How to Query Live Presto 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 Presto, configuring the connection to Presto, and interacting with your live Presto data from Perplexity Desktop.
About Presto Data Integration
Accessing and integrating live data from Trino and Presto SQL engines has never been easier with CData. Customers rely on CData connectivity to:
- Access data from Trino v345 and above (formerly PrestoSQL) and Presto v0.242 and above (formerly PrestoDB)
- Read and write access all of the data underlying your Trino or Presto instances
- Optimized query generation for maximum throughput.
Presto and Trino allow users to access a variety of underlying data sources through a single endpoint. When paired with CData connectivity, users get pure, SQL-92 access to their instances, allowing them to integrate business data with a data warehouse or easily access live data directly from their preferred tools, like Power BI and Tableau.
In many cases, CData's live connectivity surpasses the native import functionality available in tools. One customer was unable to effectively use Power BI due to the size of the datasets needed for reporting. When the company implemented the CData Power BI Connector for Presto they were able to generate reports in real-time using the DirectQuery connection mode.
Getting Started
Step 1: Download and install the CData MCP Server for Presto
- To begin, download the CData MCP Server for Presto
- 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 Presto.
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 Presto
-
After installation, you can open the CData MCP Server for Presto 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_presto") and click "OK"
-
Enter the appropriate connection properties in the configuration wizard.
Set the Server and Port connection properties to connect, in addition to any authentication properties that may be required.
To enable TLS/SSL, set UseSSL to true.
Authenticating with LDAP
In order to authenticate with LDAP, set the following connection properties:
- AuthScheme: Set this to LDAP.
- User: The username being authenticated with in LDAP.
- Password: The password associated with the User you are authenticating against LDAP with.
Authenticating with Kerberos
In order to authenticate with KERBEROS, set the following connection properties:
- AuthScheme: Set this to KERBEROS.
- KerberosKDC: The Kerberos Key Distribution Center (KDC) service used to authenticate the user.
- KerberosRealm: The Kerberos Realm used to authenticate the user with.
- KerberosSPN: The Service Principal Name for the Kerberos Domain Controller.
- KerberosKeytabFile: The Keytab file containing your pairs of Kerberos principals and encrypted keys.
- User: The user who is authenticating to Kerberos.
- Password: The password used to authenticate to Kerberos.
- Click "Connect" to authenticate with Presto.
- 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 Presto MCP").
In the Command box, enter the absolute path to your MCP Server executable.
For example:
/Applications/CData MCP Server for Presto.app/Contents/Payload/jre/Contents/Home/bin/java \ -jar /Applications/CData MCP Server for Presto.app/Contents/Payload/lib/cdata.mcp.presto.jar \ cdata_presto
- Click Save.
Your MCP Server should now appear in the connector list with a "Running" status
Step 4: Query Your Live Presto 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 Presto data.
For example:
"List all the tables available in my Presto data connection."
Connect your AI to your Presto 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.