Skip to main content
Glama

ris-austria-mcp-server

by io.github.cyanheads

Search Austrian Case Law

ris_search_case_law
Read-onlyIdempotent

Search Austrian case law (Judikatur) in ONE court or tribunal per call — court is required: vfgh (Constitutional Court), vwgh (Supreme Administrative Court), justiz (ordinary courts incl. OGH, selected decisions), bvwg (federal administrative), lvwg (state administrative), dsk (data protection authority), normenliste (VwGH norm index), dok, pvak, gbk, verg, upts (party transparency), and the historical uvs, asylgh, ubas, umse, bks. Cross-court research is one call per court (calls are cheap); historical bodies are closed windows with successors — codes, windows, and Geschäftszahl examples: ris_list_reference topic courts. Filter by full-text query, cited norm ("DSG §1", "DSGVO Art32" — the highest-value filter), exact case_number (Geschäftszahl), decision date range, decision_type (headnote vs full text), decision_kind, or the court-conditional filters: issuing_body (dsk/dok/pvak/verg), court_name/legal_area/subject_area (justiz), state (lvwg/uvs), party (upts), commission/senate/discrimination_ground (gbk), subject_law (bks), collection_number (vfgh/vwgh/uvs). For a known Geschäftszahl or VfSlg/VwSlg cite, ris_lookup_citation resolves it directly.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
normNoCited-provision filter (Norm) — "DSG §1", "DSGVO Art32", "GewO 1994 §129", matching the format returned in norms_cited. The highest-value case-law filter.
pageNo1-based result page. Default 1.
courtYesWhich court/tribunal application to search — one per call. Codes, coverage windows, and successor mapping: ris_list_reference topic courts.
partyNoPolitical party the decision concerns (upts only). Documented values: ÖVP, SPÖ, FPÖ, KPÖ, BZÖ, Team Stronach — the filter is full-text, and further party names appear in live data (e.g. "Wandel").
queryNoFull-text search over decisions (Suchworte). Boolean UND/ODER/NICHT or AND/OR/NOT, quoted phrases, trailing-only * wildcard.
stateNoWhich of the nine state administrative courts/senates to search (lvwg and uvs only).
senateNoCommission senate (gbk only).
sort_byNoSort column. Default: upstream order. Not available for court: normenliste, which indexes laws rather than decisions.
page_sizeNoDocuments per page — RIS accepts 10, 20, 50, or 100. Default 20.
commissionNoEqual-treatment commission (gbk only): federal (Bundes-Gleichbehandlungskommission) or general (Gleichbehandlungskommission).
court_nameNoFilter within the ordinary courts (justiz only) — "OGH", "OLG Wien", "LG Linz".
decided_toNoLatest decision date (YYYY-MM-DD).
legal_areaNoLegal area (Rechtsgebiet, justiz only): civil (Zivilrecht) or criminal (Strafrecht).
case_numberNoExact Geschäftszahl — returns that decision’s documents. Formats differ per court (examples: ris_list_reference topic courts). Not available for normenliste.
subject_lawNoMedia statute the case concerns (Bereich, bks only) — e.g. "ORF-Gesetz", "Privatradiogesetz".
decided_fromNoEarliest decision date (YYYY-MM-DD). Not available for normenliste.
issuing_bodyNoDeciding body (EntscheidendeBehoerde) — dsk, dok, pvak, and verg only. dsk: Datenschutzbehoerde (2014+) or Datenschutzkommission (up to 2013). Full value lists: ris_list_reference topic issuing_bodies.
subject_areaNoSubject-area taxonomy filter (Fachgebiet, justiz only) — 39 exact German values like "Datenschutzrecht", validated locally: ris_list_reference topic justiz_subject_areas. The corpus carries no tagged documents yet (every value returns 0 hits, verified 2026-07-05) — filter with query or norm instead until RIS populates the tags.
changed_sinceNoCoarse recency filter — decisions changed in RIS within the interval. For exact windows use ris_track_changes.
decision_kindNoDecision kind (Entscheidungsart) — per-court value sets, validated locally: ris_list_reference topic decision_kinds. No such parameter exists for normenliste, dok, pvak, umse, bks, or upts. For justiz the four documented values are not yet populated in the corpus (every value returns 0 hits, verified 2026-07-05) — filter justiz with query or norm instead.
decision_typeNoSearch headnotes (Rechtssätze), full decision texts (Entscheidungstexte), or both (all, the default). Not available for gbk, upts, or normenliste.all
sort_directionNoSort direction; applies with sort_by.
collection_numberNoOfficial collection number (Sammlungsnummer). vfgh, vwgh, and uvs only, and the accepted form differs: vfgh and uvs store the bare number and match it dotted or undotted ("19632", "19.632"), while vwgh stores the full labelled undotted cite — pass "VwSlg 18000 A/2010", or the space-anchored prefix "VwSlg 18000 *" when the part letter or year is unknown. A bare or dotted number matches nothing under vwgh.
discrimination_groundNoDiscrimination ground (gbk only): Alter (age), EthnischeZugehoerigkeit (ethnic origin), Geschlecht (gender/sex), Mehrfachdiskriminierung (multiple grounds), Religion (religion), SexuelleOrientierung (sexual orientation), Weltanschauung (worldview/belief). Upstream German enum values, sent verbatim.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNo1-based page number RIS served.
errorNoPresent when the call failed. Absent on success.
noticeNoZero-hit guidance — names the likely cause and the concrete next call.
resultsNoMatching documents for the requested page — decisions, or indexed laws under court normenliste. Totals and paging in enrichment.
pageSizeNoPage size RIS applied.
truncatedNoPresent and true when more pages exist beyond this one — raise page to continue.
totalCountNoTotal matching documents across all pages.

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, and the description adds substantial non-obvious behavior: historical bodies are 'closed windows with successors', calls are cheap, and it discloses that subject_area and justiz decision_kind are unpopulated ('every value returns 0 hits, verified 2026-07-05'). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is long, but it front-loads the one non-negotiable constraint (one court per call, court required) and every subsequent clause earns its place for a 24-parameter, 17-court tool. Some redundancy exists between the description and the already-rich schema property descriptions, but the grouping logic justifies the length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For the most complex tool in the suite — 24 parameters, 17 courts, heavy court-conditional filter logic — the description covers every filter, routes value lookups to ris_list_reference, flags unpopulated fields, and notes the output schema handles return values. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema's own property descriptions are already rich (norm, court, collection_number each carry format detail). The description adds value beyond that by grouping filters by court conditionality (issuing_body for dsk/dok/pvak/verg, court_name/legal_area for justiz, etc.) and flagging norm as 'the highest-value filter' — genuine organizational insight rather than repetition.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource ('Search Austrian case law (Judikatur)') and immediately distinguishes itself by the hard constraint 'ONE court or tribunal per call — court is required'. It differentiates from siblings by naming ris_lookup_citation as the alternative for known cites, and the court enumeration makes the scope unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes agents to ris_lookup_citation when a Geschäftszahl or VfSlg/VwSlg cite is known, and to ris_list_reference for codes, windows, and Geschäftszahl examples. It explains cross-court work ('one call per court (calls are cheap)') but does not explicitly contrast against ris_search_legislation/announcements/drafts — though tool names and resource type make those exclusions obvious.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All ris-austria-mcp-server toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.8/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: fetching documents, resolving citations, searching different content domains (legislation, case law, gazette, drafts, announcements), listing reference data, and tracking changes. No two tools overlap in function or could be confused for the same task.

Naming Consistency5/5

All tools follow a uniform ris_[verb]_[noun] snake_case pattern, using verbs like get, list, lookup, search, and track. The naming convention is entirely predictable and consistent across the server.

Tool Count5/5

With 9 tools, the server is well-scoped for its purpose of Austrian legal information retrieval. Each tool serves a distinct and necessary function, with no redundancy or unnecessary bloat.

Completeness5/5

The tool set covers the full lifecycle of legal research: reference lookup, citation resolution, five content-type searches, document retrieval with format control, and delta tracking for mirrors. There are no obvious gaps—every action an agent might need is available.

Resources