Build Voice Agents in ElevenLabs with access to Live Zuora 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 Zuora 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 Zuora 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 Zuora data during conversations.

Step 1: Configure Zuora connectivity for ElevenLabs

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

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

2. Select Zuora from the Add Connection panel

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

   Zuora uses the OAuth standard to authenticate users. See the online Help documentation for a full OAuth authentication guide.

   Configuring Tenant property

   In order to create a valid connection with the provider you need to choose one of the Tenant values (USProduction by default) which matches your account configuration. The following is a list with the available options:

   • USProduction: Requests sent to https://rest.zuora.com.
   • USAPISandbox: Requests sent to https://rest.apisandbox.zuora.com"
   • USPerformanceTest: Requests sent to https://rest.pt1.zuora.com"
   • EUProduction: Requests sent to https://rest.eu.zuora.com"
   • EUSandbox: Requests sent to https://rest.sandbox.eu.zuora.com"

   Selecting a Zuora Service

   Two Zuora services are available: Data Query and AQuA API. By default ZuoraService is set to AQuADataExport.

   DataQuery

   The Data Query feature enables you to export data from your Zuora tenant by performing asynchronous, read-only SQL queries. We recommend to use this service for quick lightweight SQL queries.

   Limitations
   • The maximum number of input records per table after filters have been applied: 1,000,000
   • The maximum number of output records: 100,000
   • The maximum number of simultaneous queries submitted for execution per tenant: 5
   • The maximum number of queued queries submitted for execution after reaching the limitation of simultaneous queries per tenant: 10
   • The maximum processing time for each query in hours: 1
   • The maximum size of memory allocated to each query in GB: 2
   • The maximum number of indices when using Index Join, in other words, the maximum number of records being returned by the left table based on the unique value used in the WHERE clause when using Index Join: 20,000

   AQuADataExport

   AQuA API export is designed to export all the records for all the objects ( tables ). AQuA query jobs have the following limitations:

   Limitations
   • If a query in an AQuA job is executed longer than 8 hours, this job will be killed automatically.
   • The killed AQuA job can be retried three times before returned as failed.
   
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 Zuora connection configured and a PAT generated, ElevenLabs can now connect to Zuora 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 350+ 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 Zuora 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 Zuora"
   • "Query recent records from Zuora 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 Zuora 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 350+ SaaS, Big Data, and NoSQL sources through secure, AI-ready interfaces, try CData Connect AI today.