> For the complete documentation index, see [llms.txt](https://docs.glbnxt.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.glbnxt.com/platform/mcp-servers/dictum.md).

# DICTUM

**Dutch and EU primary law, verbatim, for AI assistants.** One MCP endpoint over every published ruling of the Dutch courts, the disciplinary courts and the Court of Justice of the EU, every Dutch law and regulation in force with its historical versions, the local regulations, the EU acts, the parliamentary papers of bills, and the links between all of them; next to that the decisions and guidance of Dutch and EU regulators, the rulings of dispute committees such as Kifid and De Geschillencommissie, and open-access legal literature, each marked as not binding. The assistant searches, reads the full text, checks later case law and quotes the decisive paragraph with its number. DICTUM never writes legal text itself.

* **What it holds**

  About 1.1 million rulings and decisions, 2.4 million articles of law with 148 thousand historical versions, 17 thousand EU acts, the case law of the Court of Justice and the European Court of Human Rights, 67 thousand Kamerstukken with the moties and answered Kamervragen, and regulators' guidance and legal literature. Live numbers on [Sources and coverage](https://docs.glbnxt.com/platform/mcp-servers/dictum/coverage).
* **How an assistant uses it**

  Eleven tools and four prompts over one endpoint: `search_rulings`, `get_ruling`, `find_by_statute`, `get_article` on any date, `citing_rulings`, `find_history`, `search_literature` and more. See [Tools](https://docs.glbnxt.com/platform/mcp-servers/dictum/tools) and the [Research method](https://docs.glbnxt.com/platform/mcp-servers/dictum/method).
* **Where it works**

  Claude.ai and Claude Desktop, Open WebUI, LibreChat, Claude Code and any MCP client with OAuth, always through the GLBNXT login. See [Connect](https://docs.glbnxt.com/platform/mcp-servers/dictum/connect).
* **How good it is**

  Measured every night against a question set with verified answers; numbers and method on [Quality](https://docs.glbnxt.com/platform/mcp-servers/dictum/quality).

### Why primary law, verbatim

A legal answer is only as good as its source. DICTUM returns the paragraphs of the ruling and the text of the article, each with the identifier a lawyer cites (ECLI and rechtsoverweging, article and law) and a link to the official publication. The assistant's reasoning sits on top of that and stays separable from it. Every text DICTUM serves may be reused: Dutch rulings and legislation carry no copyright (Auteurswet art. 11), EU texts may be reused under Commission Decision 2011/833/EU, and every other source under its own published terms. Texts that are not binding law (a regulator's guidance, a dispute committee's ruling, an article in a journal) say so on every result. [Sources and reuse terms](https://docs.glbnxt.com/platform/mcp-servers/dictum/terms).

### What it is not

Not a legal database with its own commentary, not a model, not a chatbot. DICTUM is the retrieval layer under an assistant you already use. The assistant decides what to ask and how to write; DICTUM makes sure every claim can be checked.

### Who runs it

[GLBNXT](https://glbnxt.com), on its own servers in the EU, with its own model hub for embeddings and reranking. No text leaves that infrastructure for indexing. DICTUM is an integral part of the GLBNXT platform: the [GLBNXT Trust Center](https://www.glbnxt.com/trust-center) and GLBNXT's [terms, DPA and SLA](https://www.glbnxt.com/legal#service-level-agreement) apply. Contact: through your GLBNXT account manager.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.glbnxt.com/platform/mcp-servers/dictum.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
