AI OAuth-Based Gateway

Configure AI gateway access and OAuth-based authentication for custom LLMs.

This documentation describes a preview version of the feature, which is not fully functional yet. Some capabilities may be incomplete or subject to change.

Use this feature for evaluation purposes. If you have any questions, contact the Emporix Support Team or post directly in the Community.

Use AI OAuth to create a reusable authentication configuration for self-hosted or gateway-backed LLMs. An OAuth-managed gateway layer may be necessary when your company's security and compliance policy does not allow sending prompts directly to public LLM providers. The same configuration can be reused across external models.

Choosing the provider connection depends on how your company wants to manage LLM access:

• Use a direct provider connection when your company allows direct access to the provider and a token-based setup is sufficient.
• Use a self-hosted option when the model endpoint is managed within your own infrastructure, or when you need an additional governance layer between Emporix and the LLM provider. Self-hosted LLMs can use the custom OAuth configuration described on this page.

Supported authentication option

You can enable the following authentication method:

• OAuth 2.0 client credentials – Use client_credentials when the agent authenticates server-to-server on its own behalf. This is the standard choice for managed gateway or self-hosted model connections that do not require end-user consent during runtime.

Configure reusable OAuth access

Create the OAuth configuration once and reuse it across multiple agents that connect to the same gateway or provider.

Prerequisites

Gather the OAuth details from your gateway provider:

• Required – Client ID and Token URL
• Optional – Scopes, if your gateway provider requires them
• Optional – a Client Secret stored as an AI Token

1

Navigate to AI OAuth

In the Management Dashboard, go to Agentic AI -> AI OAuth and choose Add new OAuth to start configuration.

2

Provide the authentication credentials

Fill in the details for your OAuth configuration:

• OAuth ID – Enter a unique identifier for the configuration.
• Client ID – Enter the client ID provided by the authentication provider.
• Grant Type – Choose Client credentials.
• Token URL – Enter the URL used to issue the access token.
• Scopes – Optional. Enter the scopes required for restricted LLM access, if your gateway provider uses them.
• Client Secret – Optional. Select a token defined in AI Tokens.
• Enabled – Leave the toggle on. Toggle it off only when you want to disable the configuration temporarily.

When done, choose Save.

OAuth configuration with client credentials grant_type

3

Use the OAuth configuration in the custom agent

The OAuth configuration is ready to use with an agent that uses a self-hosted LLM. The agent references the configuration instead of embedding secrets directly in the agent definition.

1. In the Management Dashboard, go to Agentic AI -> AI Agents.
2. Open the Model tab.
3. Choose Self-hosted Ollama or Self-hosted vLLM.
4. Toggle on Use OAuth authentication.
5. Select the OAuth configuration you created.

Configuring self-hosted LLM model with OAuth config

For the full agent creation flow, see AI Agents.

Reusable OAuth configuration reduces duplication and makes secret rotation easier because multiple agents can reference the same authentication setup.