Data & AI · wired today
Stability AI, wired into your agent workforce
Models and datasets are infrastructure now, and agents need eyes on them. The Stability AI connector is one of 205 executable connectors and gives agents 3 read-only tools, with the credential held in the vault and every call receipted.
Connecting Stability AI takes one credential
You provide API key from your Stability AI account; Quox sends it as a bearer token. 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: Stability AI's own API documentation ↗ covers creating and scoping the credential.
What agents can run against Stability AI
accountGet the Stability AI account the API key belongs to: user id, email and every organisation the user is a member of
balanceGet the credit balance of the Stability AI account or organisation the API key is scoped to
list_enginesList the Stability AI engines (models) available to the account, with the content type each one produces
Every tool above is read-only. Write surfaces ship only after live testing, and always behind approval gates.
How proven is this?
This connector was blind shape-proven against the real Stability AI 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.
Stability AI integration FAQ
What can Quox agents do with Stability AI?
Agents can run 3 read-only tools against Stability AI: account, balance, list engines. Every call is receipted in the evidence trail.
What does the Stability AI integration need?
You provide API key from your Stability AI account; Quox sends it as a bearer token. 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 Stability AI 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 Stability AI connector?
This connector was blind shape-proven against the real Stability AI 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.