Get started

Data & AI · wired today

Drive Typesense with governed agents

Models and datasets are infrastructure now, and agents need eyes on them. The Typesense connector is one of 205 executable connectors and gives agents 6 read-only tools, with the credential held in the vault and every call receipted.

What agents can run against Typesense

ToolWhat it does
healthCheck whether the Typesense node is healthy and accepting requests
get_debugGet the Typesense node version and cluster state
list_collectionsList the collections on this Typesense node with their document counts
get_collectionGet one Typesense collection by name, including its field schema
search_collectionSearch documents in one Typesense collection. Use q=* to list documents without a text query
list_aliasesList the collection aliases configured on this Typesense node

Every tool above is read-only. Write surfaces ship only after live testing, and always behind approval gates.

What the Typesense connector needs

You provide host, API key, port from your Typesense 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: Typesense's own API documentation ↗ covers creating and scoping the credential.

How proven is this?

LIVE-PROVEN: every tool on this page was executed with real credentials against a real running Typesense instance (provisioned for the proof, then destroyed), and every call answered successfully. The strongest proof class a connector can carry before it runs inside your own deployment.

Typesense integration FAQ

What can Quox agents do with Typesense?

Agents can run 6 read-only tools against Typesense: health, get debug, list collections, get collection, search collection and more. Every call is receipted in the evidence trail.

What does the Typesense integration need?

You provide host, API key, port from your Typesense 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 Typesense 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 Typesense connector?

LIVE-PROVEN: every tool on this page was executed with real credentials against a real running Typesense instance (provisioned for the proof, then destroyed), and every call answered successfully. The strongest proof class a connector can carry before it runs inside your own deployment.