Ask who reports to a manager in Rippling, or who is on leave this week.
Connect Rippling with an API token and Memtro reads workers with work email, title, department, manager, status and start date, the department list, and leave requests with type, dates, hours and status. Pay, SSN, date of birth, addresses and phone numbers are never read. The token inherits its creator's permissions. An hourly sync writes changed workers into memory and keeps the token in use, since Rippling revokes one left unused for 30 days. When asked, and once an administrator has granted the action by name, it can request leave, approve, reject or cancel requests, edit pending ones and create departments.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Rippling tool, reads what it needs, and answers with the source cited.
These tools change something in Rippling. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Once Rippling is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Who reports to Priya Nair?
Who is on leave next week?
Which leave requests are waiting for approval?
What is Dan Fletcher's title, and who is his manager?
Approve Dan Fletcher's pending leave for 3 to 5 December
Before sprint planning the engineering manager asks who in Engineering is off next week. Memtro reads the leave requests and answers that Dan Fletcher is away Monday to Wednesday, approved, and one request from Priya Nair is still pending.
Priya Sharma, who manages customer success at Northwind, asks Memtro to approve Tom Ellis's pending leave for the week after Christmas. Memtro reads the request, approves it in Rippling, and Rippling may notify Tom that it went through.
The teams that lean on Rippling most, a question each of them asks, and what they connect beside it.
A record in Rippling is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
BambooHR
Ashby
Breathe HR
Lever
Workable
Deel
Factorial HR
Pinpoint
Recruitee
CharlieHR
Deputy
Humaans
JazzHR
SmartRecruiters
Lattice
15Five
Homerun
Jibble
Leapsome
LearnUpon
Planday
7shifts
Timetastic
Recruit CRMIn Rippling open Developer → API credentials → New API token. Creating one needs the Create and manage API Tokens permission, and Rippling does not say which plans include the Developer app
Tick companies.read, workers.read and departments.read, plus leave-requests.read and leave-types.read for leave, and leave-requests.read-write or departments.read-write only if Memtro may change leave or create departments. Copy the token: Rippling shows it once
Make it from an account that will stay: the token inherits its creator's access, and Rippling revokes it when that person leaves. Paste the API token into Connections → Rippling in Memtro
Ask who is on leave this week
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Rippling tools are the same everywhere.
Only when you ask, and only what it has been granted: request time off for a worker (pending goes to approvers, approved records leave already agreed); approve, reject or cancel a leave request; change the dates, hours, leave type or comments of a pending leave request; create a department. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded. An hourly sync anchors recently changed Rippling records into memory as entities.
API token. In Rippling open Developer → API credentials → New API token. Creating one needs the Create and manage API Tokens permission, and Rippling does not say which plans include the Developer app.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time
