How to Query Live JSON Services in Perplexity MacOS Desktop

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

Model Context Protocol (MCP) is an emerging, open-source standard for connecting LLMs with external services and enterprise data sources. Using MCP Servers, AI clients such as Perplexity Desktop can securely interact with applications and data, performing actions, retrieving live information, and enabling natural language access to data.

CData Code Assist MCP provides schema-aware context to AI tools — whether you're using it for AI-assisted code generation in IDEs like Cursor, or for querying live data through chat interfaces like Perplexity Desktop.

In this article, we guide you through installing CData Code Assist MCP for JSON, configuring the connection to JSON, and interacting with your live JSON services from Perplexity Desktop.

Step 1: Download and install CData Code Assist MCP for JSON

1. To begin, download CData Code Assist MCP for JSON 👁 Downloading the CData Code Assist MCP installer
   
2. Find and double-click the installer to begin the installation
3. Drag the Code Assist MCP app into the Applications folder 👁 Completing the Code Assist MCP installation
   

When the installation is complete, you are ready to configure Code Assist MCP by connecting to JSON.

NOTE: Since you downloaded the application from the internet and not the Apple App Store, you may see a warning that the application was not opened because Apple could not verify its security. You may continue with the installation.

Installing a trusted, unverified App

CData's solutions are trusted across the globe by some of the largest software vendors in the world. That said, if you have any concerns about continuing, please consult with your IT and/or security team.

1. In the warning message that pops up, click "Done"
2. Open "System Settings" on your machine and navigate to the "Privacy & Security" page
👁 Dismissing the notification

3. Scroll down to the "Security" section and click "Open Anyway" 👁 Installing a trusted, unverified App
   
4. Authorize the installation (passkey or password) 👁 Authorizing the installation
   

Step 2: Configure the Connection to JSON

1. After installation, you can open CData Code Assist MCP for JSON from the Applications folder on your mac 👁 The Code Assist MCP configuration wizard
   
2. Click the dropdown menu in MCP Configuration > Configuration Name and select "new configuration" 👁 Creating a new configuration
   
3. Name the configuration (e.g. "cdata_json") and click "OK" 👁 Naming the configuration
   

4. Enter the appropriate connection properties in the configuration wizard.

   See the Getting Started chapter in the data provider documentation to authenticate to your data source: The data provider models JSON APIs as bidirectional database tables and JSON files as read-only views (local files, files stored on popular cloud services, and FTP servers). The major authentication schemes are supported, including HTTP Basic, Digest, NTLM, OAuth, and FTP. See the Getting Started chapter in the data provider documentation for authentication guides.

   After setting the and providing any authentication values, set to more closely match the data representation to the structure of your data.

   The 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 JSON 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 JSON 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.

   👁 Configuring the Server connection.
   
5. Click "Connect" to authenticate with JSON.
6. Click "Save Configuration" to save the configuration 👁 Saving the Code Assist MCP configuration
   

With Code Assist MCP configured, you are ready to connect it to Perplexity Desktop.

Step 3: Connect Code Assist MCP to Perplexity Desktop

1. Download the Perplexity Desktop application for macOS and sign in with your Pro or Premium 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 👁 Downloading Perplexity Helper App
   
3. After restarting, return to Settings > Connectors and click Add Connector
4. Select the Simple tab and assign a name for the connector (e.g., "CData JSON"). In the Command box, enter the absolute path to the Code Assist MCP executable.

   For example:

   	/Applications/CData Code Assist MCP for JSON.app/Contents/Payload/jre/Contents/Home/bin/java \
   	-jar /Applications/CData Code Assist MCP for JSON.app/Contents/Payload/lib/cdata.mcp.json.jar \
   	cdata_json
   

   👁 Providing the MCP server command
   
5. Click Save. Code Assist MCP should now appear in the connector list with a "Running" status 👁 Connector successfully running
   

Step 4: Query Your Live JSON services in Perplexity Desktop

1. Open a new chat in Perplexity Desktop. Click the Sources toggle and enable Code Assist MCP 👁 Selecting Code Assist MCP as a source
   
2. Start asking questions about your JSON services. For example:

   "List all the tables available in my JSON services connection."

   👁 Querying live data through MCP
   

Build with Code Assist MCP. Deploy with CData Drivers.

Download Code Assist MCP for free and give your AI tools schema-aware access to live JSON services during development. When you're ready to move to production, CData JSON Drivers deliver the same SQL-based access with enterprise-grade performance, security, and reliability.

Visit the CData Community to share insights, ask questions, and explore what's possible with MCP-powered AI workflows.