Build Voice Agents in ElevenLabs with access to Live HubDB Data

ElevenLabs is a leading AI audio platform that enables developers to build conversational voice agents capable of natural, human-like interactions. The ElevenLabs Conversational AI platform allows you to create voice-powered assistants that can reason through tasks, respond dynamically, and interact with external systems in real time.

By integrating ElevenLabs with CData Connect AI through the MCP (Model Context Protocol), your voice agents gain the ability to query, analyze, and act on live HubDB data during conversations. This integration bridges ElevenLabs' conversational AI framework with the governed enterprise connectivity of CData Connect AI, ensuring all data access runs securely against authorized sources without manual data movement.

This article outlines the steps to configure HubDB connectivity in Connect AI, generate the required authentication credentials, register the Connect AI MCP Server in ElevenLabs, and verify that your voice agent can successfully interact with live HubDB data during conversations.

Step 1: Configure HubDB connectivity for ElevenLabs

Connectivity to HubDB from ElevenLabs is made possible through CData Connect AI's Remote MCP Server. To interact with HubDB data from your voice agents, start by creating and configuring a HubDB connection in CData Connect AI.

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

2. Select HubDB from the Add Connection panel

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

   There are two authentication methods available for connecting to HubDB data source: OAuth Authentication with a public HubSpot application and authentication with a Private application token.

   Using a Custom OAuth App

   AuthScheme must be set to "OAuth" in all OAuth flows. Be sure to review the Help documentation for the required connection properties for you specific authentication needs (desktop applications, web applications, and headless machines).

   Follow the steps below to register an application and obtain the OAuth client credentials:

   1. Log into your HubSpot app developer account.
      • Note that it must be an app developer account. Standard HubSpot accounts cannot create public apps.
   2. On the developer account home page, click the Apps tab.
   3. Click Create app.
   4. On the App info tab, enter and optionally modify values that are displayed to users when they connect. These values include the public application name, application logo, and a description of the application.
   5. On the Auth tab, supply a callback URL in the "Redirect URLs" box.
      • If you're creating a desktop application, set this to a locally accessible URL like http://localhost:33333.
      • If you are creating a Web application, set this to a trusted URL where you want users to be redirected to when they authorize your application.
   6. Click Create App. HubSpot then generates the application, along with its associated credentials.
   7. On the Auth tab, note the Client ID and Client secret. You will use these later to configure the driver.

   8. Under Scopes, select any scopes you need for your application's intended functionality.

      A minimum of the following scopes is required to access tables:

      • hubdb
      • oauth
      • crm.objects.owners.read
   9. Click Save changes.
   10. Install the application into a production portal with access to the features that are required by the integration.
       • Under "Install URL (OAuth)", click Copy full URL to copy the installation URL for your application.
       • Navigate to the copied link in your browser. Select a standard account in which to install the application.
       • Click Connect app. You can close the resulting tab.

   Using a Private App

   To connect using a HubSpot private application token, set the AuthScheme property to "PrivateApp."

   You can generate a private application token by following the steps below:

   1. In your HubDB account, click the settings icon (the gear) in the main navigation bar.
   2. In the left sidebar menu, navigate to Integrations > Private Apps.
   3. Click Create private app.
   4. On the Basic Info tab, configure the details of your application (name, logo, and description).
   5. On the Scopes tab, select Read or Write for each scope you want your private application to be able to access.
   6. A minimum of hubdb and crm.objects.owners.read is required to access tables.
   7. After you are done configuring your application, click Create app in the top right.
   8. Review the info about your application's access token, click Continue creating, and then Show token.
   9. Click Copy to copy the private application token.

   To connect, set PrivateAppToken to the private application token you retrieved.

   
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 ElevenLabs. 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 (e.g., "ElevenLabs Voice Agent") and click Create

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

With the HubDB connection configured and a PAT generated, ElevenLabs can now connect to HubDB data through Connect AI.

Step 2: Add the Connect AI MCP Server in ElevenLabs

ElevenLabs supports connecting to external MCP servers that use SSE (Server-Sent Events) or HTTP streamable transport. The CData Connect AI Remote MCP Server is compatible with this integration.

1. Log into the ElevenLabs platform and navigate to your agent dashboard
2. Go to Integrations and click + Add Integration to access the MCP server integrations section
3. Click on Custom MCP Server to add a new integration
4. Enter the following configuration:
   • Name: CData Connect AI
   • Description: Access live enterprise data from hundreds of sources
   • Server URL: https://mcp.cloud.cdata.com/sse
   • Secret Token: Leave empty (authentication is handled via headers)
   • HTTP Headers: Add a header with key Authorization and value Basic your_email:your_PAT
   
5. Replace your_email:your_PAT with your Connect AI login email and the Personal Access Token you created earlier. For example: Basic [email protected]:ABC123...XYZ789
6. Click Save to test the connection and retrieve available tools from Connect AI
7. The CData Connect AI MCP server is now available to assign to your voice agents

Step 3: Configure your Voice Agent to use Connect AI

With the MCP server registered, you can now add it to your ElevenLabs voice agents to enable real-time data access during conversations.

1. Create a new agent or edit an existing agent in the ElevenLabs dashboard
2. In the agent configuration, navigate to the Tools section
3. Add the CData Connect AI MCP server you configured in Step 2
4. Configure the tool approval mode based on your requirements:
   • Always Ask: The agent will request permission before each data query (recommended for sensitive data)
   • Fine-Grained: Set approval requirements per tool/action
   • No Approval: The agent can query data autonomously
5. Save your agent configuration

Step 4: Interact with live data through your Voice Agent

Your ElevenLabs voice agent can now access and query live HubDB data through the CData Connect AI MCP Server during conversations.

1. Start a conversation with your voice agent
2. Ask your agent data-related questions such as:
   • "What connections are available?"
   • "Show me the schemas for HubDB"
   • "Query recent records from HubDB data"
   • "Summarize our latest Data"
3. The agent will use the Connect AI MCP tools to retrieve live data and respond conversationally

Your ElevenLabs voice agent is now fully configured to access and query live HubDB data through the CData Connect AI Remote MCP Server, enabling real-time, data-driven voice interactions for your users.

Get CData Connect AI

To access hundreds of SaaS, Big Data, and NoSQL sources through secure, AI-ready interfaces, try CData Connect AI today.