FRENES

Legal · MCP server

LibreJustice: MCP server, setup and security

LibreJustice is an open-source MCP server published on GitHub that lets an AI agent search case law and consult legal texts consolidated at relevant dates. Its repository has 29 stars and its last commit is from October 11, 2026 and it is licensed under Apache-2.0.

OfficialActively maintainedRemote server

What LibreJustice does

According to its repository: “French and European case law (Conseil d'État, Cour de cassation, ECHR, CJEU and more) linked to point-in-time consolidated legal texts, with hybrid search.”

The Model Context Protocol (MCP) is a standard plug between an AI agent and an outside service: once the server is connected, its tools show up in the agent, which decides when to call them. LibreJustice is listed under Legal, a category of 14 servers in the directory, where it ranks #7 by stars.

Topics declared by the repository: case-law, claude-skills, france, jurisprudence, legal, legaltech.

Installing and connecting LibreJustice

Distribution modes declared in the official MCP registry:

  • remote server (streamable-http): you connect to it by URL, with nothing to install locally

It works with any MCP-compatible client (Claude Desktop, Claude Code, Cursor, VS Code, Codex and most recent agents). You add one entry to the client's MCP configuration: server name, start command or URL, environment variables. Project language: Python, Rust.

Security: what to check

Connecting an MCP server means installing software that talks straight to your agent: it runs with your rights and the model trusts its tool descriptions. The risk therefore depends on what it can touch and how far its code can be trusted.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to LibreJustice. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on July 2, 2026, the librejustice/librejustice repository has 29 stars and 2 forks, with 1 open issues. It has more stars than 44% of the servers in the directory. It received changes this month. Version published in the registry: 1.18.0 (September 30, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

OpenMetadataOpenMetadata : 15.6K15.6KMelta UIMelta UI : 202202LogclawLogclaw : 7979DCC MCP CoreDCC MCP Core : 7070Open AgreementsOpen Agreements : 6161Us legal MCPUs legal MCP : 3838LibreJusticeLibreJustice : 2929Korean rnd regs MCPKorean rnd regs MCP : 1414
GitHub stars of the most followed servers in the category (log scale); LibreJustice in orange. Checked October 25, 2026.

Verdict

LibreJustice is one of the most solid servers in its category: followed, maintained and well framed.

Strengths

  • Maintained by the service's own vendor
  • Active project: recent commit
  • Listed in the official MCP registry
  • Usable remotely, without installation
  • Permissive licence (Apache-2.0)

Frequently asked questions

How do I install LibreJustice?

LibreJustice is distributed as a remote server. Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of librejustice/librejustice.

Is LibreJustice free?

The code is published under the Apache-2.0 licence and can be used free of charge.

Is LibreJustice safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Yes: the awesome-mcp-servers list marks it as the service vendor's official implementation.

What are the alternatives to LibreJustice?

In the same category: OpenMetadata, Melta UI, Open Agreements, and DCC MCP Core.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score