Skip to content
← Connectors

Public dataConnector

Info légale FR

Search French case law, read a code article as it stood on any date, or search agreements by IDCC, from Claude or ChatGPT, through Tulina's MCP server.

Official site: www.legifrance.gouv.fr

What it can do

3 read

  • 01
    Read

    Search case law across the Cour de cassation, Conseil d'État, Conseil constitutionnel, CEDH and CJUE

  • 02
    Read

    Read a code article as it stood on a given date, with its revision history

  • 03
    Read

    Search branch-wide collective agreements (KALI) by IDCC

Open data: no credential to issue, hold or revoke. It reads the same source a person could look up by hand, at a scale nobody has time to do by hand.

How do you connect Légifrance to Claude and ChatGPT?

Through Tulina's MCP server, reading Légifrance and DILA's own open data directly. Search case law across the Cour de cassation, Conseil d'État, Conseil constitutionnel, CEDH and CJUE, read a code article as it stood on a given date with its revision history, or search collective agreements by IDCC — 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 Info légale FR 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 Info légale FR 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 Info légale FR returns something usable instead of something generic.

Processes that run on Info légale FR

None published yet.

See Tulina in a 30-minute demo.

Book a demo