rechtspraak-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PRUDAI_BASE_URL | No | Base URL for the viewer deeplinks. | https://prudai.com |
| RECHTSPRAAK_DEBUG | No | 1 logs upstream requests to stderr. | 0 |
| LIDO_REST_ENDPOINT | No | Override the LiDO service endpoint. | KOOP default |
| RECHTSPRAAK_USER_AGENT | No | User-Agent sent upstream. | rechtspraak-mcp/… |
| RECHTSPRAAK_HTTP_TIMEOUT_MS | No | Upstream request timeout. | 30000 |
| RECHTSPRAAK_BULK_CONCURRENCY | No | Concurrency for bulk tools. | 4 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_uitsprakenA | Search Dutch case law (jurisprudentie/uitspraken) via the official Open Data API and get back ECLIs with links to the ruling and a PrudAI viewer. This is a faceted search: filter by rechtsgebied, instantie, date range and document type. It does not do free-text keyword matching. If you already have an ECLI, pass it as |
| search_uitspraken_bulkA | Run several Open Data lookups at once (3–10 entries). Pass ECLIs to resolve a batch of decisions' summaries in one call. Note: Open Data has no free-text matching, so non-ECLI terms fall back to facet-only results — prefer get_uitspraken_bulk when you already have the ECLIs. Use to cast a broad net before narrowing down via get_uitspraak. |
| get_uitspraakA | Fetch the full text and metadata of a single Dutch court decision by ECLI, from the official Open Data API (data.rechtspraak.nl). Returns metadata (court, date, rechtsgebied, zaaknummer), the plain-text body, formal relations (conclusie/cassatie/etc.), and links to the ruling on rechtspraak.nl plus a PrudAI viewer. If the ECLI is not published or has no body text, the tool says so — do not invent or cite it in that case. |
| get_uitspraken_bulkA | Fetch multiple Dutch court decisions by ECLI in one call (1–10 ECLIs) from the official Open Data API. Returns a per-ECLI result with the body text, metadata, relations, and links — or an error for any ECLI that is unpublished or not found. |
| list_waardelijstenA | List the Rechtspraak value lists (waardelijsten) used to build valid search filters: instanties, instanties_buitenlands, rechtsgebieden, proceduresoorten, niet_nederlandse_uitspraken. 'rechtsgebieden' and 'instanties' return the identifiers/URIs you pass to search_uitspraken (rechtsgebied / instanties). Call without a name to see the available lists. |
| lido_relatedA | Get the LiDO citation graph around a Dutch ECLI: rulings that cite it or are cited by it, referenced statute articles, and official publications, with typed Dutch link labels (e.g. 'Verwijst naar', 'Conclusie', 'Vernietigt'). Data comes from KOOP's live LiDO service (linkeddata.overheid.nl). Use it to position a ruling (is it a landmark? what does it cite?). Read-only and bounded (per-direction limit default 100, max 250). This returns structure, not full text — use get_uitspraak for the text of any neighbour. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: search returns summaries with facets, get returns full text by ECLI, bulk variants handle multiple ECLIs, list_waardelijsten provides filter vocabulary, and lido_related maps citations. Even the overlap between search_uitspraken and get_uitspraak when given an ECLI is unambiguous because one returns a summary and the other full text.
The set predominantly follows a consistent verb_noun pattern (search_*, get_*, list_*) with a uniform _bulk suffix for batch operations. The sole deviation is 'lido_related', which uses a noun-adjective form instead of a verb, but it is still clear and does not disrupt overall predictability.
Six tools is well-scoped for a case law search and retrieval server. Each tool serves a distinct aspect: searching, fetching, bulk operations, value lists, and citation analysis, with no redundancy or glaring omissions.
The server covers the core workflow: discover filter values, search for summaries, retrieve full texts, bulk-fetch multiple decisions, and explore citations. Minor gaps like lack of search by case number or free-text search are noted, but the official API does not support these, so the surface is appropriate.