Integrating Claude Code CLI with Amazon S3 Data via CData CLI

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 Amazon S3 data to Claude Code CLI through CData CLI.

Prerequisites

• Claude Code installed
• CData CLI installed

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 Amazon S3 data. For example, consider the following prompt:

"I would like to build a command line app that connects to Amazon S3 data and checks for updates from ObjectsACL. Make sure to include data from important columns like Name and OwnerId."

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.

1. Driver setup: Check for existing CData Amazon S3 driver, or search and download a new one:

   1. cdatacli drivers list

   2. cdatacli drivers search --driver "Amazon S3"

   3. cdatacli drivers download --artifact-id <artifact-id>

2. Activation: Activate Amazon S3 driver with a single command for trial or full license:

   1. cdatacli drivers activate "Amazon S3" --name "<name>" --email "<email>" --trial

   2. cdatacli drivers activate "Amazon S3" --name "<name>" --email "<email>" --key "<product-key>"

3. Establish Amazon S3 connection: Check for existing Amazon S3 connections or create a new one:

   1. cdatacli connection list

   2. cdatacli connection create --driver "Amazon S3" --name my_amazons3_connection --connectionstring "Prop1=value1;Prop2=value2;..."

4. Create Amazon S3 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 Amazon S3" error is returned, no driver instructions exist and you can continue to use main driver skill)

   cdatacli drivers skill "Amazon S3" > ~/skills/cdata-amazons3/SKILL.md

Step 4: Query Amazon S3 data

With the CData Amazon S3 Driver fully setup, your agent can now begin executing queries and writing code if desired.

cdatacli query sql --connection my_amazons3_connection --sql "SELECT * FROM ObjectsACL"

Query Amazon S3 data directly from your terminal with CData CLI

Claude Code and CData CLI together give your AI coding agent a direct path to live Amazon S3 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 Amazon S3 today.