Rippling
Connect AI agents and workflows to Rippling: employees, departments, teams, work locations, leave requests and balances, groups and custom objects.
Book a demoRippling for AI agents and workflows.
engini lets your AI agents and workflows work in Rippling: read employees, departments, teams and work locations, read leave requests and balances, manage groups and custom object records, and start a workflow when someone is hired, changes or leaves. The systems Rippling does not run still hear about every joiner and leaver. 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 Rippling. Every tool is one you allow or leave out.
The Rippling tools in engini, grouped by what they change. Read tools are safe to hand out widely. Write and delete tools go only to the agents that need them.
Read
Read people with their title, manager, department and location.
Read the company structure.
Read time off.
Read groups and your own objects.
Write
Request time off or change its status.
Manage group membership for access and apps.
Write to your own Rippling objects.
Any endpoint
Call any Rippling API endpoint, with the sign-in added for you.
Triggers
Joiners, movers and leavers.
Time off requested.
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 Rippling. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your Rippling 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 Rippling 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 Rippling 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 Rippling 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 Rippling through engini
{
"mcpServers": {
"engini-rippling": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your Rippling 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 Rippling tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.
What teams build on Rippling. Agents and workflows, across systems.
Systems Rippling does not manage
A hire or termination in Rippling creates or closes accounts in the ERP, the CRM and internal tools Rippling does not provision.
Headcount where finance plans
Employees and departments flow to NetSuite or Sage Intacct, so department costs and approvals match the org chart.
Out of office, visible
Approved time off posts to the team's Slack channel and blocks the calendar.
HR answers in Slack
An agent answers balances, managers and who is out from Rippling. 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 Rippling and another system engini connects is available.
You decide what each agent may do in Rippling. engini enforces it on every call.
Only the tools you allow
A toolset lists the Rippling 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 Rippling account and engini acts as that person, with their Rippling 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.
Connect Rippling in three steps. Then decide what each agent may do.
Sign in to Rippling
Add a Rippling connection and sign in with Rippling as an admin, choosing the scopes the workflows need. Or paste an API token from Rippling.
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 Rippling from Claude, ChatGPT, Cursor or your own code.
Rippling and engini. Straight answers.
Can an AI agent write to Rippling, or only read?
Both. engini has tools to create and update leave requests, groups and custom object records. 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 Rippling?
It acts as the Rippling admin who signed in or whose token the connection uses, with the scopes that were granted. Every run is recorded under the person who started it.
Can a change in Rippling start work?
Yes. Rippling notifies engini when employees are hired, changed or terminated, and a scheduled trigger checks for new leave requests. A workflow can include an AI agent step.
What if the tool I need is not listed?
Use Send API Request to call any Rippling API endpoint through the same connection, and give it only to the agents that need it.