HRIS
WorkRamp MCP connector
The WorkRamp connector brings your training users, groups, guides, and learning path assignments into Claude, ChatGPT, Cursor, and any MCP client, so your team can ask about and assign training while every request runs under their own WorkRamp access.
-
How it connects. Connects with an API key. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
How to connect
How to connect WorkRamp to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect WorkRamp once
-
Open Connections, choose Add connection, and pick WorkRamp.
-
Optionally set Share with to give a team access, then press Connect.
-
Paste a WorkRamp API key. One person generates a token in WorkRamp and pastes it once. Everyone else works through Share with, and never sees it.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Connect WorkRamp to Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Connect WorkRamp to ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Connect WorkRamp to Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect WorkRamp to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with WorkRamp through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
People
Enroll a new hire on day one
Create the person's WorkRamp user, add them to the right group, and assign the onboarding path in one ask instead of clicking through four screens.
-
Learning and development
See who has not finished a guide
Pull the assignments for a compliance guide and list who is still outstanding, then follow up with the exact names rather than a spreadsheet export.
-
Sales enablement
Roll out product training to a whole team
Assign the new pricing guide to the sales group and set a due date, then check back later on what changed across those assignments.
-
Support
Move an agent onto a new learning path
When someone changes queue or tier, update their path assignment and remove the old one so their training list matches the job they now do.
-
Managers
Check a direct report's training status
Ask what guides and paths are assigned to one person and what has changed recently before a one-to-one, without logging into WorkRamp yourself.
-
IT
Keep user records and groups tidy
Update attributes such as department or location when the org chart changes, and deactivate users who have left so groups and assignments stay accurate.
Try asking
- “Which groups is this new hire assigned to in WorkRamp?”
- “List guides assigned to the Sales group this month.”
- “Show user attributes missing for the onboarding cohort.”
AI tools
WorkRamp tools for your AI agents
100 tools are ready to call through Elaichi's MCP endpoint the moment you connect WorkRamp, governed by the same roles, restrictions, and audit log as everything else in Elaichi.
No tools match your search.
See it in Elaichi
What connecting WorkRamp gets you
6 screens from the product, each doing one job for your WorkRamp account.
The agent
Ask WorkRamp questions, get live answers back.
Type a plain language question and pull answers straight from WorkRamp records.
- users
- groups
- attributes
- guides
Ask Elaichi to work across your apps.
Which groups is this new hire assigned to in WorkRamp?
List guides assigned to the Sales group this month.
Show user attributes missing for the onboarding cohort.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One WorkRamp endpoint, every client connects.
Claude, ChatGPT and Cursor reach WorkRamp through one governed org endpoint, no shared keys.
Copy the endpoint
Tool catalog
100 WorkRamp tools, zero custom code.
Browse every WorkRamp tool, resource and method available without writing any code.
- List all WorkRamp users
- Create a WorkRamp user
- Update a WorkRamp user by ID
- Delete a WorkRamp user by ID
Toolboxes
Every team gets its own WorkRamp toolbox.
Scope a distinct WorkRamp toolbox to each team so access matches their work.
- People Ops
- Sales
- Support
- Engineering
Shared connections
Delegated WorkRamp access, no shared credentials.
See who connected each WorkRamp account and how many teams and members use it.
- Sales Onboarding
- Support Training
- Engineering Enablement
- People Ops
Audit log
Every WorkRamp action, logged and answerable.
Review who did what in WorkRamp, with timestamps, action type and resource.
- When
- Who
- What happened
- Type
Launching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
WorkRamp digests run themselves, people approve.
A schedule fetches WorkRamp records, drafts a digest, and posts back once approved.
WorkRamp digest
Run 418 · started 2 minutes ago · on behalf of Emma Laurent
-
✓
Schedule
Every weekday at 08:00
0.2s -
✓
Fetch users
WorkRamp
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
WorkRamp
Queued
Collections and dashboards
WorkRamp health, computed on a schedule.
Track WorkRamp metrics and a 14 day trend by team with no model involved.
WorkRamp health
Refreshed 4 minutes ago · every 15 minutes · from the users collection
Users
1,284 ↓ 12%
Groups
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Users created
Last 14 days
By team
Share of activity
Sales Onboarding 34%
Support Training 27%
Engineering Enablement 21%
People Ops 18%
Related connectors
More from the catalog
FAQ
Frequently asked questions
How do I connect WorkRamp to Claude?
Connect WorkRamp in Elaichi first: WorkRamp signs in with an API key, so you paste the key from your WorkRamp admin settings and the connection is ready. Then in Claude go to Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. There is no OAuth application to register and no client ID or secret to generate.
Does WorkRamp work with ChatGPT and Cursor as well as Claude?
Yes. Once WorkRamp is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect WorkRamp once and every client your team uses picks it up.
What can an AI agent actually do with my WorkRamp data?
With WorkRamp connected, an agent can look up users and groups, create or update a user, add someone to a group, and change attributes such as department. It can also list your guides, assign a guide or a learning path to a person, update or remove that assignment, and show what has changed across assignments recently. Short concrete asks work best, such as "assign the security guide to everyone in the support group" rather than a long paragraph.
Does connecting WorkRamp give the AI access to everyone's training records?
No. Every request runs inside the WorkRamp access of the person who signed in, so a manager who can only see their own team in WorkRamp sees only that team through the AI. Elaichi can narrow that access further, for example to read-only, but it can never widen it beyond what WorkRamp already allows that person.
Can I stop an agent from deleting or changing things in WorkRamp?
Yes. In Elaichi you can restrict WorkRamp actions one by one, for example allowing assignments to be created but blocking users or assignments from being deleted. A blocked action is never shown to Claude, ChatGPT, or any other client at all, so no prompt, however worded, can reach it.
What happens to a WorkRamp connection when someone leaves?
When you offboard a person in Elaichi, their access to WorkRamp through every AI client ends immediately. If they had shared a WorkRamp connection with a team, it keeps working for everyone else. If you ever want to remove WorkRamp entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client at the same time.
Put WorkRamp in front of your team
Fourteen days on Gold, no credit card. Connect it once and pick what each team can call.