How to Query Live Box Data 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.
In this article, we guide you through installing the CData MCP Server for Box, configuring the connection to Box, and interacting with your live Box data from Perplexity Desktop.
Step 1: Download and install the CData MCP Server for Box
- To begin, download the CData MCP Server for Box
- Find and double-click the installer to begin the installation
- Drag the CData MCP Server app into the Applications folder
When the installation is complete, you are ready to configure your MCP Server by connecting to Box.
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.
- In the warning message that pops up, click "Done"
- Open "System Settings" on your machine and navigate to the "Privacy & Security" page
- Scroll down to the "Security" section and click "Open Anyway"
- Authorize the installation (passkey or password)
Step 2: Configure the Connection to Box
-
After installation, you can open the CData MCP Server for Box from the Applications folder on your mac
- Click the dropdown menu in MCP Configuration > Configuration Name and select "new configuration"
- Name the configuration (e.g. "cdata_box") and click "OK"
-
Enter the appropriate connection properties in the configuration wizard.
Box uses the OAuth standard to authenticate. To authenticate to Box, obtain the OAuthClientId, OAuthClientSecret, and CallbackURL by registering an app. See the "Getting Started" chapter of the help documentation for a guide to using OAuth.
- Click "Connect" to authenticate with Box through OAuth.
- Click "Save Configuration" to save the MCP server
With your MCP Server configured, you are ready to connect it to Perplexity Desktop.
Step 3: Connect the MCP Server to Perplexity Desktop
- Download the Perplexity Desktop application for macOS and sign in with your Pro or Premium account
- 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
- After restarting, return to Settings > Connectors and click Add Connector
- Select the Simple tab and assign a name for the connector (e.g., "CData Box MCP").
In the Command box, enter the absolute path to your MCP Server executable.
For example:
/Applications/CData MCP Server for Box.app/Contents/Payload/jre/Contents/Home/bin/java \ -jar /Applications/CData MCP Server for Box.app/Contents/Payload/lib/cdata.mcp.box.jar \ cdata_box
- Click Save.
Your MCP Server should now appear in the connector list with a "Running" status
Step 4: Query Your Live Box data in Perplexity Desktop
- Open a new chat in Perplexity Desktop.
Click the Sources toggle and enable your MCP Server
- Start asking questions about your Box data.
For example:
"List all the tables available in my Box data connection."
Connect your AI to your Box data today!
CData MCP Servers make it simple to connect Perplexity and other LLM clients to real-time enterprise data. Download a free, 30-day trial and join the CData Community to share insights, ask questions, and help shape the future of enterprise-ready AI.