Marketing & email · wired today
What can agents actually do with Postmark?
Campaign and audience data drives half the questions agents get asked. The Postmark connector is one of 205 executable connectors and gives agents 4 read-only tools, with the credential held in the vault and every call receipted.
The Postmark tool list, exactly as agents see it
get_server— Get the Postmark server this token belongs to (name, delivery type, inbound address and tracking settings)outbound_overview— Get the Postmark outbound sending overview (sent, bounced, bounce rate, spam complaints, opens and click totals)list_outbound_messages— Search recent Postmark outbound messages, optionally filtered by recipient, tag or delivery statuslist_bounces— List Postmark bounces, optionally filtered by bounce type, recipient email or tag
Every tool above is read-only. Write surfaces ship only after live testing, and always behind approval gates.
What the Postmark connector needs
You provide server token from your Postmark account; Quox sends it as an API key sent as a header. The credential is stored encrypted in the vault and resolved just-in-time, so agents use it without ever seeing it.
Where to get it: Postmark's own API documentation ↗ covers creating and scoping the credential.
How proven is this?
This connector was blind shape-proven against the real Postmark API: every endpoint it declares answered measurably differently from a deliberately bogus control request, without any account or credential involved. It is Beta: proven against the live API surface, not yet run with a real credential.
Postmark integration FAQ
What can Quox agents do with Postmark?
Agents can run 4 read-only tools against Postmark: get server, outbound overview, list outbound messages, list bounces. Every call is receipted in the evidence trail.
What does the Postmark integration need?
You provide server token from your Postmark account; Quox sends it as an API key sent as a header. The credential is stored encrypted in the vault and resolved just-in-time, so agents use it without ever seeing it.
Do agents see my Postmark credentials?
No. Credentials live encrypted in the Quox vault and are resolved server-side at call time. Agents invoke tools; they never receive the underlying secret.
How proven is the Postmark connector?
This connector was blind shape-proven against the real Postmark API: every endpoint it declares answered measurably differently from a deliberately bogus control request, without any account or credential involved. It is Beta: proven against the live API surface, not yet run with a real credential.