Integrating OpenCode with Invoiced data via CData CLI

OpenCode is an open source AI coding agent from Anomaly that runs in your terminal, desktop, or IDE. It connects to over 75 LLM providers, including Claude, GPT, Gemini, and local models, and stores none of your code or context data. It runs multiple agent sessions in parallel on the same project, each with its own context. Its support for integrations, AGENTS.md configuration files, and a TypeScript/JavaScript plugin system makes it well-suited for tool-driven data workflows through CData CLI. By describing your data goals in plain language, OpenCode handles driver configuration, license activation, connection creation, and query execution from a single prompt.

This article walks through how to connect Invoiced data to OpenCode through CData CLI.

Prerequisites

1. OpenCode installed (either Terminal CLI or Desktop): OpenCode | Download
2. CData CLI installed
3. Access to Invoiced

Step 1: Download the skill (one-time setup)

Always use CData CLI with the official Skill.

1. The official CData CLI Skill on GitHub can be downloaded using npx skills through the terminal:

   npx skills add CDataSoftware/cli-skills

2. Follow the prompts in the terminal to install for OpenCode.

Step 2: Set up the project directory

Create a project directory to contain all project files. Below are examples for using OpenCode in either the Terminal or Desktop app.

OpenCode in Terminal CLI

Navigate to your desired directory in the terminal and start a session with the opencode command.

OpenCode Desktop App

Open the desktop app and select your project folder as the working directory.

Step 3: Establish the driver and connection

Describe what you want to accomplish with the CLI and Invoiced data.

I would like to build a command line app that connects to Invoiced and checks for updates from Invoices. Make sure to include data from important columns like Id and Name.

This prompt automatically loads the Skill and kicks off the following process. You can also manually prompt the agent for each of the following steps.

1. Driver setup: OpenCode checks for an existing CData Invoiced driver, or searches and downloads a new one:

• cdatacli drivers list

• cdatacli drivers search --driver "Invoiced"

• cdatacli drivers download --artifact-id <artifact-id>

2. Activation: Activate the Invoiced driver with a single command for a trial or full license:

• cdatacli drivers activate "Invoiced" --name "<name>" --email "<email>" --trial

• cdatacli drivers activate "Invoiced" --name "<name>" --email "<email>" --key "<product-key>"

3. Establish the connection: Check for existing Invoiced connections or create a new one:

• cdatacli connection list

• cdatacli connection create --driver Invoiced --name my_invoiced_connection --connectionstring "Prop1=value1;Prop2=value2;..."

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

  cdatacli drivers skill "Invoiced" > ~/skills/cdata-invoiced/SKILL.md

Step 4: Query Invoiced data

With the CData driver configured, your agent can execute queries and write code against live Invoiced data:

1. cdatacli query sql --connection my_invoiced_connection --sql "SELECT * FROM Invoices"

Query Invoiced data directly from your terminal with CData CLI

OpenCode and CData CLI together give your AI coding agent a direct path to live Invoiced 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.

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