Connect and Query Live Claude Compliance Data in Databricks with CData Connect AI

Databricks is a leading AI cloud-native platform that unifies data engineering, machine learning, and analytics at scale. Its powerful data lakehouse architecture combines the performance of data warehouses with the flexibility of data lakes. Integrating Databricks with CData Connect AI gives organizations live, real-time access to Claude Compliance data without the need for complex ETL pipelines or data duplication—streamlining operations and reducing time-to-insights.

In this article, we'll walk through how to configure a secure, live connection from Databricks to Claude Compliance using CData Connect AI. Once configured, you'll be able to access Claude Compliance data directly from Databricks notebooks using standard SQL—enabling unified, real-time analytics across your data ecosystem.

Overview

Here is an overview of the simple steps:

1. Step 1 — Connect and Configure: In CData Connect AI, create a connection to your Claude Compliance source, configure user permissions, and generate a Personal Access Token (PAT).
2. Step 2 — Query from Databricks: Install the CData JDBC driver in Databricks, configure your notebook with the connection details, and run SQL queries to access live Claude Compliance data.

Prerequisites

Before you begin, make sure you have the following:

1. An active Claude Compliance account.
2. A CData Connect AI account. You can log in or sign up for a free trial here.
3. A Databricks account. Sign up or log in here.

Step 1: Connect and Configure a Claude Compliance Connection in CData Connect AI

1.1 Add a Connection to Claude Compliance

CData Connect AI uses a straightforward, point-and-click interface to connect to available data sources.

1. Log into Connect AI, click Sources on the left, and then click Add Connection in the top-right.

2. Select "Claude Compliance" from the Add Connection panel.

3. Enter the necessary authentication properties to connect to Claude Compliance.

   The driver connects to Claude Compliance using a Compliance Access Key, the only supported authentication method. Set the following connection property:

   • APIKey: The Compliance Access Key you created.

   Creating a Compliance Access Key

   1. Enable the Compliance API for your organization.
   2. Sign in to claude.ai as a primary owner or organization owner and open Organization settings > API > Keys.
   3. Select Create Key and assign only the scopes your integration needs:
      • read:compliance_activities for Activities and the typed activity views.
      • read:compliance_org_data for organizations, roles, groups, and settings.
      • read:compliance_user_data for users, chats, files, projects, and downloads.
      • delete:compliance_user_data for the explicit Delete stored procedures.
   4. Create the key and copy it when it appears. The key starts with sk-ant-api01- and is shown only once.

   Optionally, set OrganizationUUID to limit organization-scoped views (such as OrganizationUsers and ComplianceRoles) to a single linked organization. If it is left empty, those views default to the first available organization and do not include data from all linked organizations.

   
4. Click Save & Test in the top-right.
5. Navigate to the Permissions tab on the Claude Compliance Connection page and update the user-based permissions based on your preferences.

1.2 Generate a Personal Access Token (PAT)

When connecting to Connect AI through the REST API, the OData API, or the Virtual SQL Server, a Personal Access Token (PAT) is used to authenticate the connection to Connect AI. PAT functions as an alternative to your login credentials for secure, token-based authentication. It is a best practice to create a separate PAT for each service to maintain granularity of access.

1. Click on the Gear icon () at the top right of the Connect AI app to open the settings page.
2. On the Settings page, go to the Personal Access Tokens section and click Create PAT.
3. Give the PAT a name and click Create.
4. Note: The personal access token is only visible at creation, so be sure to copy it and store it securely for future use.

Step 2: Connect and Query Claude Compliance Data in Databricks

Follow these steps to establish a connection from Databricks to Claude Compliance. You'll install the CData JDBC Driver for Connect AI, add the JAR file to your cluster, configure your notebooks, and run SQL queries to access live Claude Compliance data data.

2.1 Install the CData JDBC Driver for Connect AI

1. In CData Connect AI, click the Integrations page on the left. Search for JDBC or Databricks, click Download, and select the installer for your operating system.
2. Once downloaded, run the installer and follow the instructions:
   • For Windows: Run the setup file and follow the installation wizard.
   • For Mac/Linux: Unpack the archive and move the folder to /opt or /Applications. Make sure you have execute permissions.
3. After installation, locate the JAR file in the installation directory:
   • Windows:

     C:\Program Files\CData\CData JDBC Driver for Connect AI\lib\cdata.jdbc.connect.jar

   • Mac/Linux:

     /Applications/CData/CData JDBC Driver for Connect AI/lib/cdata.jdbc.connect.jar

2.2 Install the JAR File on Databricks

1. Log in to Databricks. In the navigation pane, click Compute on the left. Start or create a compute cluster.
2. Click on the running cluster, go to the Libraries tab, and click Install New at the top right.
3. In the Install Library dialog, select DBFS, and drag and drop the cdata.jdbc.connect.jar file. Click Install.

2.3 Query Claude Compliance Data in a Databricks Notebook

Notebook Script 1 — Define JDBC Connection:

1. Paste the following script into the notebook cell:

driver = "cdata.jdbc.connect.ConnectDriver"
url = "jdbc:connect:AuthScheme=Basic;User=your_username;Password=your_pat;URL=https://cloud.cdata.com/api/;DefaultCatalog=Your_Connection_Name;"

2. Replace:
   • your_username - With your CData Connect AI username
   • your_pat - With your CData Connect AI Personal Access Token (PAT)
   • Your_Connection_Name - With the name of your Connect AI data source, from the Sources page
3. Run the script.

Notebook Script 2 — Load DataFrame from Claude Compliance data:

1. Add a new cell for this second script. From the menu on the right side of your notebook, click Add cell below.
2. Paste the following script into the new cell:

remote_table = spark.read.format("jdbc") \
  .option("driver", "cdata.jdbc.connect.ConnectDriver") \
  .option("url", "jdbc:connect:AuthScheme=Basic;User=your_username;Password=your_pat;URL=https://cloud.cdata.com/api/;DefaultCatalog=Your_Connection_Name;") \
  .option("dbtable", "YOUR_SCHEMA.YOUR_TABLE") \
  .load()

3. Replace:
   • your_username - With your CData Connect AI username
   • your_pat - With your CData Connect AI Personal Access Token (PAT)
   • Your_Connection_Name - With the name of your Connect AI data source, from the Sources page
   • YOUR_SCHEMA.YOUR_TABLE - With your schema and table, for example, ClaudeCompliance.Projects
4. Run the script.

Notebook Script 3 — Preview Columns:

1. Similarly, add a new cell for this third script.
2. Paste the following script into the new cell:

display(remote_table.select("ColumnName1", "ColumnName2"))

3. Replace ColumnName1 and ColumnName2 with the actual columns from your Claude Compliance structure (e.g. Id, Name, etc.).
4. Run the script.

You can now explore, join, and analyze live Claude Compliance data directly within Databricks notebooks—without needing to know the complexities of the back-end API and without replicating Claude Compliance data.

Try CData Connect AI Free for 14 Days

Ready to simplify real-time access to Claude Compliance data? Start your free 14-day trial of CData Connect AI today and experience seamless, live connectivity from Databricks to Claude Compliance.

Low code, zero infrastructure, zero replication — just seamless, secure access to your most critical data and insights.