Sage X3
Connect AI agents and workflows to Sage X3: customers, suppliers, products, sales and purchase orders, stock, invoices and journal entries.
Book a demo
Sage X3 for AI agents and workflows.
engini lets your AI agents and workflows work in Sage X3: read customers, suppliers, products and stock by site, enter sales and purchase orders, read invoices and open items, post journal entries, call any X3 web service your team publishes, and start a workflow when records change. Distributors and manufacturers keep X3 and the systems around it in step, in the cloud or on premises. 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 Sage X3. Every tool is one you allow or leave out.
The Sage X3 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 business partners and products with the fields you choose.
Read stock by site, location and lot.
Read orders, lines and status.
Read billing and what is still open.
Read any X3 table with a SQL query. Read only.
Write
Enter and change orders.
Raise an order to a supplier.
Keep master data current.
Post a journal entry with its dimensions.
Run any X3 object or subprogram your team publishes as a web service.
Any endpoint
Call any Sage X3 API, with the sign-in added for you.
Triggers
An X3 workflow rule sends a record to engini as it changes.
Orders, invoices or partners added or changed.
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 Sage X3. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your Sage X3 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 Sage X3 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 Sage X3 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 Sage X3 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 Sage X3 through engini
{
"mcpServers": {
"engini-sage-x3": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your Sage X3 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 Sage X3 tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.
What teams build on Sage X3. Agents and workflows, across systems.
Orders from every channel into X3
Orders from Salesforce, Shopify or EDI become Sage X3 sales orders, and the confirmation goes back to the customer.
Supplier invoices entered
A supplier invoice from the inbox is read by an agent and entered in X3 against the purchase order.
X3 in the warehouse
Orders, invoices and ledger entries land in Snowflake or Power BI on a schedule.
Stock questions answered
An agent in Teams answers stock, order and ship-date questions from X3. Its toolset holds read tools only.
Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between Sage X3 and another system engini connects is available.
You decide what each agent may do in Sage X3. engini enforces it on every call.
Only the tools you allow
A toolset lists the Sage X3 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 Sage X3 account and engini acts as that person, with their Sage X3 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.
Sage X3 behind your firewall.
If Sage X3 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 Sage X3 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 Sage X3 in three steps. Then decide what each agent may do.
Sign in to Sage X3
Create a Sage X3 user with access only to the functions the workflows need and publish the web services you want to call, then add a Sage X3 connection with your server, endpoint and that user, through the On-Prem Agent if X3 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 Sage X3 from Claude, ChatGPT, Cursor or your own code.
Sage X3 and engini. Straight answers.
Can an AI agent write to Sage X3, or only read?
Both. engini has tools to enter and change sales and purchase orders, create and update partners and products, post journal entries and call published web services. 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 the agent act as me in Sage X3?
It acts as the Sage X3 user behind the connection, with that user's function profile. Every run is recorded under the person who started it.
Can a change in Sage X3 start work?
Yes. An X3 workflow rule can send a record to engini as it changes, and scheduled triggers check for new or changed records. A workflow can include an AI agent step.
What if the tool I need is not listed?
Use Send API Request to call any Sage X3 API endpoint through the same connection, and give it only to the agents that need it.