Integrate Open WebUI with Live Okta Data via CData Connect AI

Open WebUI is an open-source, self-hosted AI chat platform that brings together hosted LLM APIs and locally served models under a single, customizable interface. It supports the Model Context Protocol (MCP) through its tool server framework, allowing you to configure external tools and data sources so that chats can reach beyond the model's training data and interact with live systems.

By integrating Open WebUI with CData Connect AI through the built-in MCP Server, Open WebUI gains governed, real-time access to live Okta data. This enables users to list catalogs, explore schemas, and query records from Okta data using natural language prompts, with all data access running securely against authorized sources.

This article explains how to configure Okta connectivity in Connect AI, generate the required personal access token, install Open WebUI, register the Connect AI MCP Server, configure an LLM provider, and verify the integration by querying live Okta data from the Open WebUI chat interface.

Step 1: Configure Okta connectivity for Open WebUI

Connectivity to Okta from Open WebUI is made possible through Connect AI's Remote MCP Server. To interact with Okta data from Open WebUI, start by creating and configuring a Okta connection in Connect AI.

1. Log into Connect AI, click Sources, and then click Add Connection

2. Select Okta from the Add Connection panel

3. Enter the necessary authentication properties to connect to Okta.

   To connect to Okta, set the Domain connection string property to your Okta domain.

   You will use OAuth to authenticate with Okta, so you need to create a custom OAuth application.

   Creating a Custom OAuth Application

   From your Okta account:

   1. Sign in to your Okta developer edition organization with your administrator account.
   2. In the Admin Console, go to Applications > Applications.
   3. Click Create App Integration.
   4. For the Sign-in method, select OIDC - OpenID Connect.
   5. For Application type, choose Web Application.
   6. Enter a name for your custom application.
   7. Set the Grant Type to Authorization Code. If you want the token to be automatically refreshed, also check Refresh Token.
   8. Set the callback URL:
      • For desktop applications and headless machines, use http://localhost:33333 or another port number of your choice. The URI you set here becomes the CallbackURL property.
      • For web applications, set the callback URL to a trusted redirect URL. This URL is the web location the user returns to with the token that verifies that your application has been granted access.
   9. In the Assignments section, either select Limit access to selected groups and add a group, or skip group assignment for now.
   10. Save the OAuth application.
   11. The application's Client Id and Client Secret are displayed on the application's General tab. Record these for future use. You will use the Client Id to set the OAuthClientId and the Client Secret to set the OAuthClientSecret.
   12. Check the Assignments tab to confirm that all users who must access the application are assigned to the application.
   13. On the Okta API Scopes tab, select the scopes you wish to grant to the OAuth application. These scopes determine the data that the app has permission to read, so a scope for a particular view must be granted for the driver to have permission to query that view. To confirm the scopes required for each view, see the view-specific pages in Data Model < Views in the Help documentation.
   
4. Click Save & Test
5. Navigate to the Permissions tab and update user-based permissions

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Open WebUI. It is best practice to create a separate PAT for each integration to maintain granular access control.

1. Click the gear icon () at the top right of the Connect AI app to open Settings
2. On the Settings page, go to the Access Tokens section and click Create PAT
3. Give the PAT a descriptive name and click Create

4. Copy the token when displayed and store it securely. It will not be shown again

With the Okta connection configured and a PAT generated, Open WebUI can now connect to Okta data through Connect AI.

Step 2: Install Open WebUI and configure Connect AI MCP

Next, install Open WebUI locally and configure the Connect AI Remote MCP Server as a tool server so that the chat interface can discover and call live data tools through Connect AI.

1. Install Open WebUI by following the official Quick Start guide
2. Once the installation is complete, start Open WebUI and open it in your browser to access the chat interface
3. Click your profile icon in the top right and select Admin Panel
4. In the top navigation bar of the Admin Panel, click Settings
5. Select Integrations from the left menu, then click the icon next to Manage Tool Servers to add a new connection
6. In the Add Connection panel, configure the server with the following values:
   • Type: MCP Streamable HTTP
   • Name: CData MCP, or any name of your choice
   • ID: cdata-mcp
   • URL: https://mcp.cloud.cdata.com/mcp
   • Auth: None
7. Expand the Advanced section and paste the following JSON into the Headers field:

   {
       "Authorization": "Basic your_base64_encoded_email_PAT",
       "Content-Type": "application/json"
   }
   		

   Note: Open WebUI will use Basic authentication with Connect AI. Combine your Connect AI user email and the PAT you created earlier in the format email:PAT, base64 encode the combined string, and prefix it with Basic. For example, given [email protected]:ABC123...XYZ789, the Authorization header value becomes something like: Basic dXNlckBkb21haW4uY29tOkFCQzEyMy4uLlhZWjc4OQ==

   
8. Click Save to register the tool server

Enable the MCP server and configure an LLM provider

Open WebUI requires at least one LLM provider to power the chat. Enable the MCP server from the chat input and configure an API key for your preferred provider so the model can interpret prompts and call MCP tools through Connect AI.

1. Return to the chat interface, click the Integrations icon at the bottom of the chat input, select Tools, and toggle CData MCP on to expose the tools to the chat
2. At the top of the chat, click the model selector and choose your preferred LLM provider and model. Add your provider API key when prompted so the model can be used in the chat

With the MCP server and an LLM provider configured, Open WebUI is ready to query live Okta data through Connect AI.

Step 3: Query live Okta data from Open WebUI

With the integration complete, use the Open WebUI chat input to interact with live Okta data through natural language prompts handled by the configured LLM.

1. With the CData MCP server enabled and a model selected, type a prompt in the chat input, for example:
   • List all catalogs in my cdata mcp
   • Show the available schemas and tables for Okta
   • Query the top 5 records from a table in Okta data
2. Open WebUI calls the Connect AI MCP Server and returns live results from Okta data

At this point, your Open WebUI instance communicates with the Connect AI MCP Server and retrieves live Okta data through remote MCP tools directly from the chat interface.

Get CData Connect AI

To acess hundreds of SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today! Download a free 14-day trial of CData Connect AI today, and as always, our world-class Support Team is available to assist you with any questions you may have.