Skip to main content
Connections brings gateway accounts and direct model credentials into one workspace view. Select an account to review its access checks, model resources, routing and recorded activity. Workspace administrators manage credentials; members use the resources their work is already permitted to access. A saved credential has not necessarily passed an access check. An old successful check is shown as history, and unavailable inventory remains unavailable rather than an empty success. Model pricing and evidence status remain separate facts. The catalog distinguishes guided setup through installed services from unavailable integration blueprints. A catalog entry does not establish live compatibility. Databricks guided setup covers model serving. Slack setup covers notifications. Private execution requires an enrolled environment and support for the exact operation; entering a private address does not establish connectivity. Replacing a direct credential updates EvalGate’s stored key. Revoke the old key with the provider separately. Removing EvalGate access does not delete an upstream account, index, collection or model. This surface is a source candidate until its deployment is verified. New knowledge transports, reviewed resource grants and one-time budget approvals remain unavailable. Existing runtime policy, reservations and evidence services continue to govern work. Automation uses the same read contracts:
The TypeScript and Python OpenAPI clients expose listConnections and getConnectionCatalog. MCP clients use connections.list and connections.catalog. None of these reads returns a secret or grants permission to read content or invoke a model.