French company dataConnector
INPI
Pull directors, legal representatives and filed annual accounts for any French company into Claude or ChatGPT, through Tulina's own INPI MCP server.
Official site: data.inpi.fr
What it can do
3 read
- 01Read
List the directors and legal representatives of a company
- 02Read
Retrieve the list of filed annual accounts for a SIREN
- 03Read
Pull a specific filing by closing date
An empty result means "not filed" or "not public", never "no revenue". Filing accounts publicly is optional and many small companies decline; scoring the absence as a negative quietly penalises them for exercising a right.
Directors are named individuals, which makes this the connector where minimisation stops being theoretical. Open access is not a lawful basis, so what comes back can be narrowed before it reaches a model at all.
How do you connect INPI to Claude and ChatGPT?
Through Tulina's own MCP server. List the directors and legal representatives of a French company, pull the annual accounts it has filed, or retrieve one filing by its closing date — from the same chat as Claude or ChatGPT.
Why through Tulina
The connection was never the hard part.
Most systems now publish their own way for a model to reach them, and that is good: it is what Tulina connects to. The hard part is deciding who may use it, what it is allowed to return, and what the model knows before it asks.
The keys stay in one place
YouTeamOrganisation
Connect INPI once. The credential is encrypted in a vault, never held in clear, and never pasted into a chat or a workflow file. A person uses their own key where they have one, their team's where they do not, the organisation's after that, so nobody is blocked and nobody holds more access than they need. Revoke it once and everything running on it stops.
What leaves is filtered before it leaves
fields droppedmasked or hashedpseudonymised
Roles decide who can reach INPI at all. Beyond that, a policy on the connector itself decides what comes back. The data is minimised at the source rather than after it has already reached a model.
Every call is on the record
whatwhowhen
Runs are logged for the organisation. That is what makes an automated action reviewable after the fact, and it is what a security review asks for first.
The run starts knowing your company
namingkey accountsdecisions
A direct connection gives a model access. It does not tell it how your company names things, which accounts matter, or what was decided last quarter. Tulina carries that across every tool, so the same request against INPI returns something usable instead of something generic.
Processes that run on INPI
Qualify inbound leads
AI lead scoring for inbound leads: each one matched to its legal entity, scored on real headcount and filed accounts, and written back with the reason.
5 steps →Reply to every LinkedIn conversation
Four times a day, LinkedIn threads where the other person wrote last come back to you in Slack with a reply drafted in your style. Nothing is sent for you.
9 steps →
