HR MCP server

Your HR data in Claude and ChatGPT

Connect Claude, ChatGPT, Cursor or VS Code to Skailer. Each person signs in as themselves, and the client gets their permissions and no more.

Safe by design: what the MCP connector can do

01
Signs in as youEach person connects their own account, not an admin key.
02
Read-only if you chooseLeave changes off when you connect, and the client only reads.
03
Checks before it createsTime off is checked for balance and approvers before it's made.
04
Nothing gets deletedIt changes a short list of things and has no delete actions.
The problem

HR data shouldn't reach AI as a pasted export

Someone exports a table and pastes it into the chat. By tomorrow it's stale, and it shows the whole table. An admin API key gives the AI client everyone's data.

Connect your client

Connect Claude, ChatGPT, Cursor or VS Code in minutes

Add the Skailer server address in your client, sign in to Skailer in the browser and choose what the client may do. Claude Team and Enterprise owners add the connector once; each member connects their own account.

01
Claudecustom connector on Free, Pro and Max; Team and Enterprise too
02
ChatGPTdeveloper mode; Business, Enterprise, Edu write and Pro only reads
03
Cursor and VS Codefor all projects or one; in VS Code through GitHub Copilot chat
04
Other clientsany client that adds a remote MCP server and signs in by browser
Ask about your company

Ask about people, leave and goals without leaving chat

Once connected, the client reads the Skailer data you may see and answers with it: who is off in a release week, which goals are at risk, how a review cycle is going. Nobody exports a file first.

01
Peoplesearch employees, open a profile or find someone by their email
02
Time offbalances, categories, and team and company leave calendars
03
Goalssearch goals and open one with all of its key results
04
Surveys and reviewsresults, answers, participants and performance review stats
Act from the chat

Request leave and approve requests from the chat

If you allowed changes when connecting, the client can make the same short list of changes SK.AI makes. Time off is checked first: balance, what's left and who approves. A request that breaks policy isn't created.

01
Goalscreate and update goals and key results, and add check-ins
02
Your time offrequest time off and cancel requests you have already sent
03
Approvalsapprove or decline time off waiting for you, with a comment
04
Stays in Skaileroffers and position requests are listed; you decide in Skailer
Your permissions, not a key

Give each connection one person's access

The connector has no company-wide key. Each person signs in from their client and gets exactly what their role opens. Reading is always on; changing data is a separate permission. Removing the connector ends access.

  • Sign-in per personeach person signs in through the browser, with no shared token
  • Two permissionsviewing your data is always on, and changing it is optional
  • Role-based scopethe same field and data permissions as in Skailer itself
  • Disconnect any timeremove the connector, and the client stops working with Skailer
What the connector can do

See every tool and whether it reads or writes

Reading works with the default permission; changes need the permission to create and update data. Recruiting, compensation, documents and settings aren't included.

AreaReadWrite (needs permission)
PeopleSearch, profile, find by email, get me—
Things to doGet my inbox—
GoalsSearch goals, get a goalGoals, key results, check-ins
Time offBalances, categories, calendars, request checkCreate, cancel, approve, reject
SurveysSearch, results, answers, participants—
Performance reviewsSearch, results, stats, participant report—
RecognitionSearch recognitionsGive a recognition
Try asking

Questions you can ask from Claude or ChatGPT

01
"Who on my team is off next week?"
02
"What do I have to do this week?"
03
"Which goals in Sales are at risk?"
04
"Request time off November 10–14."
05
"Approve Anna's time off request."
06
"Summarize the Q3 survey answers."
One HR platform

SK.AI, MCP or API: pick what fits the job

Inside Skailer, SK.AI answers from the side panel. In Claude, ChatGPT, Cursor or VS Code, MCP does the same under the same permissions. Systems use the API and webhooks.

What is the Skailer HR MCP server?

The Skailer HR MCP server, also called the MCP connector, links AI clients such as Claude, ChatGPT, Cursor and VS Code to Skailer. Each person signs in through the browser, and the client gets their permissions. It reads employees, goals, time off, surveys, reviews, Things to do and recognitions. If allowed, it updates goals, requests, cancels, approves or declines time off, and gives recognitions. It has no delete actions and no recruiting data.

Skailer
Security

Know what the client can see and change

The client works only with the data the signed-in person may see in Skailer, and changes data only if they allowed it. Choose the client and plan your company already approves for work data.

Skailer vs. the alternatives

Three ways HR data gets into an AI chat

Pasted exports need no setup, but they show the whole file and go stale. Connectors on one integration key are live, and the key often sees more than any one user should.

CapabilityExports pasted into chatIntegration-key connectorSkailer MCP
Data freshnessAs of the exportLiveLive
Who the client acts asWhoever has the fileThe key's account, often adminThe person who connected
PermissionsNone after exportThe key's scopeThe person's role in Skailer
Changing dataNot possibleWhatever the key allowsGoals, own leave, approvals, if allowed
Read-only optionNot applicableDepends on the key's scopeA choice on the access screen
Ending accessDelete every copyRevoke the key for everyoneRemove the connector in the client
How it works

How to connect Skailer to your AI client

01
Add the serverPaste the Skailer server address into your client. In Claude Team and Enterprise, the owner adds it once.
02
Sign in to SkailerThe client opens Skailer in your browser. Sign in as yourself, with your usual Skailer account.
03
Choose permissionsReading is always on. Decide whether the client may also change data, then allow the access.
04
AskTurn Skailer on in the chat and ask about your people, leave, goals, reviews and surveys.
FAQ

Skailer MCP: common questions

MCP (Model Context Protocol) is an open standard that lets AI clients such as Claude and ChatGPT connect to other systems. An HR MCP server is the HR system's side of that connection: Skailer's lets your client read your HR data and, if you allow it, change it.

Your demo

See Skailer working inside Claude

We build your company in Skailer. You look around. Like it? Then we talk price.
[email protected]
Just show me the prices first