agents that
mount a knowledge base (list_agents + get_agent) so they can see whether deleting it breaks anything.
That check is exactly why deletion is a human action in the console, not a tool call.