TOTVS
Connect AI agents and workflows to TOTVS Protheus, RM and Datasul: customers, suppliers, products, sales and purchase orders, invoices and receivables.
Book a demo
TOTVS for AI agents and workflows.
engini lets your AI agents and workflows work in TOTVS, the leading ERP in Brazil and across Latin America, on Protheus, RM or Datasul: read customers, suppliers, products and stock, enter sales and purchase orders, read invoices and electronic fiscal documents, follow receivables and payables, call the REST services your team publishes, and start a workflow when records change. Subsidiaries in Brazil stay in step with headquarters on another ERP. 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 TOTVS. Every tool is one you allow or leave out.
The TOTVS tools in engini, grouped by what they change. In an ERP a write is a financial and fiscal event, so write tools go only to the agents that need them.
Read
Read master data by company and branch.
Read stock by warehouse.
Read orders and their status.
Read issued and received invoices, with their electronic fiscal document keys.
Read open financial titles.
Write
Enter an order with its items.
Raise an order to a supplier.
Keep master data current.
Run any REST service your team publishes in TOTVS.
Any endpoint
Call any TOTVS API, with the sign-in added for you.
Triggers
Orders, invoices 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 TOTVS. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your TOTVS 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 TOTVS 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 TOTVS 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 TOTVS 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 TOTVS through engini
{
"mcpServers": {
"engini-totvs": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your TOTVS 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 TOTVS tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.
What teams build on TOTVS. Agents and workflows, across systems.
Brazil on TOTVS, headquarters elsewhere
Sales, invoices and balances from a Brazilian subsidiary on TOTVS reach headquarters on NetSuite, SAP or Oracle, and both sides reconcile.
Orders from the CRM and the store
Orders from Salesforce or Shopify become TOTVS sales orders, and the invoice key goes back to the customer record.
Receivables people follow up
Overdue receivables go to the account owner in Teams with the invoice details.
Answers in plain words
An agent answers stock, order and invoice questions from TOTVS. 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 TOTVS and another system engini connects is available.
You decide what each agent may do in TOTVS. engini enforces it on every call.
Only the tools you allow
A toolset lists the TOTVS 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 TOTVS account and engini acts as that person, with their TOTVS 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.
TOTVS behind your firewall.
If TOTVS 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 TOTVS 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 TOTVS in three steps. Then decide what each agent may do.
Sign in to TOTVS
Create a TOTVS user with access only to the routines the workflows need and enable the REST services, then add a TOTVS connection with your server, company, branch and that user, through the On-Prem Agent if TOTVS 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 TOTVS from Claude, ChatGPT, Cursor or your own code.
TOTVS and engini. Straight answers.
Can an AI agent write to TOTVS, or only read?
Both. engini has tools to enter sales and purchase orders, create and update customers, suppliers and products, and call published REST 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 TOTVS?
It acts as the TOTVS user behind the connection, with that user's access by company and branch. Every run is recorded under the person who started it.
Can a change in TOTVS start work?
Yes. Scheduled triggers check TOTVS for new or changed orders, invoices and customers. A workflow can include an AI agent step.
What if the tool I need is not listed?
Use Send API Request to call any TOTVS API endpoint through the same connection, and give it only to the agents that need it.