Lucca MCP: connect Lucca to Claude and ChatGPT
Ask Claude or ChatGPT who is off on Friday, which notes de frais are still waiting for approval or who has not filled in last week’s timesheet. The answer comes straight from Lucca, without opening each module or exporting a list.
We build the connector for your company on Lucca’s own API. It only reads, it reaches only what your Lucca admin gives its key, and your company decides which groups get it. HR data is sensitive, so payroll and salary data stay out unless you choose otherwise.
Built for your company · Works in Claude, ChatGPT and Copilot
What your team can do with Lucca in Claude and ChatGPT
Answers across the Lucca modules
Who is in this week
Expenses before month end
Time spent per project
Ask it like this
“Who in the Bordeaux team is off this Friday?”
“Which expense reports are still waiting for approval, and since when?”
“Who has not submitted last week’s timesheet?”
“How many RTT days has the sales team taken since January?”
“Which leave requests for December are still pending?”
“Who are Julien Lefèvre’s direct reports, and which of them are off next week?”
What we build for Lucca
Deployed OS has no ready Lucca connector yet. We build it for your company when you start, on Lucca’s own API, with the same rules as every other connector: each person’s own login, access decided by group, every call logged.
- Employee directory
- People with the details your Lucca admin allows, such as department, establishment, manager and start date.
- Organisation
- Departments and establishments, so the AI can answer per team, site or legal entity.
- Time off
- Leave requests and approved leave per person, team and date range, with their status.
- Expenses
- Expense reports and their items from Cleemy, with status, so finance sees what is open.
- Timesheets
- Time entries and timesheets per person and period, and which ones are submitted.
Who sees what
- Read-only
- The connector reads. It does not request or approve leave, submit or approve expenses, or change a timesheet or employee record.
- Company key, access per group
- Lucca’s API connects with a key or client your Lucca admin creates for the company, not with each person’s own Lucca login. So Deployed OS decides who gets it: admins choose which groups get Lucca, and a group without access never sees the connector.
- A key that reaches only what it needs
- Your admin sets the key’s role or scopes in Lucca, down to the establishments it may see. We ask only for the modules you want, and leave payroll and salary data out unless you ask, and then only for the groups you name.
- Every call logged
- Who asked, what was read and when. Deployed OS keeps the log, and it can be exported.
Set up the Lucca connector in three steps
Lucca MCP: common questions
Not as far as we know. Lucca has a documented API, and a few third parties offer Lucca MCP servers. We build the connector on Lucca’s API, so the answers can be used in Claude and ChatGPT next to your other systems, with access per group and a log.
No. The connector reads the directory, time off, expense reports and timesheets. It does not request or approve leave, submit expenses or edit records.
Nobody, unless you decide otherwise. The connector reaches only what your Lucca admin gives its key, and we do not ask for payroll or salary data by default. If it should be readable, we keep it to the groups you name, such as HR or payroll, and every call is logged.
No. Lucca’s API connects with company credentials, so the connector cannot apply each person’s own Lucca permissions. Access is set in Deployed OS instead: which groups get Lucca, and which modules and establishments the key reaches at all.
Deployed is an EU company and fully GDPR compliant, and you choose where your data is stored, down to the city. Lucca data is fetched when someone asks for it.
It depends on the size of your team. Get in touch and we will walk you through it.
See it on your own tools.
Tell us which systems your company runs on. We’ll show you what your team can ask, and what IT gets to control.