Data & AI · wired today
Drive DeepL with governed agents
Models and datasets are infrastructure now, and agents need eyes on them. The DeepL 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.
What agents can run against DeepL
| Tool | What it does |
|---|---|
get_usage | Get DeepL API usage and limits for the current billing period (characters translated against the account limit) |
list_glossaries | List the glossaries owned by this DeepL account, with their language pair, entry count and readiness |
glossary_language_pairs | List the source and target language pairs DeepL supports for glossaries |
Every tool above is read-only. Write surfaces ship only after live testing, and always behind approval gates.
What the DeepL connector needs
You provide API key from your DeepL 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: DeepL's own API documentation ↗ covers creating and scoping the credential.
How proven is this?
This connector was blind shape-proven against the real DeepL 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.
DeepL integration FAQ
What can Quox agents do with DeepL?
Agents can run 3 read-only tools against DeepL: get usage, list glossaries, glossary language pairs. Every call is receipted in the evidence trail.
What does the DeepL integration need?
You provide API key from your DeepL 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 DeepL 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 DeepL connector?
This connector was blind shape-proven against the real DeepL 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.