Sage 50
Connect AI agents and workflows to Sage 50: customers, vendors, items, invoices, bills, payments and journal entries, on the machine that runs it.
Book a demo
Sage 50 for AI agents and workflows.
engini lets your AI agents and workflows work in Sage 50, the desktop accounting system used by small businesses: read customers, vendors, items and the chart of accounts, enter sales invoices, purchase invoices and receipts, record payments, post general journal entries, and start a workflow when records change. Sage 50 stays on the machine where it runs, 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 50. Every tool is one you allow or leave out.
The Sage 50 tools in engini, grouped by what they change. Writes go through Sage 50 itself, so its validation applies.
Read
Read master data and stock.
Read sales and purchase invoices with what is owed.
Read money in and out.
Read the chart of accounts and balances.
Write
Enter invoices.
Record money in and out.
Post a journal.
Keep records current.
Triggers
Invoices, payments or customers 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 50. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your Sage 50 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 50 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 50 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 50 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 50 through engini
{
"mcpServers": {
"engini-sage-50": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your Sage 50 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 50 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 50. Agents and workflows, across systems.
Store orders into Sage 50
Paid Shopify or WooCommerce orders become Sage 50 sales invoices with the receipt recorded.
Bills from the inbox
A vendor invoice from email is read by an agent and entered in Sage 50.
Ready for the next system
When the business outgrows Sage 50, the same connection moves customers, items and open invoices to Sage Intacct, NetSuite or QuickBooks Online.
Numbers on request
An agent answers what was billed, what is overdue and what is due to suppliers. 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 50 and another system engini connects is available.
You decide what each agent may do in Sage 50. engini enforces it on every call.
Only the tools you allow
A toolset lists the Sage 50 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 50 account and engini acts as that person, with their Sage 50 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 50 stays where it is.
Install the engini On-Prem Agent on the machine or server that runs Sage 50. It opens every connection itself, out to engini over HTTPS on port 443, so you open no inbound ports.
On-Prem Agent guide →Connect Sage 50 in three steps. Then decide what each agent may do.
Sign in to Sage 50
Install the engini On-Prem Agent on the machine with Sage 50, allow it access to the company in Sage 50, then add a Sage 50 connection with that company and 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 50 from Claude, ChatGPT, Cursor or your own code.
Sage 50 and engini. Straight answers.
Can an AI agent write to Sage 50, or only read?
Both. engini has tools to enter sales and purchase invoices, record receipts and payments, post journals and keep customers, vendors and items current. 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.
Which Sage 50 does it work with?
Sage 50 Accounting, US edition, on Windows. Other regional editions of Sage 50 differ: talk to us about yours.
Does the agent act as me in Sage 50?
It acts as the Sage 50 user behind the connection. Every run is recorded under the person who started it.
Can a change in Sage 50 start work?
Yes. Scheduled triggers check Sage 50 for new or changed records. A workflow can include an AI agent step.