Query Live XML Data in Perplexity Desktop via CData Connect AI

Perplexity is an AI-powered research and answer engine that combines web search, structured data, and connected tools through a unified conversational interface. With Perplexity Desktop for macOS, you can bring external data sources directly into your workflow using MCP, enabling fast, context-aware insights powered by live data.

Integrating Perplexity Desktop with CData Connect AI via its built-in MCP connector allows the AI to query, explore, and reason over live XML data without copying data out of its source system. The result is a research experience where you can ask questions about your governed enterprise data directly from Perplexity Desktop.

This article outlines how to configure XML connectivity in Connect AI, generate the required access token, register Connect AI's MCP Server in Perplexity Desktop, and then use the chat interface to explore live XML data.

Step 1: Configure XML connectivity for Perplexity Desktop

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

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

2. Select XML from the Add Connection panel

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

   Connecting to Local or Cloud-Stored (Box, Google Drive, Amazon S3, SharePoint) XML Files

   CData Drivers let you work with XML files stored locally and stored in cloud storage services like Box, Amazon S3, Google Drive, or SharePoint, right where they are.

   Setting connection properties for local files

   Set the URI property to local folder path.

   Setting connection properties for files stored in Amazon S3

   To connect to XML file(s) within Amazon S3, set the URI property to the URI of the Bucket and Folder where the intended XML files exist. In addition, at least set these properties:

   • AWSAccessKey: AWS Access Key (username)
   • AWSSecretKey: AWS Secret Key

   Setting connection properties for files stored in Box

   To connect to XML file(s) within Box, set the URI property to the URI of the folder that includes the intended XML file(s). Use the OAuth authentication method to connect to Box.

   Dropbox

   To connect to XML file(s) within Dropbox, set the URI proprerty to the URI of the folder that includes the intended XML file(s). Use the OAuth authentication method to connect to Dropbox. Either User Account or Service Account can be used to authenticate.

   SharePoint Online (SOAP)

   To connect to XML file(s) within SharePoint with SOAP Schema, set the URI proprerty to the URI of the document library that includes the intended XML file. Set User, Password, and StorageBaseURL.

   SharePoint Online REST

   To connect to XML file(s) within SharePoint with REST Schema, set the URI proprerty to the URI of the document library that includes the intended XML file. StorageBaseURL is optional. If not set, the driver will use the root drive. OAuth is used to authenticate.

   Google Drive

   To connect to XML file(s) within Google Drive, set the URI property to the URI of the folder that includes the intended XML file(s). Use the OAuth authentication method to connect and set InitiateOAuth to GETANDREFRESH.

   The DataModel property is the controlling property over how your data is represented into tables and toggles the following basic configurations.

   • Document (default): Model a top-level, document view of your XML data. The data provider returns nested elements as aggregates of data.
   • FlattenedDocuments: Implicitly join nested documents and their parents into a single table.
   • Relational: Return individual, related tables from hierarchical data. The tables contain a primary key and a foreign key that links to the parent document.

   See the Modeling XML Data chapter for more information on configuring the relational representation. You will also find the sample data used in the following examples. The data includes entries for people, the cars they own, and various maintenance services performed on those cars.

   
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 Perplexity Desktop. 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. The personal access token is only visible at creation, so be sure to copy it and store it securely for future use

Create an OAuth App in CData Connect AI

Perplexity Desktop uses OAuth 2.0 to authenticate users against the CData Connect AI MCP Server. This requires creating an OAuth App in your CData Connect AI account.

1. Click the Gear icon () in the top-right corner of Connect AI to open Settings
2. Navigate to OAuth Apps and click + Create App. The Create OAuth App dialog appears
3. Fill in the following fields:
   • Name — Enter a descriptive name (e.g.,

     PerplexityOAuth

     )
   • Authentication Flow — Select User-based (Authorization Code)
   • Callback URL — Enter the callback URL provided by Perplexity Desktop when adding the connector
   
4. Click Confirm. CData Connect AI generates a Client ID and Client Secret
5. Copy both values and store them securely. You will need them in Step 2

With the XML connection configured and an OAuth App created, Perplexity Desktop can now connect to XML data through Connect AI.

Step 2: Configure Connect AI in Perplexity Desktop

Next, register the CData Connect AI MCP Server as a custom remote connector in Perplexity Desktop. This feature requires a Perplexity Pro, Max, or Enterprise account and the macOS desktop app. Once configured, Perplexity's AI can call the tools exposed by CData Connect AI to access live XML data.

1. Download the Perplexity Desktop application for macOS and sign in with your Pro, Max, or Enterprise account
2. Open Settings > Connectors. If the Perplexity Helper App is not installed, you will be prompted to download it. Install the Helper App, then restart Perplexity Desktop
3. After restarting, return to Settings > Connectors and click Add Custom Remote Connector
4. In the URL field, enter the CData Connect AI MCP endpoint:

   https://mcp.cloud.cdata.com/mcp

   
5. For the authentication method, select OAuth. Enter the Client ID and Client Secret from the OAuth App created in Step 1, and click Connect
6. You will be redirected to CData Connect AI to authorize the connection. Sign in and click Allow to grant Perplexity access
7. After successful authorization, you will be redirected back to Perplexity Desktop. The connector should now appear in the list with an active status

Step 3: Query your live XML data from Perplexity Desktop

1. Open a new chat in Perplexity Desktop. Click the Sources toggle and enable your CData connector
2. Start asking questions about your XML data. For example:

   "List all the tables available in my XML data connection."

   
3. Try additional queries such as:
   • "Show the available schemas in XML."
   • "Retrieve the top 10 records from the Account table."
   • "Summarize the high-priority open opportunities in XML."

Perplexity Desktop is now fully integrated with the CData Connect AI MCP Server and can reason over live XML data directly from the chat interface.

Get CData Connect AI

To access hundreds of SaaS, Big Data, and NoSQL sources directly from your AI tools, try CData Connect AI today!