< Back to all integrations

Sage 100

ERP & Finance

Connect AI agents and workflows to Sage 100: customers, vendors, items, sales orders, receivables, payables and the general ledger, behind your firewall.

Book a demo
[ Sage 100 + engini ]

Sage 100 for AI agents and workflows.

engini lets your AI agents and workflows work in Sage 100: read customers, vendors, items and stock, read open receivables and payables and the general ledger, enter sales orders, customers and AP invoices through Sage 100's own business objects, and start a workflow when records change. Sage 100 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.

MCPPython and TypeScript SDKCLIREST APIWorkflow Studio
Sign-inA Sage 100 user, through the On-Prem Agent
ReachCustomers, vendors, items, sales orders, receivables, payables and the general ledger, by company
DeploymentStandard, Advanced or Premium, on your server
[ 01 / What agents can do ]

What your agent can do in Sage 100. Every tool is one you allow or leave out.

The Sage 100 tools in engini, grouped by what they change. Writes go through Sage 100's own business objects, so its validation applies.

Read

Get Customers, Get Vendors, Get Items

Read master data and stock by warehouse.

Read
Get Sales Orders, Get Invoices

Read open orders and invoice history.

Read
Get Open Receivables, Get Open Payables

Read aging for customers and vendors.

Read
Get GL Accounts, Get GL Balances

Read the chart of accounts and balances by period.

Read
Run Query

Read any Sage 100 table with a query. Read only.

Read

Write

Create Sales Order

Enter an order with its lines.

Write
Create or Update Customer, Create or Update Vendor

Keep master data current.

Write
Create AP Invoice

Enter a vendor invoice for payment.

Write
Create GL Journal Entry

Enter a general journal.

Write

Triggers

Check for New or Changed Records

Customers, orders or invoices added or changed, by company.

Scheduled

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.

[ 02 / Connect your agent ]

Connect your AI agent to Sage 100. Four ways in, one set of permissions.

MCP

Claude, ChatGPT, Cursor

Create an MCP server in engini with your Sage 100 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 →
SDK

Python and TypeScript

Hand your agent a toolset of Sage 100 tools. The SDK gives OpenAI and Anthropic models the tools in the format they expect and runs the ones they pick.

SDK guide →
CLI

For coding agents

The engini CLI connects Sage 100 and runs its tools from a terminal, with machine-readable output, so an AI coding agent can drive it without getting stuck.

CLI guide →
REST API

Any language

Every Sage 100 tool is an endpoint. Call it with exact inputs from a scheduled job or a sync, with no model in the loop.

API reference →
MCP in four steps
In engini, connect Sage 100 and create an MCP server with that connection and the tools this agent may use.
Claude: Settings, Connectors, Add custom connector, then paste the server address.
Cursor: add the address to .cursor/mcp.json. Claude Code: claude mcp add.
Sign in through engini when the client asks. The agent sees only the tools you chose.
Cursor, connected to Sage 100 through engini
// .cursor/mcp.json: Cursor, connected to Sage 100 through engini
{
"mcpServers": {
"engini-sage-100": {
"url": "<your engini MCP server address>"
}
}
}

Create the MCP server in engini with your Sage 100 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.

Try asking your agent
“Which customers are more than 60 days past due?”
“How many of item 6655 are in the east warehouse?”
“Enter a sales order for 12 of item 6655 for customer 01-ABF.”
“Which AP invoices are due this week?”
“What were sales by salesperson last month?”
“Add this vendor from the W-9.”

Each request runs through the Sage 100 tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.

[ 03 / What teams build ]

What teams build on Sage 100. Agents and workflows, across systems.

Order to cash

Store and CRM orders into Sage 100

Orders from Shopify, WooCommerce or HubSpot become Sage 100 sales orders, and tracking goes back when they ship.

ShopifyWooCommerceHubSpotSage 100
Accounts payable

Vendor invoices without retyping

A vendor invoice from the inbox is read by an agent and entered in Sage 100 for payment.

OutlookSage 100
Finance

Reports without exports

Sales and aging from Sage 100 update a Google Sheet or Power BI every morning.

Sage 100Google SheetsPower BI
Sales

Answers in plain words

An agent in Teams answers stock, order and balance questions from Sage 100. Its toolset holds read tools only.

Microsoft TeamsSage 100

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 100 and another system engini connects is available.

[ 04 / Agent Policy ]

You decide what each agent may do in Sage 100. engini enforces it on every call.

Toolsets

Only the tools you allow

A toolset lists the Sage 100 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.

MCP servers

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.

Identity

Whose permissions apply

Connect a person's own Sage 100 account and engini acts as that person, with their Sage 100 permissions. Use a shared integration account and it acts as that account. Every run is recorded under the user who started it.

Credentials

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.

Audit

Every call on record

Every call lands in History and the audit log, which you can export or stream to your SIEM.

Environments

Test before production

Workspaces keep teams apart, and development, staging and production environments keep a test agent away from live data.

SOC 2 Type IIISO 27001GDPRSecurity at engini →
[ Behind your firewall ]

Sage 100 behind your firewall.

If Sage 100 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 100 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 →
[ 05 / Set up ]

Connect Sage 100 in three steps. Then decide what each agent may do.

Step 01

Sign in to Sage 100

Install the engini On-Prem Agent on the Sage 100 server or one that can reach it, create a Sage 100 user with access only to the modules the workflows need, then add a Sage 100 connection with the company code and that user.

Step 02

Choose the tools

Add the connection to an MCP server or a toolset with only the tools each agent needs.

Step 03

Build or ask

Use the connection as a step in a workflow, or ask your agent to work in Sage 100 from Claude, ChatGPT, Cursor or your own code.

[ 06 / Questions ]

Sage 100 and engini. Straight answers.

Can an AI agent write to Sage 100, or only read?

Both. engini has tools to enter sales orders, create and update customers and vendors, enter AP invoices and enter journal entries. 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 100 need to be in the cloud?

No. Sage 100 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?

Run Query reads any Sage 100 table, and new business-object tools can be added for the modules you use. Talk to us about what you need.

Does the agent act as me in Sage 100?

It acts as the Sage 100 user behind the connection, with that user's role. Every run is recorded under the person who started it.

Can a change in Sage 100 start work?

Yes. Scheduled triggers check Sage 100 for new or changed records by company. A trigger starts a workflow, and that workflow can include an AI agent step.