Use Claude to Talk to Your JD Edwards Data via CData Connect AI

Claude is a family of advanced large language models (LLMs) built by Anthropic, an AI research company founded in 2021. These models power the Claude conversational assistant and developer tools.

CData Connect AI offers a dedicated cloud-to-cloud interface for connecting to JD Edwards data. The CData Connect AI Remote MCP Server enables secure communication between Claude and JD Edwards. This allows you to ask questions and take actions on your JD Edwards data using Claude, all without the need for data replication to a natively supported database. With its inherent optimized data processing capabilities, CData Connect AI efficiently channels all supported SQL operations, including filters and JOINs, directly to JD Edwards. This leverages server-side processing to swiftly deliver the requested JD Edwards data.

Step 1: Configure JD Edwards Connectivity for Claude

Connectivity to JD Edwards from Claude is made possible through CData Connect AI Remote MCP. To interact with JD Edwards data from Claude, we start by creating and configuring a JD Edwards connection in CData Connect AI.

1. Log into Connect AI, click Sources, and then click Add Connection

2. Select "JD Edwards" from the Add Connection panel

3. Enter the necessary authentication properties to connect to JD Edwards.

   The driver connects to JD Edwards through your Application Interface Services (AIS) Server. Set the following connection properties:

   • URL: The base HTTPS URL of your AIS Server (e.g., https://jde-ais.example.com:8300).
   • User: Your JD Edwards username.
   • Password: Your JD Edwards password.
   • Environment (optional): The JD Edwards environment to use (e.g., PD920 for production or DV920 for development). If not specified, the AIS Server's default environment is used.
   • Role (optional): The JD Edwards role for the session. If not specified, the AIS Server's default role is used.
   • DeviceName (optional): An identifier for the connecting device or application, used for auditing and logging on the AIS Server.
   • Jasserver (optional): The specific Java Application Server (JAS) instance to route requests through, useful in clustered environments.

   Choosing Which Data Is Exposed

   JD Edwards organizes tables and business views by System Code, and the driver exposes each System Code as its own schema. Use these properties to control which schemas are available:

   • DataModel: One or more ERP modules (comma-separated) whose System Codes are exposed as schemas, or All to expose every System Code in the connected instance. Defaults to FinancialManagement.
   • SystemCodes: A comma-separated list of additional System Codes to expose alongside those from DataModel (e.g., 42,43).

   When you connect, the driver sends your credentials to the AIS Server to obtain a session token and caches it. The driver requests a new token automatically before the session expires.

   
4. Click Save & Test

Step 2: Connect Claude to CData Connect AI

Follow these steps to add a CData Connect AI connector in Claude:

1. Sign in to Claude.ai or create a new account.
2. Expand the left navigation menu.
3. In the bottom-left corner, click your user name and select Settings from the menu. The Settings screen appears.
4. In the Settings screen, click Connectors.
5. Click the button to Browse Connectors.
6. Search for "CData Connect AI" and click the listing.
7. Click "Connect" and sign into your Connect AI account.
8. After connecting, Claude opens a new chat.

Step 3: Explore Live JD Edwards Data with Claude

1. You can now start exploring your data with natural language prompts. Claude outlines the steps it uses to retrieve data from the source in CData Connect AI. Refer to CData's prompt library for prompt ideas.

NOTE: Claude's setup process is subject to change. Refer to Claude's documentation for the latest setup information.

Get CData Connect AI

To get live data access to hundreds of SaaS, Big Data, and NoSQL sources directly from your cloud applications, try CData Connect AI today!