How to Query Live HubDB Data in Claude Desktop

Model Context Protocol (MCP) is an emerging, open-source standard for connecting LLMs with external services and data sources. Through MCP Servers, AI clients can perform actions like opening Jira tickets, posting Slack messages, committing GitHub branches and more. With CData Code Assist MCP, these capabilities expand exponentially.

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 Claude Desktop.

In this article, we guide the reader through installing CData Code Assist MCP for HubDB, configuring the connection to HubDB, and asking questions of the data in Claude Desktop.

Prerequisites

You need to download Claude Desktop (download) and create an account before continuing.

Overview

Here's a quick overview of the steps:

1. Download and install the CData Code Assist MCP for HubDB
2. Configure the connection to HubDB
3. Ask questions about the data in Claude Desktop

Step 1: Download and install CData Code Assist MCP

1. To begin, navigate to https://www.cdata.com/solutions/codeassist/ and download the CData Code Assist MCP for HubDB. 👁 Downloading the CData Code Assist MCP installer
   
2. Find and double-click the installer to begin the installation. 👁 Running the installer for CData Code Assist MCP (Google Sheets is shown.)
   
3. Follow the prompts to complete the installation. 👁 Completing the CData Code Assist MCP installation (Google Sheets is shown).
   

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

Step 2: Configure the connection to HubDB

1. After installation, the Code Assist MCP configuration wizard should open automatically. 👁 The Code Assist MCP configuration wizard.
   

   NOTE: If the wizard does not open automatically, search for "CData Code Assist MCP" in the Windows search bar and double-click the application. 👁 Opening the Code Assist MCP configuration wizard (Google Sheets is shown).
   

2. Click the dropdown menu in MCP Configuration > Configuration Name and select "
3. Name the configuration (e.g. "cdatahubdb") and click "OK."

   NOTE: This name is used as the name for the MCP server and as the prefix for all of the MCP Server's tools.

   👁 Naming the configuration.
   

4. Connecting to HubDB

   There are two authentication methods available for connecting to HubDB data source: OAuth Authentication with a public HubSpot application and authentication with a Private application token.

   Using a Custom OAuth App

   AuthScheme must be set to "OAuth" in all OAuth flows. Be sure to review the Help documentation for the required connection properties for you specific authentication needs (desktop applications, web applications, and headless machines).

   Follow the steps below to register an application and obtain the OAuth client credentials:

   1. Log into your HubSpot app developer account.
      • Note that it must be an app developer account. Standard HubSpot accounts cannot create public apps.
   2. On the developer account home page, click the Apps tab.
   3. Click Create app.
   4. On the App info tab, enter and optionally modify values that are displayed to users when they connect. These values include the public application name, application logo, and a description of the application.
   5. On the Auth tab, supply a callback URL in the "Redirect URLs" box.
      • If you're creating a desktop application, set this to a locally accessible URL like http://localhost:33333.
      • If you are creating a Web application, set this to a trusted URL where you want users to be redirected to when they authorize your application.
   6. Click Create App. HubSpot then generates the application, along with its associated credentials.
   7. On the Auth tab, note the Client ID and Client secret. You will use these later to configure the driver.

   8. Under Scopes, select any scopes you need for your application's intended functionality.

      A minimum of the following scopes is required to access tables:

      • hubdb
      • oauth
      • crm.objects.owners.read
   9. Click Save changes.
   10. Install the application into a production portal with access to the features that are required by the integration.
       • Under "Install URL (OAuth)", click Copy full URL to copy the installation URL for your application.
       • Navigate to the copied link in your browser. Select a standard account in which to install the application.
       • Click Connect app. You can close the resulting tab.

   Using a Private App

   To connect using a HubSpot private application token, set the AuthScheme property to "PrivateApp."

   You can generate a private application token by following the steps below:

   1. In your HubDB account, click the settings icon (the gear) in the main navigation bar.
   2. In the left sidebar menu, navigate to Integrations > Private Apps.
   3. Click Create private app.
   4. On the Basic Info tab, configure the details of your application (name, logo, and description).
   5. On the Scopes tab, select Read or Write for each scope you want your private application to be able to access.
   6. A minimum of hubdb and crm.objects.owners.read is required to access tables.
   7. After you are done configuring your application, click Create app in the top right.
   8. Review the info about your application's access token, click Continue creating, and then Show token.
   9. Click Copy to copy the private application token.

   To connect, set PrivateAppToken to the private application token you retrieved.

   Enter the appropriate connection properties in the configuration wizard.

   👁 Configuring the Server to connect with a specific Spreadsheet.
   
5. Click "Connect" to authenticate with HubDB through OAuth. 👁 Authenticating with Google
   

   NOTE: The configuration wizard should open your browser and ask you to sign into HubDB. If your browser does not open, close the configuration wizard and re-open the application using "Run as Administrator" (see below).

   👁 Running the configuration wizard with elevated permissions.
   
6. Finally, click "Save Configuration" to save the configuration. 👁 Saving the Code Assist MCP configuration.
   

   NOTE: This saves the configuration details to a separate file and updates the Claude Desktop configuration file (claude_desktop_config.json) to start Code Assist MCP when the Claude Desktop client starts.

With Code Assist MCP configured, you are ready to start asking questions of your live data from Claude.

Step 3: Ask AI for answers from live HubDB data

Now that we have installed Code Assist MCP and configured a connection, we are ready to start with HubDB data in Claude Desktop.

1. Open Claude Desktop. It may take a moment for Code Assist MCP to start, but you will see the list of servers and tools available in the Claude interface (look for the settings icon below the prompt bar). 👁 The MCP servers menu showing available connections in Claude Desktop
   

   You can individually enable and disable specific tools by clicking on the server name. 👁 The expanded tool list for Code Assist MCP in Claude Desktop
   

2. Now that you have connected, you can ask Claude questions about the HubDB data. For example: "Can you give me a quantitative analysis about my closed-won opportunities by industry?"

   NOTE: Claude may need to explore the HubDB data to make sense of it before it can begin answering questions of the data. The tabular model presented by CData alongside the database tools available simplify the data exploration and analysis for an LLM.

   👁 Claude Desktop displaying a quantitative analysis of live data
   

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 HubDB data during development. When you're ready to move to production, CData HubDB 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.