Sage 300
Connect AI agents and workflows to Sage 300: customers, vendors, items, sales and purchase orders, AR and AP invoices and GL batches, behind your firewall.
Book a demo
Sage 300 for AI agents and workflows.
engini lets your AI agents and workflows work in Sage 300: read customers, vendors, items and stock by location, enter sales orders and purchase orders, enter AR and AP invoices, create GL batches, read open balances, and start a workflow when records change, across companies and currencies. Sage 300 stays on your server, 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 Sage 300. Every tool is one you allow or leave out.
The Sage 300 tools in engini, grouped by what they change. Writes go through the Sage 300 Web API, so its validation applies.
Read
Read master data and stock by location.
Read open orders.
Read aging for customers and vendors.
Read the chart of accounts and balances, by company and currency.
Write
Enter an order in Order Entry.
Raise an order to a vendor.
Enter invoices in batches.
Enter a journal batch for posting.
Keep master data current.
Triggers
Customers, orders or invoices added or changed, by company.
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 300. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your Sage 300 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 300 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 300 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 300 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 300 through engini
{
"mcpServers": {
"engini-sage-300": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your Sage 300 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 300 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 300. Agents and workflows, across systems.
Orders from the CRM and the store
Orders from Salesforce, HubSpot or Shopify become Sage 300 sales orders, and status flows back.
Vendor invoices without retyping
A vendor invoice from the inbox is read by an agent and entered in Sage 300 for payment.
Multi-company reporting
Balances from every Sage 300 company land in Power BI or a Google Sheet every morning.
Answers in plain words
An agent in Teams answers stock, order and balance questions. 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 300 and another system engini connects is available.
You decide what each agent may do in Sage 300. engini enforces it on every call.
Only the tools you allow
A toolset lists the Sage 300 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 300 account and engini acts as that person, with their Sage 300 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 300 behind your firewall.
If Sage 300 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 300 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 300 in three steps. Then decide what each agent may do.
Sign in to Sage 300
Install the engini On-Prem Agent on a server that can reach Sage 300, enable the Sage 300 Web API, create a user with access only to the modules the workflows need, then add a Sage 300 connection with the company and that user.
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 300 from Claude, ChatGPT, Cursor or your own code.
Sage 300 and engini. Straight answers.
Can an AI agent write to Sage 300, or only read?
Both. engini has tools to enter sales and purchase orders, AR and AP invoices and GL batches, and to create and update customers, vendors and items. 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 Sage 300 need to be in the cloud?
No. Sage 300 stays on your server. The engini On-Prem Agent runs inside your network and connects out to engini, so you open no inbound ports.
What if the tool I need is not listed?
The Sage 300 Web API covers most modules, and new tools can be added for the ones you use. Talk to us about what you need.
Does the agent act as me in Sage 300?
It acts as the Sage 300 user behind the connection, with that user's security groups. Every run is recorded under the person who started it.
Can a change in Sage 300 start work?
Yes. Scheduled triggers check Sage 300 for new or changed records by company. A workflow can include an AI agent step.