IFS
Connect AI agents and workflows to IFS Cloud: customers, parts, orders, work orders, equipment, projects and invoices, with event actions as triggers.
Book a demo
IFS Cloud for AI agents and workflows.
engini lets your AI agents and workflows work in IFS Cloud, the ERP, asset management and field service suite for manufacturing, energy, aerospace and service companies: read customers, parts, orders and equipment, open and update work orders, enter customer and purchase orders, run any projection action, and start a workflow when an IFS event action fires. 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 IFS Cloud. Every tool is one you allow or leave out.
The IFS Cloud tools in engini, grouped by what they change. Write tools go only to the agents that need them.
Read
Read master data and stock by site.
Read orders and their status.
Read maintenance work and the assets it is for.
Read projects, costs and billing.
Write
Open, assign and report on maintenance work.
Enter orders with their lines.
Keep master data current.
Run an action an IFS projection exposes, such as releasing an order.
Any endpoint
Call any IFS Cloud API, with the sign-in added for you.
Triggers
An IFS event action sends a record to engini, such as a new work order or a released order.
Orders, work orders or parts 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 IFS Cloud. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your IFS Cloud 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 IFS Cloud 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 IFS Cloud 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 IFS Cloud 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 IFS Cloud through engini
{
"mcpServers": {
"engini-ifs": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your IFS Cloud 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 IFS Cloud tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.
What teams build on IFS Cloud. Agents and workflows, across systems.
Alerts become work orders
An alarm from the plant historian or a ticket in ServiceNow opens an IFS work order on the right equipment.
Technicians with the full picture
An agent in Teams gives a technician the asset history, open work orders and parts on hand from IFS. Its toolset holds read tools only.
Orders from the CRM
Orders from Salesforce become IFS customer orders, and status flows back to the account.
IFS in the warehouse
Orders, projects and invoices land in Snowflake or Power BI on a schedule.
Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between IFS Cloud and another system engini connects is available.
You decide what each agent may do in IFS Cloud. engini enforces it on every call.
Only the tools you allow
A toolset lists the IFS Cloud 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 IFS Cloud account and engini acts as that person, with their IFS Cloud 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.
IFS Cloud behind your firewall.
If IFS Cloud 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 IFS Cloud 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 IFS Cloud in three steps. Then decide what each agent may do.
Sign in to IFS Cloud
In IFS IAM, create a client for engini with a service user that holds only the permission sets the workflows need, then add an IFS connection with your environment URL and the client.
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 IFS Cloud from Claude, ChatGPT, Cursor or your own code.
IFS Cloud and engini. Straight answers.
Can an AI agent write to IFS Cloud, or only read?
Both. engini has tools to open and update work orders, enter customer and purchase orders, create and update customers and parts, and run projection actions. 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 IFS Cloud?
It acts as the IFS service user behind the connection, with its permission sets. Every run is recorded under the person who started it.
Can a change in IFS Cloud start work?
Yes. An IFS event action can send a record to engini as it happens, 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 IFS Cloud API endpoint through the same connection, and give it only to the agents that need it.