How to Query Live RabbitMQ 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.

CData MCP Server 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 API Driver for MCP Server, configuring the connection to RabbitMQ, and interacting with your live RabbitMQ data from Perplexity Desktop.

Step 1: Download and install CData API Driver for MCP Server

1. To begin, download CData API Driver for MCP Server
2. Find and double-click the installer to begin the installation
3. Drag the MCP Server app into the Applications folder

When the installation is complete, you are ready to configure MCP Server by connecting to RabbitMQ.

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

3. Scroll down to the "Security" section and click "Open Anyway"
4. Authorize the installation (passkey or password)

Step 2: Configure the Connection to RabbitMQ

1. After installation, you can open CData API Driver for MCP Server from the Applications folder on your mac
2. Click the dropdown menu in MCP Configuration > Configuration Name and select "new configuration"
3. Name the configuration (e.g. "cdata_api") and click "OK"

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

   About RabbitMQ Management HTTP API

   RabbitMQ is an open-source message broker that supports multiple messaging protocols. The RabbitMQ Management HTTP API provides HTTP-based access to management and monitoring data for a RabbitMQ server. The API exposes information about virtual hosts, exchanges, queues, bindings, connections, channels, consumers, users, permissions, policies, and cluster-wide statistics.

   The Management plugin must be enabled on the RabbitMQ server for the HTTP API to be available. By default, the management interface listens on port 15672.

   Using Basic Authentication

   RabbitMQ Management HTTP API uses HTTP Basic authentication. You must supply the username and password of a RabbitMQ management user.

   To enable access to the management API:

   1. Ensure the RabbitMQ Management plugin is enabled on your server (rabbitmq-plugins enable rabbitmq_management).
   2. Use an existing management user or create one with the appropriate management tag (management, policymaker, monitoring, or administrator).
   3. Note the full base URL of your RabbitMQ Management HTTP API (e.g., http://localhost:15672).

   After configuring your RabbitMQ server, set the following connection properties to connect:

   • AuthScheme: Set this to Basic.
   • URL: Set this to the base URL of your RabbitMQ Management HTTP API (e.g., http://localhost:15672).
   • User: Set this to your RabbitMQ management username (e.g., guest).
   • Password: Set this to your RabbitMQ management password.

   Example connection string:

   Profile=C:\profiles\RabbitMQ.apip;AuthScheme=Basic;URL=http://localhost:15672;User=guest;Password=guest;
   

   Available Tables

   The RabbitMQ profile provides access to the following tables:

   • Overview - Cluster-wide statistics and information about the RabbitMQ node
   • Nodes - Information about individual nodes in the RabbitMQ cluster
   • NodeMemory - Detailed memory usage breakdown for a specific cluster node
   • Connections - List of all open AMQP connections to the broker
   • Channels - List of all open AMQP channels across all connections
   • Consumers - List of all consumers registered across all queues
   • Exchanges - List of exchanges declared across all virtual hosts
   • Queues - List of queues declared across all virtual hosts
   • Bindings - List of all bindings between exchanges and queues
   • VirtualHosts - List of virtual hosts configured on the broker
   • VhostPermissions - User permissions within a specific virtual host
   • Users - List of all RabbitMQ users
   • Permissions - Permission records for all users across all virtual hosts
   • TopicPermissions - Topic-level permission records for all users
   • Policies - List of policies applied to queues and exchanges in virtual hosts
   • OperatorPolicies - List of operator policies applied to queues in virtual hosts
   • Parameters - List of component parameters (e.g., federation, shovel) per virtual host
   • GlobalParameters - List of global parameters that apply across all virtual hosts
   • VhostLimits - Resource limits configured for specific virtual hosts
   • UserLimits - Resource limits configured for specific users
   • FeatureFlags - List of feature flags and their enabled/disabled state on the node
   • DeprecatedFeatures - List of deprecated features and their usage state
   • AuthAttempts - Authentication attempt statistics for the node
   • ClusterName - The name of the RabbitMQ cluster
   • WhoAmI - Information about the currently authenticated management user
   • ExchangeBindingsSource - Bindings for which a specific exchange is the source
   • ExchangeBindingsDestination - Bindings for which a specific exchange is the destination
   • QueueBindings - Bindings for a specific queue within a virtual host
   
5. Click "Connect" to authenticate with RabbitMQ.
6. Click "Save Configuration" to save the configuration

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

Step 3: Connect MCP Server 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
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 RabbitMQ"). In the Command box, enter the absolute path to the MCP Server executable.

   For example:

   	/Applications/CData API Driver for MCP Server.app/Contents/Payload/jre/Contents/Home/bin/java \
   	-jar /Applications/CData API Driver for MCP Server.app/Contents/Payload/lib/cdata.mcp.api.jar \
   	cdata_api
   

   
5. Click Save. MCP Server should now appear in the connector list with a "Running" status

Step 4: Query Your Live RabbitMQ data in Perplexity Desktop

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

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

   

Build with MCP Server. Deploy with CData Drivers.

Download MCP Server for free and give your AI tools schema-aware access to live RabbitMQ data during development. When you're ready to move to production, CData RabbitMQ 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.