JD Edwards EnterpriseOne
Connect AI agents and workflows to JD Edwards EnterpriseOne: run orchestrations, read and enter orders, vouchers and journals, and submit batch jobs.
Book a demo
JD Edwards EnterpriseOne for AI agents and workflows.
engini lets your AI agents and workflows work in JD Edwards EnterpriseOne: run the orchestrations your team built in Orchestrator Studio, read address book, item, order and ledger data, enter sales orders, purchase orders, vouchers and journal entries through the same applications people use, submit batch jobs and follow them to the end. JD Edwards stays where it is, and the On-Prem Agent connects it out to engini with no inbound ports. Connect from Claude, ChatGPT or Cursor over MCP, from your code, or build in Workflow Studio.
Cursor, your code
audit log

in engini
What your agent can do in JD Edwards EnterpriseOne. Every tool is one you allow or leave out.
The JD Edwards tools in engini, grouped by what they change. In an ERP a write is a financial event, so write tools go only to the agents that need them.
Read
Read customers, suppliers and employees from the address book.
Read orders, lines and their status codes.
Read items and what is on hand and available by branch.
Read what customers owe and what you owe.
Read any table or business view you allow, with a filter.
Write
Run any orchestration published in Orchestrator Studio, with its inputs.
Enter and change orders through Sales Order Entry.
Raise an order through Purchase Order Entry.
Enter a supplier voucher in Accounts Payable.
Enter a journal entry in the general ledger.
Run a batch application (UBE) with its version and follow it to completion.
Triggers
A JD Edwards notification or orchestration sends a record to engini as it happens.
Orders, vouchers or any table you choose, added or changed.
A batch job finished, with its output.
A trigger starts a workflow, and a workflow can include an AI agent step. In Code, a trigger delivers the event to your own endpoint.
Connect your AI agent to JD Edwards EnterpriseOne. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your JD Edwards EnterpriseOne connection and only the tools you choose. Add its address to your client and sign in through engini. There is no key to copy.
MCP client setup →Python and TypeScript
Hand your agent a toolset of JD Edwards EnterpriseOne tools. The SDK gives OpenAI and Anthropic models the tools in the format they expect and runs the ones they pick.
SDK guide →For coding agents
The engini CLI connects JD Edwards EnterpriseOne and runs its tools from a terminal, with machine-readable output, so an AI coding agent can drive it without getting stuck.
CLI guide →Any language
Every JD Edwards EnterpriseOne tool is an endpoint. Call it with exact inputs from a scheduled job or a sync, with no model in the loop.
API reference →.cursor/mcp.json. Claude Code: claude mcp add.// .cursor/mcp.json: Cursor, connected to JD Edwards EnterpriseOne through engini
{
"mcpServers": {
"engini-jd-edwards": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your JD Edwards EnterpriseOne connection and the tools this agent may use, then paste its address. The client signs in through engini on first use. Claude, VS Code and other clients take the same address: see the MCP client setup guide.
Each request runs through the JD Edwards EnterpriseOne tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.
What teams build on JD Edwards EnterpriseOne. Agents and workflows, across systems.
Orders from new channels into JD Edwards
Orders from Salesforce, Shopify or EDI become JD Edwards sales orders through Sales Order Entry, so every pricing and hold rule still applies.
Supplier invoices entered
A supplier invoice from the inbox is read by an agent, matched to the purchase order and entered as a voucher.
Answers without a green screen
An agent in Microsoft Teams answers availability, order status and open-invoice questions from JD Edwards. Its toolset holds read tools only.
JD Edwards next to the cloud
Customers, items and orders stay in step between JD Edwards and NetSuite, Salesforce or Snowflake while the business moves at its own pace.
Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between JD Edwards EnterpriseOne and another system engini connects is available.
You decide what each agent may do in JD Edwards EnterpriseOne. engini enforces it on every call.
Only the tools you allow
A toolset lists the JD Edwards EnterpriseOne tools an agent may call and the connection each one uses. Give one agent read tools only and another the write it needs. engini refuses any call outside the toolset.
Scoped when you set them up
An MCP server exposes only the connections and tools chosen when it is created, and engini shows who uses each server.
Whose permissions apply
Connect a person's own JD Edwards EnterpriseOne account and engini acts as that person, with their JD Edwards EnterpriseOne permissions. Use a shared integration account and it acts as that account. Every run is recorded under the user who started it.
Kept out of prompts
Your agent never needs your credentials: engini stores them and adds them when it runs each call, so keys stay out of prompts and tool inputs.
Every call on record
Every call lands in History and the audit log, which you can export or stream to your SIEM.
Test before production
Workspaces keep teams apart, and development, staging and production environments keep a test agent away from live data.
JD Edwards behind your firewall.
If JD Edwards runs in your own data center, install the engini On-Prem Agent on a server inside your network. It opens every connection itself: out to engini over HTTPS on port 443, and to JD Edwards while it runs a task. You open no inbound ports or firewall rules. Calls through it run on the same engine as MCP, the API and workflows, and each one is recorded in History.
On-Prem Agent guide →Connect JD Edwards EnterpriseOne in three steps. Then decide what each agent may do.
Sign in to JD Edwards EnterpriseOne
Make sure the AIS Server is running for your environment, create a JD Edwards user and role with only the applications and orchestrations the workflows need, then add a JD Edwards connection with the AIS address, environment and that user, through the On-Prem Agent if it runs inside your network.
Choose the tools
Add the connection to an MCP server or a toolset with only the tools each agent needs.
Build or ask
Use the connection as a step in a workflow, or ask your agent to work in JD Edwards EnterpriseOne from Claude, ChatGPT, Cursor or your own code.
JD Edwards EnterpriseOne and engini. Straight answers.
Can an AI agent write to JD Edwards EnterpriseOne, or only read?
Both. engini has tools to run orchestrations, enter and change sales orders, raise purchase orders, enter vouchers and journal entries, and submit batch jobs. Whether a given agent may use them is up to you: give it a toolset or an MCP server with read tools only, and it cannot call the rest.
Does it write to JD Edwards tables directly?
No. Writes go through JD Edwards applications and orchestrations, so every business rule, edit and security setting applies, as it does for people.
Can it use the orchestrations we already built?
Yes. Run Orchestration runs any orchestration published in Orchestrator Studio, with its inputs and outputs.
What if the tool I need is not listed?
Build an orchestration in Orchestrator Studio and run it with Run Orchestration, or read any table with Query Table. Give them only to the agents that need them.
Which releases does it work with?
JD Edwards EnterpriseOne 9.2 with the AIS Server, on premises or in your own cloud.
Does the agent act as me in JD Edwards EnterpriseOne?
It acts as the JD Edwards user behind the connection, with that user's role and row security. Every run is recorded under the person who started it.
Can a change in JD Edwards EnterpriseOne start work?
Yes. A JD Edwards notification or orchestration can send a record to engini as it happens, and scheduled triggers check for new or changed records and finished batch jobs. A workflow can include an AI agent step.