Integrating Claude Code CLI with Microsoft Dataverse Data via CData CLI

Justin Floyd
Product Business Analyst

CData CLI gives AI coding agents direct, command-line-native access to CData Drivers across hundreds of data sources, allowing agents to manage licenses, configure connections, run SQL queries, and explore schema metadata - all without leaving the terminal.

Claude Code is Anthropic's agentic command-line tool that brings AI assistance directly into your development workflow. Running natively in the terminal, it can plan and execute multi-step tasks: reading files, running commands, and making decisions across your project without constant manual input. Its ability to load and follow agent skill files makes it especially well-suited for structured workflows, making it a natural fit for connecting to external data sources through tools like CData CLI. With Claude Code, you can describe your data goals in plain language and let the agent handle driver setup, connection configuration, and query execution automatically.

This article details step-by-step directions for how to connect Microsoft Dataverse data to Claude Code CLI through CData CLI.

Prerequisites

Claude Code installed
CData CLI installed

About Microsoft Dataverse Data Integration

CData provides the easiest way to access and integrate live data from Microsoft Dataverse (formerly the Common Data Service). Customers use CData connectivity to:

Access both Dataverse Entities and Dataverse system tables to work with exactly the data they need.
Authenticate securely with Microsoft Dataverse in a variety of ways, including Microsoft Entra ID, Azure Managed Service Identity credentials, and Azure Service Principal using either a client secret or a certificate.
Use SQL stored procedures to manage Microsoft Dataverse entities - listing, creating, and removing associations between entities.

CData customers use our Dataverse connectivity solutions for a variety of reasons, whether they're looking to replicate their data into a data warehouse (alongside other data sources)or analyze live Dataverse data from their preferred data tools inside the Microsoft ecosystem (Power BI, Excel, etc.) or with external tools (Tableau, Looker, etc.).

Getting Started

Step 1: Download skill (one-time setup)

The CData CLI should always be used with the official Skill.

The official CData CLI Skill on GitHub can be downloaded using npx skills through the terminal:
```
npx skills add CDataSoftware/cli-skills
```
Follow prompts in terminal to install skill for Claude Code

Step 2: Set up project directory

A project directory should be created to contain all project files.

Navigate to directory within the terminal and start a session using the claude command

Step 3: Establish driver and connection

Describe what you hope to accomplish in this session with the CLI and Microsoft Dataverse data. For example, consider the following prompt:

"I would like to build a command line app that connects to Microsoft Dataverse data and checks for updates from Accounts. Make sure to include data from important columns like AccountId and Name."

This should automatically load the Skill and kick off the following process. You can always manually prompt the agent for each of the following steps.

Driver setup: Check for existing CData Microsoft Dataverse driver, or search and download a new one:

```
cdatacli drivers list
```
```
cdatacli drivers search CDS
```

cdatacli drivers download --artifact-id "artifact-id"

Activation: Activate Microsoft Dataverse driver with a single command for trial or full license:

cdatacli drivers activate CDS --name "name" --email "email" --trial

cdatacli drivers activate CDS --name "name" --email "email" --key "product-key"

Establish Microsoft Dataverse connection: Check for existing Microsoft Dataverse connections or create a new one:

```
cdatacli connection list
```

cdatacli connection create --driver CDS –name "my_CDS_connection" --connectionstring "Prop1=value1;Prop2=value2;..."

Create Microsoft Dataverse skill (if applicable): CData provides driver instructions for popular sources that can be used to create a source specific skill to guide the agent through best practices for the driver. Run the following command to generate a skill file and save the output to your skills directory. You can choose to save the skill either at the project level or globally. (Note: If "No instructions available for Microsoft Dataverse" error is returned, no driver instructions exist and you can continue to use main driver skill)
```
cdatacli drivers skill CDS > ~/skills/cdata-CDS/SKILL.md
```

Step 4: Query Microsoft Dataverse data

With the CData Microsoft Dataverse Driver fully setup, your agent can now begin executing queries and writing code if desired.

cdatacli query sql --connection "my_Microsoft Dataverse data_connection" --sql "SELECT * FROM table"

Query Microsoft Dataverse data directly from your terminal with CData CLI

Claude Code and CData CLI together give your AI coding agent a direct path to live Microsoft Dataverse data without custom middleware, scheduled syncs, or manual setup at each step. Describe your goal, and the agent handles driver configuration, connection setup, and query execution from start to finish in the terminal.

Download the free CData CLI and start a free, 30-day trial of the CData JDBC Driver for Microsoft Dataverse today.

Ready to get started?

Download a free trial of the Microsoft Dataverse Driver to get started:

Download Now

Learn more:

Microsoft Dataverse JDBC Driver

Rapidly create and deploy powerful Java applications that integrate with Microsoft Dataverse.

CData is the data layer that makes AI work in production—live connectivity and replication across hundreds of the most critical enterprise sources, semantic context, and built-in governance. Powering AI for Databricks, Microsoft, Google, Palantir, and 10,000+ customers worldwide.