OpenCaseLaw — Swiss Caselaw, Statutes & Doctrine

Official42 toolsLive

by jonashertner · Python

1M+ Swiss court decisions, statutes & doctrine with citation graph (DE/FR/IT). CC0, free, 42 tools.

Model Context Protocol (MCP) Server: ch.opencaselaw/swiss-caselaw

This MCP server provides open Swiss legal research data, covering 1M+ Swiss court decisions, statutes, and doctrine. It includes a citation graph with coverage across DE/FR/IT, spanning 1875–today, and is offered as CC0 data. The project exposes functionality via MCP and also includes REST, CLI, and Parquet exports.

🛠️ Key Features

1M+ decisions, statutes & doctrine
Citation graph with DE/FR/IT coverage
All 26 cantons; 1875–today
CC0 free dataset; MIT code
MCP + REST + CLI + Parquet

🚀 Use Cases

Find Swiss decisions from federal and cantonal courts
Trace citations between cases and identify leads
Support AI-assisted legal research and dataset workflows

⚡ Developer Benefits

42 tools exposed by the MCP server
API documentation available at the MCP API docs URL
Downloadable dataset and programmatic access patterns (MCP/REST/CLI/Parquet)

⚠️ Limitations

Scope is limited to Swiss legal materials and citations (DE/FR/IT).

Topics

ai-agentscaselawcitation-graphdatasetlegal-datalegal-researchmcpmcp-servermodel-context-protocolopen-dataswiss-lawswitzerland

Captured live from the server via tools/list.

search

ChatGPT Deep Research compatibility tool. Returns a ranked list of Swiss court decisions matching a query, each as {id, title, url, snippet}. Pair with `fetch` to retrieve a decision's full text by id. General (non-deep-research) clients should prefer `search_decisions`, which exposes filters (court, canton, date, language) and richer metadata.

Parameters2

query	string	required	Natural-language or keyword query.
limit	integer	optional	Max results (default 10, max 50).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Natural-language or keyword query."
    },
    "limit": {
      "type": "integer",
      "description": "Max results (default 10, max 50).",
      "default": 10
    }
  },
  "required": [
    "query"
  ]
}

fetch

ChatGPT Deep Research compatibility tool. Fetches one Swiss decision's full text by id, returning {id, title, text, url, metadata}. The id comes from a `search` result (a decision_id like bger_6B_1234_2025; a docket number or BGE reference also resolves). General clients should prefer `get_decision`.

Parameters1

string

required

Decision id from a search result (decision_id, docket, or BGE reference).

Raw schema

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Decision id from a search result (decision_id, docket, or BGE reference)."
    }
  },
  "required": [
    "id"
  ]
}

search_decisions

Use this tool to find COURT DECISIONS (Rechtsprechung): 1,050,000+ Swiss federal and cantonal decisions plus ~2,800 ECtHR decisions concerning Switzerland. Full-text search with keywords, phrases (in quotes), Boolean operators (AND, OR, NOT), prefix matching (word*), docket lookup (6B_1234/2025) and column-scoped search (regeste:keyword). Filter by court, canton, language, date range, chamber. Results are relevance-ranked and enriched with citation counts, statute references and is_leading_case. Use offset to page. Most recent decisions: empty query + sort='date_desc' + court filter. Not for statutes (search_laws), commentary (search_scholarship), or administrative guidance (search_practice).

Parameters13

query	string	optional	Search query. Best results: 3-8 precise terms, one search per legal issue — never paste document text. Max 4,000 chars; input over 500 chars is auto-condensed to its citations + key terms. Examples: - Simple: Mietrecht Kündigung - Phrase: "Treu und Glauben" - Boolean: Arbeitsrecht AND Kündigung NOT Probezeit - Prefix: Verfassung* - By docket: 6B_1234/2025 - By article: "Art. 8 BV" - Column: regeste:Mietrecht AND full_text:Kündigung
court	string	optional	Filter by court code. Federal: bger, bge, bvger, bstger, bpatger, mkg. European Court of Human Rights (Switzerland): bge_egmr (BGE-published DE translations), hudoc_ch (HUDOC Switzerland-tagged), ecthr_chamber, ecthr_grand_chamber, ecthr_committee. Cantonal: zh_obergericht, be_verwaltungsgericht, etc.
canton	string	optional	Filter by canton (CH for federal, ZH, BE, GE, etc.)
language	string	optional	OPTIONAL filter. Restricts results to ONE language. Omit (recommended default) to search across all languages — Swiss federal decisions are issued in DE, FR, or IT depending on the case, so a language filter silently excludes valid hits in the other two. Set ONLY when the user explicitly asks for a single-language result; do NOT auto-apply based on the conversation's language.
date_from	string	optional	Start date (YYYY-MM-DD)
date_to	string	optional	End date (YYYY-MM-DD)
chamber	string	optional	Filter by chamber/division (substring match). Examples: 'Abteilung V' (BVGer asylum), 'Zivilrechtliche', 'CASSO', 'Strafrechtliche'
marked_for_publication	boolean	optional	If true, return only Federal Supreme Court rulings flagged for the official BGE collection (the Neuheiten '*' marker, 'für die Publikation vorgesehen') — future leading cases, flagged before the BGE number is assigned. Populated for BGer decisions published from mid-2026 onward; older rows are unflagged.
limit	integer	optional	Max results to return (max 2000). Omit to use default of 50. Do not set low values like 5 or 10 unless the user explicitly asked for fewer results.
offset	integer	optional	Skip this many results (for pagination). Default 0.
sort	string	optional	Sort order: 'relevance' (default for FTS), 'date_desc', 'date_asc'.
fields	string	optional	Response detail level: 'full' (default) includes snippet/regeste/URL, 'compact' returns only docket, date, court, language, decision_id.
include_pinpoint	boolean	optional	Attach a pinpoint Erwägung citation to the top results when a confident match exists (BM25 over the per-decision Erwägungen FTS5 index, gap-confidence ≥ medium). Defaults true; set false to skip the per-result lookup (typically saves 0.2-2 s on the top 5 results; more for long or statute-heavy queries).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 4000,
      "description": "Search query. Best results: 3-8 precise terms, one search per legal issue — never paste document text. Max 4,000 chars; input over 500 chars is auto-condensed to its citations + key terms. Examples:\n- Simple: Mietrecht Kündigung\n- Phrase: \"Treu und Glauben\"\n- Boolean: Arbeitsrecht AND Kündigung NOT Probezeit\n- Prefix: Verfassung*\n- By docket: 6B_1234/2025\n- By article: \"Art. 8 BV\"\n- Column: regeste:Mietrecht AND full_text:Kündigung"
    },
    "court": {
      "type": "string",
      "description": "Filter by court code. Federal: bger, bge, bvger, bstger, bpatger, mkg. European Court of Human Rights (Switzerland): bge_egmr (BGE-published DE translations), hudoc_ch (HUDOC Switzerland-tagged), ecthr_chamber, ecthr_grand_chamber, ecthr_committee. Cantonal: zh_obergericht, be_verwaltungsgericht, etc."
    },
    "canton": {
      "type": "string",
      "description": "Filter by canton (CH for federal, ZH, BE, GE, etc.)"
    },
    "language": {
      "type": "string",
      "description": "OPTIONAL filter. Restricts results to ONE language. Omit (recommended default) to search across all languages — Swiss federal decisions are issued in DE, FR, or IT depending on the case, so a language filter silently excludes valid hits in the other two. Set ONLY when the user explicitly asks for a single-language result; do NOT auto-apply based on the conversation's language.",
      "enum": [
        "de",
        "fr",
        "it",
        "rm"
      ]
    },
    "date_from": {
      "type": "string",
      "description": "Start date (YYYY-MM-DD)"
    },
    "date_to": {
      "type": "string",
      "description": "End date (YYYY-MM-DD)"
    },
    "chamber": {
      "type": "string",
      "description": "Filter by chamber/division (substring match). Examples: 'Abteilung V' (BVGer asylum), 'Zivilrechtliche', 'CASSO', 'Strafrechtliche'"
    },
    "marked_for_publication": {
      "type": "boolean",
      "description": "If true, return only Federal Supreme Court rulings flagged for the official BGE collection (the Neuheiten '*' marker, 'für die Publikation vorgesehen') — future leading cases, flagged before the BGE number is assigned. Populated for BGer decisions published from mid-2026 onward; older rows are unflagged."
    },
    "limit": {
      "type": "integer",
      "description": "Max results to return (max 2000). Omit to use default of 50. Do not set low values like 5 or 10 unless the user explicitly asked for fewer results.",
      "default": 50
    },
    "offset": {
      "type": "integer",
      "description": "Skip this many results (for pagination). Default 0.",
      "default": 0
    },
    "sort": {
      "type": "string",
      "description": "Sort order: 'relevance' (default for FTS), 'date_desc', 'date_asc'.",
      "enum": [
        "relevance",
        "date_desc",
        "date_asc"
      ]
    },
    "fields": {
      "type": "string",
      "description": "Response detail level: 'full' (default) includes snippet/regeste/URL, 'compact' returns only docket, date, court, language, decision_id.",
      "enum": [
        "full",
        "compact"
      ]
    },
    "include_pinpoint": {
      "type": "boolean",
      "description": "Attach a pinpoint Erwägung citation to the top results when a confident match exists (BM25 over the per-decision Erwägungen FTS5 index, gap-confidence ≥ medium). Defaults true; set false to skip the per-result lookup (typically saves 0.2-2 s on the top 5 results; more for long or statute-heavy queries).",
      "default": true
    }
  },
  "required": []
}

get_decision

Fetch a single court decision with full text. Look up by decision_id (e.g., bger_6B_1234_2025), docket number (e.g., 6B_1234/2025), or partial match. Full text is truncated at 200,000 characters for very long decisions. Set full_text=false to get only metadata and regeste.

Parameters2

decision_id	string	required	Decision ID, docket number, or partial docket
full_text	boolean	optional	Include full text in response (default true). Set false to get only metadata and regeste.

Raw schema

{
  "type": "object",
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "Decision ID, docket number, or partial docket"
    },
    "full_text": {
      "type": "boolean",
      "description": "Include full text in response (default true). Set false to get only metadata and regeste.",
      "default": true
    }
  },
  "required": [
    "decision_id"
  ]
}

get_decisions

Use this tool to fetch SEVERAL decisions at once (1-10 ids) instead of calling get_decision repeatedly. Same data per decision — canonical citation strings, Markdown link, Regeste, metadata — in ONE call. Prefer this whenever you are about to read more than one decision from a search result: it is the difference between one tool call and ten, which matters because clients cap tool calls per turn. full_text defaults to FALSE here (unlike get_decision) because ten full judgments exceed connector response limits; set it true only for a short id list, and each text is excerpted with the cut disclosed. Ids not found are reported individually — the rest of the batch still returns.

Parameters3

decision_ids	array	required	Decision ids, docket numbers or BGE references (e.g. ['bge_BGE_140_III_86', '6B_1234/2025']).
full_text	boolean	optional	Include an excerpt of each decision's full text (default false — Regeste + metadata only).
max_chars_per_decision	integer	optional	Per-decision text cap when full_text is true (default 20,000; total response stays under connector limits).

Raw schema

{
  "type": "object",
  "properties": {
    "decision_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 10,
      "description": "Decision ids, docket numbers or BGE references (e.g. ['bge_BGE_140_III_86', '6B_1234/2025'])."
    },
    "full_text": {
      "type": "boolean",
      "default": false,
      "description": "Include an excerpt of each decision's full text (default false — Regeste + metadata only)."
    },
    "max_chars_per_decision": {
      "type": "integer",
      "default": 20000,
      "description": "Per-decision text cap when full_text is true (default 20,000; total response stays under connector limits)."
    }
  },
  "required": [
    "decision_ids"
  ]
}

list_courts

List all available courts with decision counts, date ranges, and language coverage. Use this to discover what data is available.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_statistics

Get aggregate statistics about the dataset. Optionally filter by court, canton, or year.

Parameters3

court	string	optional	Filter by court code
canton	string	optional	Filter by canton code
year	integer	optional	Filter by year

Raw schema

{
  "type": "object",
  "properties": {
    "court": {
      "type": "string",
      "description": "Filter by court code"
    },
    "canton": {
      "type": "string",
      "description": "Filter by canton code"
    },
    "year": {
      "type": "integer",
      "description": "Filter by year"
    }
  }
}

find_citations

Given a decision_id, show what it cites and what cites it. Uses the reference graph database with 9.65M citation edges. Returns resolved citations with confidence scores and unresolved references.

Parameters5

decision_id	string	required	Decision ID (e.g., bger_6B_1_2025)
direction	string	optional	Citation direction: 'both' (default), 'outgoing', or 'incoming'
min_confidence	number	optional	Minimum confidence score for resolved citations (0-1, default 0.3)
limit	integer	optional	Max citations per direction per page (default 50, max 200)
offset	integer	optional	Pagination offset per direction (default 0). The response reports _total and _has_more; when has_more is true, re-query with offset=next_offset to retrieve the rest (heavily-cited leading decisions exceed the 200-per-page cap).

Raw schema

{
  "type": "object",
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "Decision ID (e.g., bger_6B_1_2025)"
    },
    "direction": {
      "type": "string",
      "description": "Citation direction: 'both' (default), 'outgoing', or 'incoming'",
      "enum": [
        "both",
        "outgoing",
        "incoming"
      ],
      "default": "both"
    },
    "min_confidence": {
      "type": "number",
      "description": "Minimum confidence score for resolved citations (0-1, default 0.3)",
      "default": 0.3
    },
    "limit": {
      "type": "integer",
      "description": "Max citations per direction per page (default 50, max 200)",
      "default": 50
    },
    "offset": {
      "type": "integer",
      "description": "Pagination offset per direction (default 0). The response reports *_total and *_has_more; when has_more is true, re-query with offset=next_offset to retrieve the rest (heavily-cited leading decisions exceed the 200-per-page cap).",
      "default": 0
    }
  },
  "required": [
    "decision_id"
  ]
}

find_appeal_chain

Trace the appeal chain (Instanzenzug) for a decision. Shows prior instances (lower courts) and subsequent instances (appeals to higher courts). Reconstructs the full procedural path, e.g. Bezirksgericht → Obergericht → Bundesgericht. Uses the is_prior_instance flag from decision headers.

Parameters2

decision_id	string	required	Decision ID (e.g., bger_6B_1_2025)
min_confidence	number	optional	Minimum confidence score (0-1, default 0.3)

Raw schema

{
  "type": "object",
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "Decision ID (e.g., bger_6B_1_2025)"
    },
    "min_confidence": {
      "type": "number",
      "description": "Minimum confidence score (0-1, default 0.3)",
      "default": 0.3
    }
  },
  "required": [
    "decision_id"
  ]
}

find_leading_cases

Find the most-cited decisions for a topic or statute. Authority ranking based on citation graph. Filter by statute (law_code + article), topic query, court, and date range. Top-3 results auto-attach a `pinpoint` field {e_number, matched_sentence, confidence, url, score, source} anchoring the most-relevant Erwägung — see system instructions U3 for how to surface it. Each result also carries citation_string_{de,fr,it} + canonical_url + is_leading_case + citation_count for ready-to-quote Swiss-format citations.

Parameters8

query	string	optional	Optional text query to filter by topic (FTS search)
law_code	string	optional	Optional law code (e.g., BV, OR, ZGB, EMRK, StGB)
article	string	optional	Optional article number (requires law_code)
court	string	optional	Optional court filter (e.g., bger, bge, bvger)
date_from	string	optional	Optional start date (YYYY-MM-DD)
date_to	string	optional	Optional end date (YYYY-MM-DD)
limit	integer	optional	Max results (default 20, max 100)
include_pinpoint	boolean	optional	Attach a pinpoint Erwägung citation to the top 3 leading cases when a confident match exists. Defaults true.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Optional text query to filter by topic (FTS search)"
    },
    "law_code": {
      "type": "string",
      "description": "Optional law code (e.g., BV, OR, ZGB, EMRK, StGB)"
    },
    "article": {
      "type": "string",
      "description": "Optional article number (requires law_code)"
    },
    "court": {
      "type": "string",
      "description": "Optional court filter (e.g., bger, bge, bvger)"
    },
    "date_from": {
      "type": "string",
      "description": "Optional start date (YYYY-MM-DD)"
    },
    "date_to": {
      "type": "string",
      "description": "Optional end date (YYYY-MM-DD)"
    },
    "limit": {
      "type": "integer",
      "description": "Max results (default 20, max 100)",
      "default": 20
    },
    "include_pinpoint": {
      "type": "boolean",
      "description": "Attach a pinpoint Erwägung citation to the top 3 leading cases when a confident match exists. Defaults true.",
      "default": true
    }
  }
}

analyze_legal_trend

Year-by-year decision counts showing jurisprudence evolution. Use with a statute reference (law_code + article), a text query, or both. Returns yearly counts with visual bar chart.

Parameters6

query	string	optional	Optional text query (FTS search)
law_code	string	optional	Optional law code (e.g., BV, OR, EMRK). Requires article.
article	string	optional	Article number (requires law_code)
court	string	optional	Optional court filter
date_from	string	optional	Optional start date (YYYY-MM-DD)
date_to	string	optional	Optional end date (YYYY-MM-DD)

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Optional text query (FTS search)"
    },
    "law_code": {
      "type": "string",
      "description": "Optional law code (e.g., BV, OR, EMRK). Requires article."
    },
    "article": {
      "type": "string",
      "description": "Article number (requires law_code)"
    },
    "court": {
      "type": "string",
      "description": "Optional court filter"
    },
    "date_from": {
      "type": "string",
      "description": "Optional start date (YYYY-MM-DD)"
    },
    "date_to": {
      "type": "string",
      "description": "Optional end date (YYYY-MM-DD)"
    }
  }
}

draft_mock_decision

Build a research-only mock decision outline from user facts. Combines relevant Swiss case law retrieval with statute references. If possible, enriches statutes with Fedlex text excerpts. IMPORTANT: The tool may return clarification questions (high/medium priority). High-priority clarifications must be answered (via the clarifications parameter) before the tool will provide a conclusion. Call again with clarifications to get the full analysis.

Parameters8

facts	string	required	Detailed facts of the hypothetical or real case.
question	string	optional	Optional legal question to decide.
preferred_language	string	optional	Output/analysis language preference.
deciding_court	string	optional	Hypothetical deciding court (e.g., bger, bvger).
statute_references	array	optional	Optional explicit statute list. Each item: {law_code, article, paragraph?}.
fedlex_urls	array	optional	Optional Fedlex URLs used to fetch statute text. Useful when no built-in URL mapping is available.
clarifications	array	optional	Optional answers to prior clarification questions. Each item: {id, answer}. The tool withholds conclusion until high-priority clarifications are answered.
limit	integer	optional	Number of case-law exemplars (default 8, max 20).

Raw schema

{
  "type": "object",
  "properties": {
    "facts": {
      "type": "string",
      "description": "Detailed facts of the hypothetical or real case."
    },
    "question": {
      "type": "string",
      "description": "Optional legal question to decide."
    },
    "preferred_language": {
      "type": "string",
      "description": "Output/analysis language preference.",
      "enum": [
        "de",
        "fr",
        "it",
        "rm",
        "en"
      ]
    },
    "deciding_court": {
      "type": "string",
      "description": "Hypothetical deciding court (e.g., bger, bvger)."
    },
    "statute_references": {
      "type": "array",
      "description": "Optional explicit statute list. Each item: {law_code, article, paragraph?}.",
      "items": {
        "type": "object",
        "properties": {
          "law_code": {
            "type": "string"
          },
          "article": {
            "type": "string"
          },
          "paragraph": {
            "type": "string"
          }
        },
        "required": [
          "law_code",
          "article"
        ]
      }
    },
    "fedlex_urls": {
      "type": "array",
      "description": "Optional Fedlex URLs used to fetch statute text. Useful when no built-in URL mapping is available.",
      "items": {
        "type": "string"
      }
    },
    "clarifications": {
      "type": "array",
      "description": "Optional answers to prior clarification questions. Each item: {id, answer}. The tool withholds conclusion until high-priority clarifications are answered.",
      "items": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string"
          },
          "answer": {
            "type": "string"
          }
        },
        "required": [
          "id",
          "answer"
        ]
      }
    },
    "limit": {
      "type": "integer",
      "description": "Number of case-law exemplars (default 8, max 20).",
      "default": 8
    }
  },
  "required": [
    "facts"
  ]
}

get_case_brief

Structured case brief: regeste, Sachverhalt, key Erwägungen (first 12 only — for orientation, NOT a pinpoint ranking), Dispositiv, statutes, citation authority, related cases. Accepts BGE ref, decision_id, or docket. To pinpoint which Erwägung supports a specific claim, use find_relevant_erwaegung — never guess from key_erwaegungen alone.

Parameters1

case

string

required

Any case reference: BGE ref ('BGE 133 III 121', '133 III 121'), decision_id ('bge_BGE_133_III_121'), or docket number.

Raw schema

{
  "type": "object",
  "properties": {
    "case": {
      "type": "string",
      "description": "Any case reference: BGE ref ('BGE 133 III 121', '133 III 121'), decision_id ('bge_BGE_133_III_121'), or docket number."
    }
  },
  "required": [
    "case"
  ]
}

get_decision_structure

Structured decision fields: Sachverhalt (facts), Erwägungen as numbered paragraphs ('1', '1.1', '2.3'), Dispositiv (ruling), Regeste (BGE only). Federal decisions only; for cantonal use get_decision. Returns excerpts; for verbatim full text of one Erwägung, use get_erwaegung. PINPOINT POLICY: never guess. If user gave an e_number → verify with get_erwaegung. If user gave only a claim → use find_relevant_erwaegung (FTS5+BM25 with confidence labels). If neither is confident, report no_match — do NOT default to E. 3.1.

Parameters1

decision_id

string

required

decision_id ('bger_5A_42_2026', 'bge_140 III 86'), BGE reference, or docket number.

Raw schema

{
  "type": "object",
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "decision_id ('bger_5A_42_2026', 'bge_140 III 86'), BGE reference, or docket number."
    }
  },
  "required": [
    "decision_id"
  ]
}

get_erwaegung

Verbatim text of ONE numbered Erwägung — the citable unit in Swiss practice (e.g. 'BGE 140 III 86 E. 2.3'). Use when the user already gave an e_number. If only a claim was given (no e_number): use find_relevant_erwaegung — never guess. Returns text + sibling Erwägung numbers. e_number: '1', '2.3', '5.2.1', …

Parameters2

decision_id	string	required	decision_id, BGE reference, or docket number.
e_number	string	required	Erwägung number to retrieve (e.g. '2', '2.3', '5.2.1'). Leading 'E.' is stripped if present.

Raw schema

{
  "type": "object",
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "decision_id, BGE reference, or docket number."
    },
    "e_number": {
      "type": "string",
      "description": "Erwägung number to retrieve (e.g. '2', '2.3', '5.2.1'). Leading 'E.' is stripped if present."
    }
  },
  "required": [
    "decision_id",
    "e_number"
  ]
}

find_relevant_erwaegung

Find which Erwägung paragraph(s) match a legal claim. Server-side FTS5+BM25 over per-paragraph text; returns top-k with confidence labels (high/medium/low) and a highlighted_snippet wrapping the matched sentence in <mark>…</mark> (quote it verbatim). When no_match=true or confidence=low, do NOT cite any Erwägung — report no_match. Federal decisions only. Replaces the 'always-E.-3.1' guessing pattern.

Parameters3

decision_id	string	required	decision_id, BGE reference, or docket number. Must be a federal decision (structured Erwägungen).
claim	string	required	Free-text legal claim or proposition the user wants to verify against the decision. The more specific, the higher the confidence.
top_k	integer	optional	Number of top matches to return (default 3, max 10).

Raw schema

{
  "type": "object",
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "decision_id, BGE reference, or docket number. Must be a federal decision (structured Erwägungen)."
    },
    "claim": {
      "type": "string",
      "description": "Free-text legal claim or proposition the user wants to verify against the decision. The more specific, the higher the confidence."
    },
    "top_k": {
      "type": "integer",
      "description": "Number of top matches to return (default 3, max 10).",
      "default": 3
    }
  },
  "required": [
    "decision_id",
    "claim"
  ]
}

get_article_purpose

Return verbatim text from the Federal Council Botschaft (or Erläuterungsbericht) explaining the legislative purpose of a specific article. Joins the verbatim Botschaft corpus (post-2003 BBl publications, Akoma Ntoso XML where available, PDF fallback otherwise) with the article-Botschaft link table. Returns one entry per source — original Botschaft + any amendment Botschaften. All paragraphs are verbatim text the LLM can quote with `bbl_citation, S. {page}` references. USE THIS when the user asks 'what was the purpose of Art. X' or 'what did Parliament intend' or 'why does Art. X exist'. Coverage is rolling — empty `sources` means the verbatim corpus hasn't ingested that article's Botschaft yet; fall back to get_doctrine for the digest layer.

Parameters4

sr_number	string	required	SR (Systematische Rechtssammlung) number of the law, e.g. '220' for OR (Obligationenrecht), '101' for BV, '311.0' for StGB.
article	string	required	Article number, e.g. '41' for Art. 41 OR. Letter-suffixed forms like '41a' supported.
language	string	optional	Botschaft language (defaults to German).
max_paragraphs	integer	optional	Maximum paragraphs per Botschaft (default 8, max 20).

Raw schema

{
  "type": "object",
  "properties": {
    "sr_number": {
      "type": "string",
      "description": "SR (Systematische Rechtssammlung) number of the law, e.g. '220' for OR (Obligationenrecht), '101' for BV, '311.0' for StGB."
    },
    "article": {
      "type": "string",
      "description": "Article number, e.g. '41' for Art. 41 OR. Letter-suffixed forms like '41a' supported."
    },
    "language": {
      "type": "string",
      "enum": [
        "de",
        "fr",
        "it"
      ],
      "default": "de",
      "description": "Botschaft language (defaults to German)."
    },
    "max_paragraphs": {
      "type": "integer",
      "default": 8,
      "description": "Maximum paragraphs per Botschaft (default 8, max 20)."
    }
  },
  "required": [
    "sr_number",
    "article"
  ]
}

search_botschaft

Use this tool to retrieve and quote the VERBATIM text of Federal Council Botschaften (legislative messages). Where get_article_purpose answers 'why does Art. X exist?', this tool answers 'show me every Botschaft passage about TOPIC X'. Useful when the caller doesn't know which SR/article to ask for — e.g. starting from a concept like 'Vaterschaftsurlaub' or 'Klimaschutz'. Returns ranked passages (FTS5 BM25) with bbl_citation, page, section path, and an article anchor where the parser could identify one. Quote verbatim; every snippet has a stable Fedlex ELI URI.

Parameters5

query	string	required	Search terms. FTS5 syntax supported — use quoted phrases for exact matches ('"Vaterschaftsurlaub"'), Boolean operators ('Klimaschutz AND Kanton'), and prefix queries ('Versicherungs*'). Stopwords are ignored.
language	string	optional	OPTIONAL — only set when the user explicitly limits the search to one language. Leave unset to search the corpus the caller has (currently de only). Setting this without the user asking will hide all non-matching Botschaft passages.
year_min	integer	optional	Earliest publication year of the source Botschaft (inclusive) — scope legislative history to an era.
year_max	integer	optional	Latest publication year of the source Botschaft (inclusive).
limit	integer	optional	Max passages to return (default 20, max 50).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search terms. FTS5 syntax supported — use quoted phrases for exact matches ('\"Vaterschaftsurlaub\"'), Boolean operators ('Klimaschutz AND Kanton'), and prefix queries ('Versicherungs*'). Stopwords are ignored."
    },
    "language": {
      "type": "string",
      "enum": [
        "de",
        "fr",
        "it"
      ],
      "description": "OPTIONAL — only set when the user explicitly limits the search to one language. Leave unset to search the corpus the caller has (currently de only). Setting this without the user asking will hide all non-matching Botschaft passages."
    },
    "year_min": {
      "type": "integer",
      "description": "Earliest publication year of the source Botschaft (inclusive) — scope legislative history to an era."
    },
    "year_max": {
      "type": "integer",
      "description": "Latest publication year of the source Botschaft (inclusive)."
    },
    "limit": {
      "type": "integer",
      "default": 20,
      "description": "Max passages to return (default 20, max 50)."
    }
  },
  "required": [
    "query"
  ]
}

get_article_history

Chronological story of a single statute article: current text + every linked Botschaft (enacted + amendments) + leading court interpretations + doctrinal commentary, all ordered by date. Combines statutes.db, materialien.db, reference_graph.db, and ok_commentaries.db into one timeline. USE THIS when the user asks 'how did Art. X evolve' or 'what's the full picture on Art. X' — a single call returns the legislative + judicial + doctrinal arc.

Parameters4

sr_number	string	required	SR number of the federal law, e.g. '220' for OR.
article	string	required	Article number, e.g. '41' for Art. 41 OR.
language	string	optional
leading_cases_limit	integer	optional	Max leading cases (default 5, max 15).

Raw schema

{
  "type": "object",
  "properties": {
    "sr_number": {
      "type": "string",
      "description": "SR number of the federal law, e.g. '220' for OR."
    },
    "article": {
      "type": "string",
      "description": "Article number, e.g. '41' for Art. 41 OR."
    },
    "language": {
      "type": "string",
      "enum": [
        "de",
        "fr",
        "it"
      ],
      "default": "de"
    },
    "leading_cases_limit": {
      "type": "integer",
      "default": 5,
      "description": "Max leading cases (default 5, max 15)."
    }
  },
  "required": [
    "sr_number",
    "article"
  ]
}

get_regeste

Get the official Regeste (head-note) of a Swiss court decision. The Regeste is the court's own formulation of the legal rule established — for BGEs especially, this is the canonical citation target. Often references specific Erwägungen via '(E. 5.2.1)' which can then be retrieved verbatim with get_erwaegung. USE THIS when the user asks 'what does this case stand for' or 'what is the rule from this decision'. Available for ~54% of federal decisions (100% of BGE).

Parameters1

decision_id

string

required

decision_id, BGE reference, or docket number.

Raw schema

{
  "type": "object",
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "decision_id, BGE reference, or docket number."
    }
  },
  "required": [
    "decision_id"
  ]
}

check_claim_support

Verify whether a Swiss court decision actually supports a legal claim. Uses an independent Sonnet judge to compare the claim against verbatim text from the decision (Erwägung if pinpoint given, else Regeste, else first portion of full text). Returns {supports: yes|partial|no|contradicts|unrelated, confidence, supporting_excerpt, qualifying_excerpt, reasoning}. CALL THIS for any claim where citing the wrong authority would mislead the user — especially when paraphrasing a decision or drawing a proposition from a complex Erwägung. If supports=no or contradicts, do NOT use the cited decision for that claim.

Parameters3

claim	string	required	The legal proposition you want to verify (e.g., 'A landlord is liable for fire-police violations under Art. 256 OR.').
decision_id	string	required	Decision you intend to cite as authority.
pinpoint	string	optional	Optional Erwägung number ('2.3'). If given, only that paragraph is judged; more precise verdict.

Raw schema

{
  "type": "object",
  "properties": {
    "claim": {
      "type": "string",
      "description": "The legal proposition you want to verify (e.g., 'A landlord is liable for fire-police violations under Art. 256 OR.')."
    },
    "decision_id": {
      "type": "string",
      "description": "Decision you intend to cite as authority."
    },
    "pinpoint": {
      "type": "string",
      "description": "Optional Erwägung number ('2.3'). If given, only that paragraph is judged; more precise verdict."
    }
  },
  "required": [
    "claim",
    "decision_id"
  ]
}

attest_response

MANDATORY FINAL-STEP AUDIT of your draft answer. Checks five hallucination classes: (1) every case citation (BGE/BGer/BVGer/BStGer/BPatGer/MKGE and FR/IT forms) exists in the corpus and any pinpoint (E. X.Y / consid. X.Y) resolves to a real Erwägung; (2) every 'Art. X LAW' statute reference resolves (known abbreviation, existing article); (3) every quoted passage of 30+ chars appears verbatim in a cited source; (4) decision dates adjacent to citations match the stored dates; (5) with audit_grounding=true, an independent LLM judge checks that each cited source actually supports the claim sentence preceding it (one call, ~3 s, regardless of citation count). Returns the draft annotated per citation plus a structured issues list. CALL THIS BEFORE emitting any answer containing a case citation, statute reference or direct quotation; set audit_grounding=true for answers with 2+ citations. If ok=false, fix each issue; if ok=true, send linked_text verbatim.

Parameters2

draft_text	string	required	Your draft response text.
audit_grounding	boolean	optional	When true, additionally runs the LLM-judge grounding rail: for each verified case citation in the draft, the preceding claim sentence is checked against the cited Erwägung / Regeste / text by an independent Sonnet judge. Catches the 'reasoning error' class (real citation, unsupported proposition). Adds ~3 s and one Sonnet call (~$0.005). Set to true for any answer with ≥2 citations or where a wrong proposition would mislead a Swiss lawyer.

Raw schema

{
  "type": "object",
  "properties": {
    "draft_text": {
      "type": "string",
      "description": "Your draft response text."
    },
    "audit_grounding": {
      "type": "boolean",
      "description": "When true, additionally runs the LLM-judge grounding rail: for each verified case citation in the draft, the preceding claim sentence is checked against the cited Erwägung / Regeste / text by an independent Sonnet judge. Catches the 'reasoning error' class (real citation, unsupported proposition). Adds ~3 s and one Sonnet call (~$0.005). Set to true for any answer with ≥2 citations or where a wrong proposition would mislead a Swiss lawyer."
    }
  },
  "required": [
    "draft_text"
  ]
}

cite

Get the canonical Swiss citation string for a decision reference. CALL THIS BEFORE writing any case citation in your response. Returns ready-to-embed citation_string (DE/FR/IT variants plus a canonical URL) and a verbatim rule_statement. If the reference doesn't exist, returns exists=false plus close_matches for typo-correction — DO NOT guess or construct citations yourself; if you get exists=false, either re-query with a close match or skip the citation entirely. Accepts any Swiss reference form: decision_id (bger_4A_747_2012), BGE reference (BGE 140 III 86), or docket number (4A_747/2012). Optional pinpoint ('2.3') generates the Erwägung-anchored citation and URL.

Parameters3

reference	string	required	Any form of Swiss case reference: decision_id, BGE ref, or docket number. E.g. 'BGE 140 III 86', '4A_747/2012', 'bger_4A_747_2012', 'MKGE 16 Nr. 1'.
pinpoint	string	optional	Optional Erwägung/consid. number ('2.3', '5.2.1'). Included in the citation and as a #e-2-3 URL anchor.
language	string	optional	Primary language for the citation_string field (all three variants always returned). Default: de.

Raw schema

{
  "type": "object",
  "properties": {
    "reference": {
      "type": "string",
      "description": "Any form of Swiss case reference: decision_id, BGE ref, or docket number. E.g. 'BGE 140 III 86', '4A_747/2012', 'bger_4A_747_2012', 'MKGE 16 Nr. 1'."
    },
    "pinpoint": {
      "type": "string",
      "description": "Optional Erwägung/consid. number ('2.3', '5.2.1'). Included in the citation and as a #e-2-3 URL anchor."
    },
    "language": {
      "type": "string",
      "enum": [
        "de",
        "fr",
        "it"
      ],
      "description": "Primary language for the citation_string field (all three variants always returned). Default: de."
    }
  },
  "required": [
    "reference"
  ]
}

get_doctrine

Get statute text + leading cases + doctrinal timeline + Federal Council Botschaft (legislative intent) + scholarly commentary for a Swiss law article or legal concept. ALWAYS USE THIS for questions about the purpose, intent, or ratio legis of a provision — it returns the Botschaft (Materialien) alongside the case law. Input: statute reference ('Art. 41 OR', 'Art. 8 BV') or legal concept. Returns: current statute text, top 5-8 BGEs ranked by citation authority with the rule each establishes, doctrine evolution timeline, Botschaft reference (legislative intent from the Federal Council's message), and scholarly commentary excerpt from OnlineKommentar.ch when available.

Parameters1

query

string

required

Statute article ('Art. 41 OR', 'Art. 8 BV') or legal concept ('Tierhalterhaftung', 'culpa in contrahendo'). German preferred.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Statute article ('Art. 41 OR', 'Art. 8 BV') or legal concept ('Tierhalterhaftung', 'culpa in contrahendo'). German preferred."
    }
  },
  "required": [
    "query"
  ]
}

generate_exam_question

Generate a Swiss law exam practice question (Fallbearbeitung) based on a real BGE. Returns a fact pattern (Sachverhalt) from a real court decision and a hidden analysis (applicable statutes, leading case, legal test, correct outcome). Workflow: present the fact_pattern and hint to the student, wait for their analysis, then reveal the analysis field and compare. The student can then call get_case_brief(source_decision_id) to study the full case. Pass exclude_ids from previous calls to avoid repeating the same case.

Parameters2

topic	string	required	Legal area, statute, or concept. Examples: 'Haftpflichtrecht', 'Art. 41 OR', 'Mietrecht', 'Strafrecht', 'Vertragsrecht'.
exclude_ids	array	optional	decision_ids already used in this session — avoids repetition.

Raw schema

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "description": "Legal area, statute, or concept. Examples: 'Haftpflichtrecht', 'Art. 41 OR', 'Mietrecht', 'Strafrecht', 'Vertragsrecht'."
    },
    "exclude_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "decision_ids already used in this session — avoids repetition."
    }
  },
  "required": [
    "topic"
  ]
}

get_law

AUTHORITATIVE LOOKUP for the current text of any Swiss law article — federal OR cantonal. Served from two local mirrors: • Federal (canton='CH', default): Fedlex mirror — core codes (OR, ZGB, StGB, StPO, ZPO, BV, SchKG, BGG/LTF, DBG, IPRG, AIG, BVG, KVG, AsylG, BGFA and dozens more), all three official languages (DE/FR/IT). • Cantonal: LexFind mirror — every cantonal statute and ordinance from all 26 cantons (ZH, BE, LU, UR, SZ, OW, NW, GL, ZG, FR, SO, BS, BL, SH, AR, AI, SG, GR, AG, TG, TI, VD, VS, NE, GE, JU), in each canton's publication language. Both jurisdictions return the same shape (title, articles with heading + text, article_count, canton, level). Use this BEFORE relying on training-data recall — Swiss statute text changes frequently and LLMs routinely hallucinate article content. Examples: get_law(abbreviation='BV', article='8'); get_law(sr_number='220', article='41'); get_law(canton='ZH', sr_number='554.5', article='1') for Art. 1 of the Zurich Hundegesetz.

Parameters7

sr_number	string	optional	Statute number. Federal: SR number ('210'=ZGB, '220'=OR, '101'=BV). Cantonal: the canton's systematic number — e.g. ZH 'LS' number '554.5' (Hundegesetz), '550.1' (Polizeigesetz). The `systematic_number` alias (as used by get_legislation) is also accepted.
systematic_number	string	optional	Alias for sr_number — the cantonal-friendly name (LS / systematic number), matching get_legislation. Either field works.
abbreviation	string	optional	Law abbreviation (federal only for now: 'BV', 'OR', 'ZGB', 'StGB', 'BGG', etc.). Cantonal laws rarely have canonical abbreviations — use sr_number or discover via search_laws first.
article	string	optional	Article number to retrieve (e.g., '8', '41a', '1bis'). For cantonal § laws (ZH, SH, AI, AR, BS, BL, AG), pass the § number without the § sign. If omitted, returns the full article list.
language	string	optional	Language for article text: de, fr, it. For cantonal laws, must match the canton's publication language (fr for FR/GE/JU/NE/VD, it for TI, de otherwise).
canton	string	optional	Two-letter canton code (ZH, BE, LU, …) or 'CH' for federal. Default 'CH' preserves backward compat.
as_of	string	optional	ISO date (e.g. '2020-01-01') to retrieve a HISTORICAL version of the law from Fedlex. Use this to see what a provision said before it was amended. XML versions available from ~2021; older versions may only have PDF. Federal laws only.

Raw schema

{
  "type": "object",
  "properties": {
    "sr_number": {
      "type": "string",
      "description": "Statute number. Federal: SR number ('210'=ZGB, '220'=OR, '101'=BV). Cantonal: the canton's systematic number — e.g. ZH 'LS' number '554.5' (Hundegesetz), '550.1' (Polizeigesetz). The `systematic_number` alias (as used by get_legislation) is also accepted."
    },
    "systematic_number": {
      "type": "string",
      "description": "Alias for sr_number — the cantonal-friendly name (LS / systematic number), matching get_legislation. Either field works."
    },
    "abbreviation": {
      "type": "string",
      "description": "Law abbreviation (federal only for now: 'BV', 'OR', 'ZGB', 'StGB', 'BGG', etc.). Cantonal laws rarely have canonical abbreviations — use sr_number or discover via search_laws first."
    },
    "article": {
      "type": "string",
      "description": "Article number to retrieve (e.g., '8', '41a', '1bis'). For cantonal § laws (ZH, SH, AI, AR, BS, BL, AG), pass the § number without the § sign. If omitted, returns the full article list."
    },
    "language": {
      "type": "string",
      "description": "Language for article text: de, fr, it. For cantonal laws, must match the canton's publication language (fr for FR/GE/JU/NE/VD, it for TI, de otherwise).",
      "enum": [
        "de",
        "fr",
        "it"
      ],
      "default": "de"
    },
    "canton": {
      "type": "string",
      "description": "Two-letter canton code (ZH, BE, LU, …) or 'CH' for federal. Default 'CH' preserves backward compat.",
      "default": "CH"
    },
    "as_of": {
      "type": "string",
      "description": "ISO date (e.g. '2020-01-01') to retrieve a HISTORICAL version of the law from Fedlex. Use this to see what a provision said before it was amended. XML versions available from ~2021; older versions may only have PDF. Federal laws only."
    }
  }
}

search_laws

Use this tool to find STATUTE ARTICLES by topic — full-text over every locally indexed article, federal (Fedlex mirror) AND cantonal (LexFind mirror, all 26 cantons), interleaved. Not for whole laws by name (search_legislation) or court decisions (search_decisions). BM25-ranked per corpus, merged by interleaving so each response surfaces both jurisdictions. Returns ranked snippets with article number, heading, law title, canton, and level ('federal' | 'cantonal'). Use this as the DEFAULT entry point when the user asks about any Swiss legal topic and you don't know which law or which jurisdiction applies. Filter with canton='ZH' (etc.) for cantonal-only, or jurisdiction='federal'/'cantonal' for explicit scoping. Examples: search_laws(query='Verjährung') — find statute-of-limitations provisions in federal + cantonal laws; search_laws(query='Hundehaltung', canton='ZH') — ZH dog-keeping rules; search_laws(query='Mietrecht', jurisdiction='federal') — federal-only tenancy law.

Parameters6

query	string	required	Search query. Explicit syntax is supported and operators must be UPPERCASE: 'Miete OR Pacht', 'Kündigung AND Frist' (AND with an absent term returns 0), '"exakte Wortfolge"' for phrases, 'Verfahr*' for prefixes. Lowercase or/and are treated as ordinary words.
sr_number	string	optional	Restrict search to a specific federal law by SR number. Implies jurisdiction='federal'.
canton	string	optional	Two-letter canton code (ZH, BE, …) to restrict to one canton's statute corpus. 'CH' → federal only. Omit to search every jurisdiction.
jurisdiction	string	optional	Explicit scope override: 'all' (default), 'federal', or 'cantonal'. Most callers should omit this and let sr_number/canton drive the scope.
language	string	optional	OPTIONAL filter. Restricts results to ONE language. Omit (recommended default) to search across all three official languages — most laws exist in DE/FR/IT and a filter silently hides valid hits in the others. Set ONLY when the user explicitly asks for one language.
limit	integer	optional	Maximum merged results (1-50).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query. Explicit syntax is supported and operators must be UPPERCASE: 'Miete OR Pacht', 'Kündigung AND Frist' (AND with an absent term returns 0), '\"exakte Wortfolge\"' for phrases, 'Verfahr*' for prefixes. Lowercase or/and are treated as ordinary words."
    },
    "sr_number": {
      "type": "string",
      "description": "Restrict search to a specific federal law by SR number. Implies jurisdiction='federal'."
    },
    "canton": {
      "type": "string",
      "description": "Two-letter canton code (ZH, BE, …) to restrict to one canton's statute corpus. 'CH' → federal only. Omit to search every jurisdiction."
    },
    "jurisdiction": {
      "type": "string",
      "description": "Explicit scope override: 'all' (default), 'federal', or 'cantonal'. Most callers should omit this and let sr_number/canton drive the scope.",
      "enum": [
        "all",
        "federal",
        "cantonal"
      ],
      "default": "all"
    },
    "language": {
      "type": "string",
      "description": "OPTIONAL filter. Restricts results to ONE language. Omit (recommended default) to search across all three official languages — most laws exist in DE/FR/IT and a filter silently hides valid hits in the others. Set ONLY when the user explicitly asks for one language.",
      "enum": [
        "de",
        "fr",
        "it"
      ]
    },
    "limit": {
      "type": "integer",
      "description": "Maximum merged results (1-50).",
      "default": 10
    }
  },
  "required": [
    "query"
  ]
}

get_commentary

Look up a scholarly legal commentary from OnlineKommentar.ch (CC-BY-4.0) for a Swiss federal law article. Without article: lists available commentaries for that law. With article: returns the full commentary text, authors, and citation. Covers 19 Swiss laws including BV, OR, ZGB, StGB, StPO, ZPO, DSG, SchKG, and more.

Parameters4

abbreviation	string	optional	Law abbreviation (e.g., 'OR', 'BV', 'ZGB', 'StGB'). Preferred over sr_number.
sr_number	string	optional	SR number of the law (e.g., '220' for OR). Use if abbreviation unknown.
article	string	optional	Article number (e.g., '41', '8'). Omit to list available articles.
language	string	optional	Preferred language (de, en, fr, it). Falls back to de if unavailable.

Raw schema

{
  "type": "object",
  "properties": {
    "abbreviation": {
      "type": "string",
      "description": "Law abbreviation (e.g., 'OR', 'BV', 'ZGB', 'StGB'). Preferred over sr_number."
    },
    "sr_number": {
      "type": "string",
      "description": "SR number of the law (e.g., '220' for OR). Use if abbreviation unknown."
    },
    "article": {
      "type": "string",
      "description": "Article number (e.g., '41', '8'). Omit to list available articles."
    },
    "language": {
      "type": "string",
      "description": "Preferred language (de, en, fr, it). Falls back to de if unavailable.",
      "default": "de"
    }
  }
}

search_commentaries

Use this tool ONLY for article-anchored commentary from OnlineKommentar.ch — doctrinal discussion tied to a specific statute article. For the full OA scholarship corpus (which includes OnlineKommentar) use search_scholarship. Searches commentary text, titles, and article numbers. Returns ranked results with snippets, authors, and links. Useful for finding doctrinal discussion of a legal concept across multiple laws.

Parameters4

query	string	required	Search query (supports FTS5 syntax: quotes for phrases, OR for alternatives).
abbreviation	string	optional	Filter by law abbreviation (e.g., 'OR', 'StGB').
language	string	optional	OPTIONAL filter (de/fr/it/en). Omit (recommended default) to search across all languages. Set ONLY when the user explicitly asks for one-language results; do NOT auto-apply based on conversation language.
limit	integer	optional	Maximum results (1-50, default 10).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query (supports FTS5 syntax: quotes for phrases, OR for alternatives)."
    },
    "abbreviation": {
      "type": "string",
      "description": "Filter by law abbreviation (e.g., 'OR', 'StGB')."
    },
    "language": {
      "type": "string",
      "description": "OPTIONAL filter (de/fr/it/en). Omit (recommended default) to search across all languages. Set ONLY when the user explicitly asks for one-language results; do NOT auto-apply based on conversation language."
    },
    "limit": {
      "type": "integer",
      "description": "Maximum results (1-50, default 10).",
      "default": 10
    }
  },
  "required": [
    "query"
  ]
}

search_scholarship

Use this tool for open-access SCHOLARSHIP (Lehre): OA journal articles (sui generis et al.), OA legal commentaries (OnlineKommentar, OpenLegalCommentary — this tool SUBSUMES search_commentaries), dissertations and theses from Swiss university repositories, and federal legal-policy reports. Returns ranked results with snippets, authors, DOI, and direct links. Filters by source, publication type, language, and year range. Sort by relevance or year; an author filter may be used on its own (no query) for a bibliographic browse, e.g. all works by a given author, newest first.

Parameters9

query	string	optional	Topic query (FTS5 syntax: quotes for phrases, OR for alternatives). Optional — may be omitted when an `author` (or other) filter is given, which returns a bibliographic browse instead of a topical search.
source	string	optional	Filter by source slug (e.g. 'sui_generis', 'onlinekommentar', 'openlegalcommentary', 'zora_law').
pub_type	string	optional	Filter by type: 'article', 'commentary', 'dissertation', 'book', 'chapter', 'master_thesis', 'working_paper', 'report'.
language	string	optional	OPTIONAL filter by language (de/fr/it/en). Omit to search across all languages (recommended — the corpus is trilingual).
year_min	integer	optional	Earliest publication year.
year_max	integer	optional	Latest publication year.
author	string	optional	Filter by author (substring match on the authors field). May be used WITHOUT a query for a pure bibliographic browse (all works by an author).
sort	string	optional	Order: 'relevance' (BM25, default for a topic query), 'year' (newest first), 'year_asc' (oldest first). With no query the default is newest-first.
limit	integer	optional	Maximum results (1-50, default 10).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Topic query (FTS5 syntax: quotes for phrases, OR for alternatives). Optional — may be omitted when an `author` (or other) filter is given, which returns a bibliographic browse instead of a topical search."
    },
    "source": {
      "type": "string",
      "description": "Filter by source slug (e.g. 'sui_generis', 'onlinekommentar', 'openlegalcommentary', 'zora_law')."
    },
    "pub_type": {
      "type": "string",
      "description": "Filter by type: 'article', 'commentary', 'dissertation', 'book', 'chapter', 'master_thesis', 'working_paper', 'report'."
    },
    "language": {
      "type": "string",
      "description": "OPTIONAL filter by language (de/fr/it/en). Omit to search across all languages (recommended — the corpus is trilingual)."
    },
    "year_min": {
      "type": "integer",
      "description": "Earliest publication year."
    },
    "year_max": {
      "type": "integer",
      "description": "Latest publication year."
    },
    "author": {
      "type": "string",
      "description": "Filter by author (substring match on the authors field). May be used WITHOUT a query for a pure bibliographic browse (all works by an author)."
    },
    "sort": {
      "type": "string",
      "enum": [
        "relevance",
        "year",
        "year_asc"
      ],
      "description": "Order: 'relevance' (BM25, default for a topic query), 'year' (newest first), 'year_asc' (oldest first). With no query the default is newest-first."
    },
    "limit": {
      "type": "integer",
      "description": "Maximum results (1-50, default 10).",
      "default": 10
    }
  },
  "required": []
}

get_scholarship

Fetch a single OA legal publication (article, dissertation, commentary, etc.) by its pub_id. Returns full metadata + abstract + full text if available + cross-citations to statutes and decisions.

Parameters1

pub_id

string

required

Canonical pub_id, e.g. 'sui_generis:article-1382' or 'onlinekommentar:<uuid>'.

Raw schema

{
  "type": "object",
  "properties": {
    "pub_id": {
      "type": "string",
      "description": "Canonical pub_id, e.g. 'sui_generis:article-1382' or 'onlinekommentar:<uuid>'."
    }
  },
  "required": [
    "pub_id"
  ]
}

find_scholarship_citing_statute

Find OA legal scholarship that cites a given Swiss statute article. Sourced from article-anchored commentaries (OnlineKommentar / OpenLegalCommentary) PLUS full-text citation extraction across the open-access journal corpus (~90k statute references resolved from 9k full-text records).

Parameters3

sr_number	string	required	Swiss SR number (e.g. '220' for OR, '210' for ZGB).
article	string	optional	Article number (e.g. '41'). Omit for all articles of the law.
limit	integer	optional	Maximum results (1-100, default 20).

Raw schema

{
  "type": "object",
  "properties": {
    "sr_number": {
      "type": "string",
      "description": "Swiss SR number (e.g. '220' for OR, '210' for ZGB)."
    },
    "article": {
      "type": "string",
      "description": "Article number (e.g. '41'). Omit for all articles of the law."
    },
    "limit": {
      "type": "integer",
      "description": "Maximum results (1-100, default 20).",
      "default": 20
    }
  },
  "required": [
    "sr_number"
  ]
}

find_scholarship_citing_decision

Find OA legal scholarship that cites a specific Swiss court decision. Reverse direction of the scholarship↔caselaw bridge: given a decision_id (e.g. 'bge_BGE_140_III_86' or 'bger_4A_571_2008'), return open-access publications that cite it in their full text. Citations are extracted deterministically by regex + lookup against the canonical decision corpus, so resolved citations are always to decisions we hold.

Parameters2

decision_id	string	required	Canonical decision_id (e.g. 'bge_BGE_140_III_86', 'bger_4A_571_2008').
limit	integer	optional	Maximum results (1-100, default 20).

Raw schema

{
  "type": "object",
  "properties": {
    "decision_id": {
      "type": "string",
      "description": "Canonical decision_id (e.g. 'bge_BGE_140_III_86', 'bger_4A_571_2008')."
    },
    "limit": {
      "type": "integer",
      "description": "Maximum results (1-100, default 20).",
      "default": 20
    }
  },
  "required": [
    "decision_id"
  ]
}

list_scholarship_sources

List the open-access legal scholarship sources currently indexed, with publication counts by source, type, and language. Use this to discover what corpora are available before searching.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_scholarship_full_text

Fetch the full text of an OA legal publication by pub_id, on demand. Cached after first fetch so subsequent calls are instant. License-gated: only records under CC-BY-* (except CC-BY-ND), OA-Swiss-federal, or OA-author-permitted-reuse are extracted. ND/all-rights-reserved records return the upstream URL only. Use this when search_scholarship or get_scholarship returns only abstract/title and you need the article body to verify a claim or quote a passage.

Parameters1

pub_id

string

required

Canonical pub_id (from search_scholarship results).

Raw schema

{
  "type": "object",
  "properties": {
    "pub_id": {
      "type": "string",
      "description": "Canonical pub_id (from search_scholarship results)."
    }
  },
  "required": [
    "pub_id"
  ]
}

get_materialien

Look up Materialien for a Swiss federal law article. Returns up to three things: `sources` = per-article digests of legislative intent (BV and BGFA only — 167 articles); `botschaft_documents` = the Federal Council messages that concern this article, with BBl citation, title and Fedlex link (620 SR numbers, 19,809 article links); `amendment_refs` = the AS/BBl publication locators from the statute's own footnotes. Empty `sources` means no digest exists for that law, NOT that the law has no legislative history — read `botschaft_documents` and cite the BBl reference. For full text of a message use search_botschaft.

Parameters2

law_code	string	required	Law abbreviation (e.g., 'BV', 'BGFA', 'OR', 'StGB').
article	string	optional	Article number (e.g., '1', '8', '10a'). Omit to get all articles.

Raw schema

{
  "type": "object",
  "properties": {
    "law_code": {
      "type": "string",
      "description": "Law abbreviation (e.g., 'BV', 'BGFA', 'OR', 'StGB')."
    },
    "article": {
      "type": "string",
      "description": "Article number (e.g., '1', '8', '10a'). Omit to get all articles."
    }
  },
  "required": [
    "law_code"
  ]
}

search_materialien

Use this tool for DIGESTED legislative history — per-article intent summaries and key arguments, not verbatim text. COVERAGE IS NARROW: BV and BGFA digests (167 articles) plus BV debate transcripts, and nothing else. For any other law this returns 0 hits, which means 'outside this index', not 'no materials exist'. Prefer search_botschaft, which covers all 6,154 Federal Council messages verbatim, or get_materialien(law_code) for the messages linked to one statute.

Parameters3

query	string	required	Search query (natural language or FTS5 syntax).
law_code	string	optional	Filter by law abbreviation (e.g., 'BGFA').
limit	integer	optional	Maximum results (1-50, default 10).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query (natural language or FTS5 syntax)."
    },
    "law_code": {
      "type": "string",
      "description": "Filter by law abbreviation (e.g., 'BGFA')."
    },
    "limit": {
      "type": "integer",
      "description": "Maximum results (1-50, default 10).",
      "default": 10
    }
  },
  "required": [
    "query"
  ]
}

search_legislation

Use this tool to find WHOLE LAWS by name or subject — 33,000+ federal and cantonal enactments from LexFind.ch; the entry point for cantonal questions ('Hundegesetz Bern', 'loi sur l'énergie Vaud'). Not for article-level topic search (search_laws) or the core federal codes (get_law is instant there). All 26 cantons + federal, DE/FR/IT. Also the entry point for municipal regulations and federal ordinances outside the core Fedlex mirror. SINGLE-CALL MODE: set fetch_top_n_texts=1..3 and the top results are returned with the parsed full text + article list of the law itself — no follow-up get_legislation call needed. Ideal for 'what does cantonal law X say about Y' questions. For core federal codes (OR, ZGB, StGB, BV, StPO, ZPO, SchKG, BGG, DBG, IPRG, AIG, BVG, KVG etc.), prefer get_law / search_laws — they are instant and cover all three languages.

Parameters7

query	string	required	Search query in natural language or keywords. Examples: 'Hundegesetz', 'loi sur l'énergie', 'Mietrecht Kanton Zürich', 'Baugesetz'.
canton	string	optional	Two-letter canton code (ZH, BE, LU, UR, SZ, OW, NW, GL, ZG, FR, SO, BS, BL, SH, AR, AI, SG, GR, AG, TG, TI, VD, VS, NE, GE, JU) or 'CH' for federal. Omit to search all 26 cantons + federal at once.
active_only	boolean	optional	Only show laws currently in force (default true).
search_in_content	boolean	optional	Also search inside the law text, not just titles and keywords (slower).
language	string	optional	OPTIONAL filter. Restricts results to ONE language version. Omit (recommended default) to fan out across DE/FR/IT and merge results — LexFind's API is single-language per request, so omission triggers a 3-way parallel call with deduplication. Set ONLY when the user explicitly asks for one language. Hint when set: fr for FR/GE/JU/NE/VD, it for TI, de for the rest.
limit	integer	optional	Max results (1-60, default 20).
fetch_top_n_texts	integer	optional	If > 0, download + parse the full text of the top N results (max 10) and return each with full_text_preview, article_count, and sample_articles. Use 1-3 for natural-language questions so you can answer in a single tool call.

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query in natural language or keywords. Examples: 'Hundegesetz', 'loi sur l'énergie', 'Mietrecht Kanton Zürich', 'Baugesetz'."
    },
    "canton": {
      "type": "string",
      "description": "Two-letter canton code (ZH, BE, LU, UR, SZ, OW, NW, GL, ZG, FR, SO, BS, BL, SH, AR, AI, SG, GR, AG, TG, TI, VD, VS, NE, GE, JU) or 'CH' for federal. Omit to search all 26 cantons + federal at once."
    },
    "active_only": {
      "type": "boolean",
      "description": "Only show laws currently in force (default true).",
      "default": true
    },
    "search_in_content": {
      "type": "boolean",
      "description": "Also search inside the law text, not just titles and keywords (slower).",
      "default": false
    },
    "language": {
      "type": "string",
      "description": "OPTIONAL filter. Restricts results to ONE language version. Omit (recommended default) to fan out across DE/FR/IT and merge results — LexFind's API is single-language per request, so omission triggers a 3-way parallel call with deduplication. Set ONLY when the user explicitly asks for one language. Hint when set: fr for FR/GE/JU/NE/VD, it for TI, de for the rest.",
      "enum": [
        "de",
        "fr",
        "it"
      ]
    },
    "limit": {
      "type": "integer",
      "description": "Max results (1-60, default 20).",
      "default": 20
    },
    "fetch_top_n_texts": {
      "type": "integer",
      "description": "If > 0, download + parse the full text of the top N results (max 10) and return each with full_text_preview, article_count, and sample_articles. Use 1-3 for natural-language questions so you can answer in a single tool call.",
      "default": 0
    }
  },
  "required": [
    "query"
  ]
}

get_legislation

Retrieve the FULL TEXT and article list of a specific Swiss law, federal or cantonal, by LexFind ID or SR/systematic number. For federal laws in the Fedlex mirror this is instant (local SQLite). For cantonal laws, the law is downloaded from LexFind as PDF, parsed with PyMuPDF, and segmented into articles (cached 30 days). Returns: title, entity, articles (article_num, heading, text), full_text, article_count. Use search_legislation first to find the right lexfind_id or systematic_number; then pass it here. For the core federal codes, get_law is still the fastest path.

Parameters5

lexfind_id	integer	optional	LexFind ID of the law (from search_legislation results).
systematic_number	string	optional	SR/systematic number (e.g., '220' for OR, '210' for ZGB). Used when lexfind_id not available.
canton	string	optional	Canton for systematic number lookup (default CH). Required for cantonal laws.
include_versions	boolean	optional	Include full version history (default false).
language	string	optional	Result language: de, fr, it.

Raw schema

{
  "type": "object",
  "properties": {
    "lexfind_id": {
      "type": "integer",
      "description": "LexFind ID of the law (from search_legislation results)."
    },
    "systematic_number": {
      "type": "string",
      "description": "SR/systematic number (e.g., '220' for OR, '210' for ZGB). Used when lexfind_id not available."
    },
    "canton": {
      "type": "string",
      "description": "Canton for systematic number lookup (default CH). Required for cantonal laws.",
      "default": "CH"
    },
    "include_versions": {
      "type": "boolean",
      "description": "Include full version history (default false).",
      "default": false
    },
    "language": {
      "type": "string",
      "description": "Result language: de, fr, it.",
      "enum": [
        "de",
        "fr",
        "it"
      ],
      "default": "de"
    }
  }
}

browse_legislation_changes

Browse recent legislation changes for a canton or federal level. Shows new laws, amendments, and abrogations with dates.

Parameters2

canton	string	optional	Canton code (CH for federal, ZH, BE, etc.). Default: CH.
language	string	optional	OPTIONAL filter. Restricts results to ONE language version. Omit (recommended default) to fan out across DE/FR/IT and merge results — LexFind's API is single-language per request, so omission triggers a 3-way parallel call with deduplication. Set ONLY when the user explicitly asks for one language.

Raw schema

{
  "type": "object",
  "properties": {
    "canton": {
      "type": "string",
      "description": "Canton code (CH for federal, ZH, BE, etc.). Default: CH.",
      "default": "CH"
    },
    "language": {
      "type": "string",
      "description": "OPTIONAL filter. Restricts results to ONE language version. Omit (recommended default) to fan out across DE/FR/IT and merge results — LexFind's API is single-language per request, so omission triggers a 3-way parallel call with deduplication. Set ONLY when the user explicitly asks for one language.",
      "enum": [
        "de",
        "fr",
        "it"
      ]
    }
  }
}

search_practice

Use this tool when the question involves federal ADMINISTRATIVE PRACTICE (Verwaltungspraxis): Wegleitungen, Kreisschreiben, MWST-Infos, Weisungen, Rundschreiben, Vollzugshilfen — interpretive agency guidance, not court decisions. 1,892 documents: SECO commentary on the Arbeitsgesetz and ArGV 1-5, article by article (1,102, DE/FR/IT — the reference for employment-law questions); ESTV tax and VAT (438, DE/FR/IT); BAFU environment (297, DE); SEM migration/asylum/citizenship (55, DE). Returns ranked excerpts with authority, document number, date and a PDF link. NOT covered: BSV/AHV-IV, FINMA, BAG and all cantonal administrations — say so rather than implying a gap is an absence of guidance. For federal administrative decisions before 2017 use search_decisions(court='ch_vb') (VPB/JAAC).

Parameters6

query	string	required	Search query (FTS5 syntax: quotes for phrases, OR for alternatives, NEAR/N for proximity).
source	string	optional	Filter by source key. seco_arg (1,102), bafu_vollzug (297), estv_ks (285), estv_mwst (153), sem_weisungen (55).
issuing_authority	string	optional	Filter by authority. SECO (1,102), ESTV (438), BAFU (297), SEM (55).
doc_type	string	optional	Filter by document type. wegleitung (1,102), vollzugshilfe (297), kreisschreiben (285), mwst_branchen_info (84), mwst_info (69), weisung (39), rundschreiben (16).
language	string	optional	OPTIONAL filter (de/fr/it). Omit (recommended default) to search across all languages. Set ONLY when the user explicitly asks for one-language results.
limit	integer	optional	Maximum results (1-50, default 10).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search query (FTS5 syntax: quotes for phrases, OR for alternatives, NEAR/N for proximity)."
    },
    "source": {
      "type": "string",
      "enum": [
        "seco_arg",
        "bafu_vollzug",
        "estv_ks",
        "estv_mwst",
        "sem_weisungen"
      ],
      "description": "Filter by source key. seco_arg (1,102), bafu_vollzug (297), estv_ks (285), estv_mwst (153), sem_weisungen (55)."
    },
    "issuing_authority": {
      "type": "string",
      "enum": [
        "SECO",
        "ESTV",
        "BAFU",
        "SEM"
      ],
      "description": "Filter by authority. SECO (1,102), ESTV (438), BAFU (297), SEM (55)."
    },
    "doc_type": {
      "type": "string",
      "enum": [
        "wegleitung",
        "vollzugshilfe",
        "kreisschreiben",
        "mwst_branchen_info",
        "mwst_info",
        "weisung",
        "rundschreiben"
      ],
      "description": "Filter by document type. wegleitung (1,102), vollzugshilfe (297), kreisschreiben (285), mwst_branchen_info (84), mwst_info (69), weisung (39), rundschreiben (16)."
    },
    "language": {
      "type": "string",
      "description": "OPTIONAL filter (de/fr/it). Omit (recommended default) to search across all languages. Set ONLY when the user explicitly asks for one-language results."
    },
    "limit": {
      "type": "integer",
      "description": "Maximum results (1-50, default 10).",
      "default": 10
    }
  },
  "required": [
    "query"
  ]
}

get_practice

Retrieve a single federal administrative-practice document by its doc_id (e.g. 'estv_ks_ks_nr_28', 'sem_weisungen_weisungen-aug-d'). Returns full body text, title, date, issuing authority, and PDF URL. Use search_practice first to discover the doc_id.

Parameters1

doc_id

string

required

Document identifier returned by search_practice.

Raw schema

{
  "type": "object",
  "properties": {
    "doc_id": {
      "type": "string",
      "description": "Document identifier returned by search_practice."
    }
  },
  "required": [
    "doc_id"
  ]
}

README.md69 KBView on GitHub

OpenCaseLaw

Open Swiss case law and legislation for legal research and AI.

1M+ decisions · all 26 cantons · 1875–today · citation graph · MCP + REST + CLI + Parquet · CC0 data · MIT code

Try the search · Chat with your AI · Automate research · Download the dataset · API documentation

What you can do

Find Swiss decisions across federal and cantonal courts, in German, French and Italian.
Trace citations between cases and identify the leading decisions on a question.
Query case law and legislation from Claude, ChatGPT-compatible clients, or any MCP client.
Save repeatable research scripts, inspect citation resolution, and preserve selected evidence with the research CLI.
Download the corpus for legal NLP, retrieval and graph research.

Connect in 30 seconds

json

{
  "mcpServers": {
    "opencaselaw": {
      "url": "https://mcp.opencaselaw.ch/mcp"
    }
  }
}

No sign-up, no API key, read-only. 42 tools; setup guides for individual clients are at opencaselaw.ch/mcp.

Using Anthropic's Claude for Legal plugin? A Swiss playbook that makes its contract-review and NDA-triage skills work under Swiss law, every article verified against the statute mirror, is at opencaselaw.ch/claude/legal.local.md; see the setup guide.

Automate research

ocl is a small command-line client over the public research API, made for two jobs a chat window does badly: checking the citations in a draft, and keeping the evidence behind a memo in a folder you can share. It is on PyPI as opencaselaw-cli:

bash

pipx install opencaselaw-cli        # or: uv tool install opencaselaw-cli
ocl citations resolve 'BGE 136 III 513' '4A_747/2012' 'BGE 999 III 1'
ocl bundle create 'Rachekündigung Art. 336 OR' --max-results 10 --passage 2 --law OR:336 --out evidence

The first prints, per reference, whether the decision exists, which one it is, and whether a requested Erwägung exists. The second saves the selected decisions, passages and statute articles into a folder with a plain-language INDEX.md and a hashed manifest.json. Everything comes back from the service unchanged: citation strings, passage text, source links. Search is bounded, and a citation check establishes existence, not that an authority supports a proposition. See the CLI guide.

Use MCP for conversations, the CLI or REST API for automation, and Parquet for corpus-scale analysis.

A real result

Question. When is a dismissal in retaliation for an employee asserting a claim abusive under Swiss law?

One call — search_decisions("missbräuchliche Kündigung Rachekündigung") returns 129 decisions, the leading one first:

BGE 136 III 513 (7 October 2010)

Art. 336 OR; missbräuchliche Kündigung. Der Arbeitnehmer ist vor einer Rachekündigung nur geschützt (Art. 336 Abs. 1 lit. d OR), sofern er nach Treu und Glauben annehmen kann, dass die von ihm geltend gemachten Ansprüche berechtigt sind. Es ist nicht erforderlich, dass sie tatsächlich begründet sind.

The Regeste is returned verbatim from the stored official head-note, and the citation string comes from a stored field — tools never construct citations. That contract is what makes the answer checkable rather than plausible.

Reproduce it:

bash

curl -sG https://mcp.opencaselaw.ch/api/decisions \
  --data-urlencode "q=missbräuchliche Kündigung Rachekündigung" \
  --data-urlencode "limit=3"

Coverage

Resource	Coverage
Court decisions	1,050,000+ records, 118 court and source collections, 1875–today
Languages	German, French, Italian (plus English, for the ECtHR judgments whose only authoritative text is English)
Legislation	5,525 federal laws, 15,600 cantonal laws (all 26 cantons)
Citation graph	~10M resolved decision-to-decision edges, 12.4M statute references
Interpretive layers	Federal Council dispatches, commentaries, open-access scholarship, federal administrative practice
Access	Web, MCP, REST, research CLI, daily CC0 Parquet
Licensing	CC0 data, MIT code (ECtHR texts © ECHR-CEDH, see the data card)

Counts are generated from one source of truth, docs/canonical_numbers.md, with the verification method recorded alongside each figure.

Limitations, stated plainly. Coverage is not complete where portals restrict access; those sources are documented rather than glossed. The citation graph reports resolution coverage (93.8 %), which is not a precision estimate — a human semantic audit is in preparation. Some cantonal decisions may be published unredacted by the court; we inherit upstream pseudonymisation and do not re-pseudonymise. See governance and removal policy.

Contributing

Data-quality reports are the most valuable contribution — every one so far has been reproduced, fixed and pinned with a regression test. See CONTRIBUTING.md.

The remainder of this page is reference detail.

Why this exists

Swiss legal research today is fragmented across paywalls, inaccessible to language models, and prohibitively expensive for the people who need it most — law students, independent researchers, and anyone outside the major firms. Commercial databases (Weblaw, Swisslex, Legalis) charge hundreds of francs per month and still don't expose a clean API. LLMs hallucinate statute text because they have no authoritative source. Small cantons publish decisions in PDF archives nobody indexes.

OpenCaseLaw fixes this. Every published Swiss court decision, every federal and cantonal law, the resolved citation graph between them, and 44 MCP tools (42 remote in public mode + 2 local-only) that let any modern LLM act as a Swiss legal research assistant — all free, all open, all refreshed automatically.

What you get

Case law — 1,050,000+ decision records (~909,000 unique decisions; cross-identifier duplicates retained and linked, never deleted) from 1875 to today across 118 courts, full text + structured metadata, covering:

All 7 federal courts (BGer, BVGer, BStGer, BPatGer, BGE, BGE historical, BGE-EGMR)
Federal military court (Militärkassationsgericht / MKG, 1,244 decisions 1915–2025)
All 26 cantonal court systems (first, second, and third instance)
Regulatory decisions (FINMA, ComCo, FDPIC, IndepBC, ElCom, PostCom, ComCom)
ECHR/EGMR: the Swiss-respondent material (487 BGE-published EGMR translations, 847 HUDOC Switzerland-tagged) plus every ECtHR Chamber and Grand Chamber judgment of importance 1–3 against any of the 46 respondent states — 8,275 judgments, in French where the Court published a French text and English otherwise. Importance 4 (low-importance and repetitive, which is the entire Committee docket) and admissibility decisions are out of scope.
Three official languages: German 463,012 (46.7%), French 446,869 (45.1%), Italian 81,796 (8.2%); schema reserves rm for Romansh
Deduplicated via docket normalisation + content-length-aware merge
Updated daily; BGer decisions available within ~15 minutes of court publication

Legislation — every Swiss law, federal and cantonal, locally mirrored with article-level indexing:

5,525 federal laws / ~133,359 articles in each of DE/FR/IT from the Fedlex SPARQL endpoint
15,600 cantonal laws / 361,430 articles, direct-scraped from all 26 cantons (LexWork covers 18, SIL covers 2, ZH OpenData covers ZH, TI~RL covers TI); LexFind PDF fallback supplements 4 cantons for laws missing from their primary portals
Unified SQLite FTS5 search federates both corpora; sub-millisecond article lookup
Monthly refresh on the 2nd of each month (the day after laws enter into force)
12.4 M resolved links from decisions to individual statute articles

Citation graph — the only public large-scale citation graph of the Swiss legal system:

9.65 M resolved decision-to-decision citation edges (10 M extracted) with confidence scores
12.4 M decision-to-statute links resolved against the current consolidated text
Bidirectional lookup, appeal-chain resolution (Instanzenzug), leading-case ranking by citation authority
Powers find_leading_cases, find_citations, find_appeal_chain, analyze_legal_trend (top: BGE 125 V 351 with 85,108 incoming citations)

44 MCP tools (42 remote in public mode + 2 local-only) — specialised research tools that run in your LLM of choice:

Natural-language decision search (BM25 + synonym expansion + Haiku reranking, MRR@10 = 0.647 on a 100-query golden set)
Leading-case discovery, citation networks, appeal chains, jurisprudence evolution
Federal + cantonal law article lookup, full-text search across both — with colloquial→legal vocabulary expansion (searching "Vaterschaftsurlaub" finds the statute even though it says "Urlaub des andern Elternteils") and cross-language cantonal search (German query finds French/Italian cantonal laws)
Doctrine overviews (statute + authority-ranked BGEs + timeline + Botschaft reference)
Legislative history (Materialien) — 83,958 Botschaft amendment references across 9,139 BBl publications and 33,465 distinct (statute, article) pairs; Phase 2 verbatim Botschaft corpus (5,900+ documents, ~410K FTS5-indexed paragraphs) accessible via search_botschaft (topical FTS5 across the verbatim corpus), get_article_purpose (verbatim Botschaft text for a specific article), and get_article_history (chronological timeline composing statute + Botschaft + leading cases + commentary); per-article digests (legislative intent, key arguments, design choices, rejected alternatives) for BV and BGFA; parliamentary debate transcripts for the BV. Full verbatim ingest to ~25K Botschaften via Fedlex SPARQL discovery is scaling.
Decision-structure access — get_decision_structure (Sachverhalt + Erwägungen + Dispositiv + Regeste split), get_erwaegung (verbatim Schweizer-citation Einheit, e.g. get_erwaegung("BGE 136 III 513", "2.3")), get_regeste (official BGer/BVGer/BStGer head-note)
Scholarly commentary lookup from OnlineKommentar.ch + OpenLegalCommentary.ch (1,131 commentaries)
Fallbearbeitung exam questions generated from real BGE fact patterns, with hidden analysis for practice
Draft mock decisions from fact patterns (research-only tool for grounding LLM outputs)
Structured case briefs (regeste, Sachverhalt, Erwägungen, Dispositiv, cited statutes, authority)

Multiple access paths — chat with your AI, automate research, or download the corpus:

For LLM users, researchers and developers:

Remote MCP server at mcp.opencaselaw.ch (SSE + Streamable HTTP) — 30-second setup in any MCP client (Claude, ChatGPT, Cursor, Gemini, Windsurf)
OpenAI-compatible tool definitions for Grok/xAI and any function-calling LLM API
Local MCP server — full offline capability, all 44 tools (the 2 local-only update tools are available offline), ~65 GB disk
Lightweight research CLI — JSON/JSONL, batch input, saved evidence bundles and citation resolution; pipx install opencaselaw-cli; source in clients/python/
REST API with interactive documentation (Swagger UI + OpenAPI spec)
Bulk Parquet download via the HuggingFace dataset (~7 GB)
Live dashboard + browsing UI at opencaselaw.ch

For legal practitioners drafting documents — curated practitioner surface:

Word add-in — Search decisions and insert correctly-formatted Swiss legal citations directly in Word (no copy-paste). Click an Erwägung to insert it with the correct sub-citation; click a law § to insert that alinea. Free Audit scans the whole document for fabricated citations and bad pinpoints (deterministic, no LLM). Pro tier (Stripe-billed, CHF 5/month, 25 AI calls/day shared, always-on client-side PII redaction — pattern-based, scope and limits at word.opencaselaw.ch/privacy.html) adds four AI tools: Verify (single citation vs. full-text decision), Strengthen (paragraph x-ray with leading-case suggestions ranked by citation-graph centrality + commentary excerpts), Find Support (locate decisions that back an unsupported statement, scored 0–100), and Reflect (literary mirror on the whole document — one canonical work that frames the same human dilemma + one reflective question). Exposes ~8 of the 44 MCP tools (42 remote in public mode + 2 local-only) through the REST API, tuned for the write-your-brief workflow.

Performance you can defend in a paper:

Metric	Value
Decision search quality	MRR@10 = 0.647 (online) / 0.470 (offline reproducible) · +102 % over baseline
Article lookup latency	< 1 ms (local FTS5)
BGer publication → searchable	~15 min (was 24 h pre-poller)
Daily full-text rebuild	~5 h, zero downtime (atomic swap)
Citation-to-decision resolution	9.65 M edges resolved (10 M extracted)

What this is

A structured, searchable archive of Swiss court decisions — from the Federal Supreme Court (BGer) down to cantonal courts in all 26 cantons. Every decision includes the full decision text, docket number, date, language, legal area, judges, cited decisions, and 20+ additional metadata fields.

The dataset is built by direct scraping of official court websites and cantonal court portals. New decisions are scraped, deduplicated, and published every night.

There are eight ways to use it, depending on what you need:

Method	For whom	What you get
Search with AI	Everyone	Natural-language search in Claude, ChatGPT, Cursor, or Gemini — instant access, no download, full 24-tool surface
Citation Analysis	Legal scholars, researchers	Leading cases, citation networks, appeal chains, jurisprudence trends over time
Statute Lookup	Legal professionals	Full article text from 5,525 federal laws and 15,600 cantonal laws, federated FTS5, sub-millisecond lookup
Legislation Search	Legal professionals	LexFind-backed discovery search with `fetch_top_n_texts` for single-call natural-language workflows
Education tools	Law students, instructors	Structured case briefs, doctrine timelines, real-BGE exam questions with hidden analysis
Word Add-in	Legal practitioners writing briefs	Insert formatted Swiss citations into Word · click Erwägung / § to insert with correct sub-reference · free Audit (5-rail citation check) · Pro (CHF 5/mo, 25 AI calls/day): Verify (citation vs. full text) · Strengthen (paragraph x-ray + leading-case suggestions) · Find Support (decisions backing a statement) · Reflect (literary mirror) — curated ~8-tool subset
REST API / Download	Developers, data scientists, NLP researchers	Research REST API, bulk Parquet download via HuggingFace (~7 GB)
Web UI	Everyone	Live dashboard with corpus stats, daily delta, top movers, multilingual browsing

Not sure where to start? Connect to the remote MCP server — works with Claude, ChatGPT, and Gemini CLI. Instant access to all 1,050,000+ decisions, citation analysis, statute lookup, legislation search, and education tools, no download needed.

1. Search with AI

The dataset comes with an MCP server whose exact tool surface is deployment-dependent. Local deployments expose all 44 tools; remote mode omits the 2 local-only update tools (update_database, check_update_status) for 42 remote tools. You ask a question in natural language; the tool runs a full-text search and returns matching decisions with snippets.

Remote vs. local

	Remote	Local
Setup	30 seconds	30–60 minutes
Disk	None	~65 GB
Tools	38 (no local update tools)	40, including `update_database` and `check_update_status`
Freshness	Nightly (automatic)	Manual
Offline	No	Yes
Requires	Claude, ChatGPT, or Gemini CLI (see plans below)	Any MCP client

Start with the remote server. Switch to local only if you need offline access.

Option A: Remote server (recommended)

Connect directly to the hosted MCP server — no data download, no local database, instant access to 1,050,000+ decisions.

What the hosted server records. Your queries are logged: tool, parameters including the query text, timestamp, client class and a rotating session identifier, and query text is kept indefinitely in an access-restricted private research archive used to improve search and train our own models. No IP address is stored with a query, there is no account or login, and the session identifier changes with every connection. Full details, in five languages: Privacy notice. If your queries are confidential — or you are sending them on behalf of clients — use Option B below and run the corpus locally, where nothing leaves your machine.

Claude.ai / Claude Desktop (easiest):

Open Settings → Connectors
Click "Add custom connector"
Paste https://mcp.opencaselaw.ch
Click Add

Same steps in the browser (claude.ai) and the desktop app. No Node.js, no config files, no downloads.

Available on Pro, Max, Team, and Enterprise plans. For the free plan, use Claude Code or the manual JSON config.

Claude Code:

bash

claude mcp add swiss-caselaw --transport sse https://mcp.opencaselaw.ch

Alternative: manual JSON config (if custom connectors aren't available)

Add to claude_desktop_config.json (Node.js required):

json

{
  "mcpServers": {
    "swiss-caselaw": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.opencaselaw.ch"]
    }
  }
}

Restart Claude Desktop after saving.

ChatGPT:

Open Settings → Apps → Advanced settings → enable Developer mode
Click Create app → name it Swiss Caselaw, paste https://mcp.opencaselaw.ch/sse, auth: None
In any chat: click + → Developer mode → select Swiss Caselaw

Available on Plus, Pro, Team, Enterprise, and Edu plans. Recommended with GPT-5.3 (GPT-5.4 does not currently support MCP tool invocation).

Gemini CLI:

Add to ~/.gemini/settings.json:

json

{
  "mcpServers": {
    "swiss-caselaw": {
      "url": "https://mcp.opencaselaw.ch"
    }
  }
}

Restart Gemini CLI after saving. No account plan required — Gemini CLI is free.

Google ADK (Agent Development Kit):

Build a Gemini-powered agent with access to all tools:

python

from google.adk.agents import LlmAgent
from google.adk.tools import MCPToolset
from mcp.client.sse import SseConnectionParams

agent = LlmAgent(
    model="gemini-3.1-pro",
    name="swiss_law_agent",
    instruction="You are a Swiss legal research assistant.",
    tools=[
        MCPToolset(
            connection_params=SseConnectionParams(
                url="https://mcp.opencaselaw.ch/sse",
            ),
        ),
    ],
)

See the full MCP setup guide for Google Gen AI SDK examples and all other platforms.

See the full MCP setup guide for detailed instructions for all platforms.

The update_database and check_update_status tools are only available on the local server — the remote dataset is updated automatically every night.

Option B: Local server (offline access)

Run the MCP server locally with your own copy of the database (~65 GB disk). This gives you offline access and full control over the data.

Setup with Claude Code

Claude Code is Anthropic's CLI for working with Claude in the terminal.

Step 1. Clone this repository:

bash

git clone https://github.com/jonashertner/opencaselaw.git
cd caselaw-repo-1

Step 2. Create a virtual environment and install the MCP server dependencies:

bash

python3 -m venv .venv

# macOS / Linux
source .venv/bin/activate
pip install mcp pydantic huggingface-hub pyarrow fastapi

# Windows (PowerShell)
.venv\Scripts\Activate.ps1
pip install mcp pydantic huggingface-hub pyarrow

Step 3. Register the MCP server with Claude Code:

bash

# macOS / Linux
claude mcp add swiss-caselaw -- /path/to/caselaw-repo-1/.venv/bin/python3 /path/to/caselaw-repo-1/mcp_server.py

# Windows
claude mcp add swiss-caselaw -- C:\path\to\caselaw-repo-1\.venv\Scripts\python.exe C:\path\to\caselaw-repo-1\mcp_server.py

Use the full absolute path to the Python binary inside .venv so that the server always finds its dependencies, regardless of which directory you run Claude Code from.

Step 4. Restart Claude Code and run your first search.

On first use, the server automatically:

Downloads all Parquet files (~7 GB) from HuggingFace to ~/.swiss-caselaw/parquet/
Builds a local SQLite FTS5 full-text search index at ~/.swiss-caselaw/decisions.db (~58 GB)

This takes 30–60 minutes depending on your machine and connection. It only happens once — after that, searches run instantly against the local database.

Total disk usage: ~65 GB in ~/.swiss-caselaw/ (macOS/Linux) or %USERPROFILE%\.swiss-caselaw\ (Windows).

Setup with Claude Desktop

See the Claude Desktop setup guide for step-by-step instructions (macOS + Windows).

Quick version — add this to your claude_desktop_config.json:

json

{
  "mcpServers": {
    "swiss-caselaw": {
      "command": "/path/to/caselaw-repo-1/.venv/bin/python3",
      "args": ["/path/to/caselaw-repo-1/mcp_server.py"]
    }
  }
}

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows). On Windows, use .venv\\Scripts\\python.exe instead.

Any MCP-compatible client works with the same command + args pattern.

Keeping the data current

The dataset is updated daily. To get the latest decisions, ask Claude to run the update_database tool, or call it explicitly. This re-downloads the Parquet files from HuggingFace and rebuilds the local database.

SQLite snapshot artifacts

The HuggingFace dataset may also publish a full compressed SQLite base snapshot for bootstrap tools under artifacts/sqlite/snapshots/. Its metadata lives in artifacts/manifest.json as snapshot; if that value is null, consumers should fall back to the Parquet rebuild path above.

The snapshot is intended for local MCP/server bootstrapping: download artifacts/manifest.json, fetch snapshot.sqlite_zst.path, verify snapshot.sqlite_zst.sha256, decompress to decisions.db.tmp, run a quick SQLite row/schema check, then atomically move it to decisions.db. Newer artifacts/sqlite/deltas/*.sqlite.zst entries can then be applied by tools that support delta updates.

Manual snapshot bootstrap:

bash

pip install zstandard

python - <<'PY'
import hashlib
import json
import os
import sqlite3
import urllib.request
from pathlib import Path

import zstandard as zstd

base = "https://huggingface.co/datasets/voilaj/swiss-caselaw/resolve/main"
data_dir = Path(os.environ.get("SWISS_CASELAW_DIR", Path.home() / ".swiss-caselaw")).expanduser()
data_dir.mkdir(parents=True, exist_ok=True)

with urllib.request.urlopen(f"{base}/artifacts/manifest.json") as r:
    manifest = json.load(r)

snapshot = manifest.get("snapshot")
if not snapshot:
    raise SystemExit("No SQLite snapshot is advertised; use update_database instead.")

meta = snapshot["sqlite_zst"]
tmp_db = data_dir / "decisions.db.tmp"
final_db = data_dir / "decisions.db"

class HashingReader:
    def __init__(self, raw, digest):
        self.raw = raw
        self.digest = digest

    def read(self, size=-1):
        data = self.raw.read(size)
        if data:
            self.digest.update(data)
        return data

h = hashlib.sha256()
with urllib.request.urlopen(f"{base}/{meta['path']}") as src, tmp_db.open("wb") as dst:
    zstd.ZstdDecompressor().copy_stream(HashingReader(src, h), dst)
if h.hexdigest() != meta["sha256"]:
    tmp_db.unlink(missing_ok=True)
    raise SystemExit("SHA-256 verification failed")

con = sqlite3.connect(tmp_db)
try:
    rows = con.execute("SELECT COUNT(*) FROM decisions").fetchone()[0]
    con.execute("SELECT decision_id FROM decisions LIMIT 1").fetchone()
finally:
    con.close()

expected = snapshot.get("rows")
if expected is not None and rows != expected:
    raise SystemExit(f"Row-count check failed: got {rows}, expected {expected}")

tmp_db.replace(final_db)
print(f"Installed {final_db} with {rows:,} decisions")
PY

How the local database works

code

~/.swiss-caselaw/
├── parquet/              # Downloaded Parquet files from HuggingFace (~7 GB)
│   └── data/
│       ├── bger.parquet
│       ├── bvger.parquet
│       └── ...           # 100 files, one per court
├── decisions.db          # SQLite FTS5 search index (~58 GB)
├── reference_graph.db    # Case citations + statute links (~3.5 GB)
└── statutes.db           # Federal law articles from Fedlex (~610 MB)

All data stays on your machine. No API calls are made during search — the MCP server queries the local SQLite database directly.

Database structure. decisions.db is a single SQLite file with two tables:

decisions — the main table with one row per decision. Holds 24 columns, including the search-facing fields plus json_data (full record blob) and canonical_key for dedup-aware lookup. Indexed on court, canton, decision_date, language, docket_number, chamber, and decision_type for fast filtered queries.
decisions_fts — an FTS5 virtual table that mirrors 7 text columns from decisions: court, canton, docket_number, language, title, regeste, and full_text. FTS5 builds an inverted index over these columns, enabling sub-second full-text search across 1M+ decisions. The tokenizer is unicode61 remove_diacritics 2, which handles accented characters across German, French, Italian, and Romansh. Insert/update/delete triggers keep the FTS index in sync with the main table automatically.

Why ~58 GB. The full text of 962K+ court decisions averages ~15 KB per decision. The FTS5 inverted index adds overhead for every unique token, its position, and the column it appears in. This is a known trade-off: FTS5 indexes over large text corpora are substantially larger than the source data, but they enable instant ranked search without external infrastructure.

Search pipeline. When you search, the server:

Detects query intent — docket number lookup (6B_1234/2023), explicit FTS syntax (Mietrecht AND Kündigung), or natural language (decisions on tenant eviction).
Runs multiple FTS5 query strategies — For natural-language queries, the server generates several FTS query variants (AND, OR, phrase, field-focused on regeste/title, with multilingual term expansion) and executes them in sequence. Each strategy produces a ranked candidate set. For explicit syntax (AND/OR/NOT, quoted phrases, column filters), the raw query is tried first.
Fuses candidates via RRF — Results from all strategies are merged using Reciprocal Rank Fusion: each candidate's score is the weighted sum of 1/(k + rank) across all strategies that returned it. Decisions found by multiple strategies get a boost.
Reranks with signal scoring — The top candidates are reranked using a composite score that combines:
- BM25 score (from FTS5, with custom column weights: full_text 1.2, regeste 5.0, title 6.0 — headnotes and titles are weighted heavily over body text)
- Term coverage in title (3.0x), regeste (2.2x), and snippet (0.8x)
- Phrase match in title/regeste (1.8x)
- Docket match — exact (6.0x) or partial (2.0x)
- Statute/citation graph signals — if the query mentions an article (e.g., "Art. 8 BV"), decisions that cite that provision are boosted
- Court prior — e.g., asylum queries boost BVGer results
Selects the best passage — For each result, the server scans the full text for the most relevant passage and returns it as a snippet.

Available tools

Available on both remote and local unless noted.

Tool	Description
`search_decisions`	Full-text search with filters (court, canton, language, date range, chamber)
`get_decision`	Fetch a single decision by docket number or ID. Includes citation graph counts (cited by / cites).
`list_courts`	List all courts with decision counts
`get_statistics`	Aggregate stats by court, canton, or year
`find_citations`	Show what a decision cites and what cites it, with confidence scores
`find_appeal_chain`	Trace the appeal chain (Instanzenzug) — prior and subsequent instances
`find_leading_cases`	Find the most-cited decisions for a topic or statute
`analyze_legal_trend`	Year-by-year decision counts for a statute or topic
`draft_mock_decision`	Build a research-only mock decision outline from facts, grounded in caselaw + statute references; asks clarification questions before conclusion
`get_case_brief`	Structured brief for any case — regeste, key Erwägungen, cited statutes, and citation authority
`get_doctrine`	Statute article or legal concept → ranked leading cases + doctrine timeline
`generate_exam_question`	Legal topic → real BGE fact pattern with hidden analysis for Fallbearbeitung practice
`get_law`	Look up a federal or cantonal Swiss law by SR number / abbreviation + optional canton. Returns full article text from the local mirror (Fedlex for federal; cantonal_laws.db for cantonal — direct portal scrape for 22 cantons, LexFind PDF extraction for the remaining 4)
`search_laws`	Unified federal + cantonal FTS5 search with BM25 rank interleaving. Filter by `canton=` for a specific jurisdiction, or `jurisdiction='federal'` / `'cantonal'`
`get_commentary`	Scholarly commentary for a specific federal law article from OnlineKommentar.ch (CC-BY-4.0)
`search_commentaries`	Full-text search across 362 legal commentaries from OnlineKommentar.ch across 19 federal laws
`search_legislation`	LexFind-backed discovery search across federal + cantonal legislation. `fetch_top_n_texts=N` enriches the top N results with full article text in a single call
`get_legislation`	Full metadata + article text for any federal or cantonal law. Local-first (statutes.db → cantonal_laws.db → LexFind API fallback)
`browse_legislation_changes`	Recent-changes feed per canton or federal level (live LexFind API, no local mirror)
`update_database`	Re-download latest Parquet files from HuggingFace and rebuild the local database (local only)
`check_update_status`	Check progress of a running database update (local only)

Citation-integrity toolkit (anti-hallucination)

OpenCaseLaw treats Swiss legal citations as a closed-corpus problem: every reference an LLM writes either resolves to a real entry in the ~1.05M-record corpus + Fedlex statute mirror, or it does not. The MCP server ships a four-tool toolkit that makes this contract enforceable end-to-end.

Tool	Purpose
`cite`	Build the canonical citation_string + canonical_url for a Swiss reference. Returns `exists=false` plus close_matches when the reference is fabricated — the LLM is contracted to copy the returned string verbatim instead of constructing one itself.
`check_claim_support`	Per-claim Sonnet judge: given a (claim, decision_id, optional pinpoint), return `supports: yes / partial / no / contradicts / unrelated` against the verbatim Erwägung text. Different model family (Sonnet) than the one running retrieval (Haiku) so retrieval errors are not re-introduced in verification.
`attest_response`	Closing audit, called once before a final answer ships. Runs up to five rails over the LLM's draft: ① case — every BGE/BGer/BVGer/BStGer/BPatGer/MKGE reference exists, every pinpoint resolves; ② statute — every `Art. X LAW` reference resolves in `statutes.db`; ③ quote — every `"…"` of ≥30 chars appears verbatim in a cited source (decision or statute); ④ date — every `vom DD.MM.YYYY` adjacent to a citation matches the stored decision date; ⑤ grounding (opt-in via `audit_grounding=true`) — for each verified citation, an independent Sonnet judge checks whether the cited source actually supports the proposition the LLM attached to it. Returns `linked_text` ready to ship verbatim with every validated citation wrapped in a Markdown link.
`get_erwaegung` / `get_regeste` / `get_law` / `get_materialien` / `get_commentary`	The verbatim-text suppliers — the only sources the LLM is permitted to direct-quote.

The architecture defends against two empirically-measured legal-LLM failure classes:

Hallucination (Dahl, Magesh, Suzgun & Ho, Large Legal Fictions, Stanford RegLab, 2024 — Journal of Legal Analysis): 58–88 % of legal queries to general-purpose LLMs produced at least one fabricated authority. A follow-up Stanford RegLab study of commercial legal-RAG tools (Magesh et al., Hallucination-Free?, 2024) measured 17–33 %. → caught by audits ① ② ③ ④.
Reasoning error (Butler & Butler, Isaacus, Legal RAG Bench, Mar 2026): citation is real and source was retrieved, but the proposition attached to it is not actually supported by the cited text. → caught by audit ⑤.

The full server prompt (R1–R8) embeds these rules so any connecting client (Claude, ChatGPT, Cursor, Gemini, Copilot Studio) inherits the contract automatically. See mcp_server.py for the implementation, tests/web/test_attest_audits.py for the regression suite, and the verification section on opencaselaw.ch for a public explainer.

End-to-end performance against this architecture is measured by Swiss Legal RAG Bench — a benchmark modelled on Butler & Butler's Legal RAG Bench methodology, covering DE/FR/IT federal-law questions and decomposing errors into hallucination / retrieval / reasoning components. v0.1 baseline (live OpenCaseLaw + Claude Sonnet 4.6, 10 questions): 100 % correctness, 90 % groundedness, 70 % retrieval accuracy.

Example queries

These work on both the remote and local server:

code

> Search for BGer decisions on Mietrecht Kündigung from 2024

> What did the BVGer rule on asylum seekers from Eritrea?

> Show me the full text of 6B_1234/2023

> How many decisions does each court in canton Zürich have?

> Find decisions citing Art. 8 BV

> What are the leading cases on Art. 8 EMRK?

> Show me the citation network for BGE 138 III 374

> How has Mietrecht jurisprudence evolved over time?

> Show me Art. 41 OR (statute lookup)

> Search for statute provisions about Verjährung

> Trace the appeal chain for 5A_234/2026

> Explain BGE 133 III 121 to me

> What are the leading cases on Art. 41 OR and how has the doctrine evolved?

> Give me a practice case on Haftpflichtrecht

> Search for cantonal data protection laws

> Show me the details of SR 220 (Obligationenrecht)

> What legislation changed recently in Zürich?

The AI calls the MCP tools automatically — you see the search results inline and can ask follow-up questions about specific decisions.

Citation graph tools

Four tools expose the reference graph: 9.65 million resolved decision-to-decision citation edges (10 million extracted) and 12.4 million statute references. These require the graph database (output/reference_graph.db); if it's not available, the tools return a message instead of failing.

find_citations — Given a decision, show its outgoing citations (what it references) and incoming citations (what references it). Each resolved citation includes the target decision's metadata and a confidence score. Unresolved references (e.g., older decisions not in the dataset) appear with their raw reference text.

code

> Show me the citation network for BGE 138 III 374

## Outgoing (13 — what this decision cites)
1. BGE 136 III 365 (2010-01-01) [bge] conf=0.98 mentions=1
2. BGE 133 III 189 (2007-01-01) [bge] conf=0.93 mentions=1
...

## Incoming (13,621 — what cites this decision)
1. 5A_234/2026 (2026-02-19) [bger] conf=0.92 mentions=2
2. 5A_117/2026 (2026-01-30) [bger] conf=0.88 mentions=1
...

Parameters: decision_id (required), direction (both/outgoing/incoming), min_confidence (0–1, default 0.3), limit (default 50, max 200).

find_appeal_chain — Trace the appeal chain (Instanzenzug) for a decision. Shows prior instances (lower courts) and subsequent instances (appeals to higher courts), reconstructing the full procedural path (e.g., Bezirksgericht → Obergericht → Bundesgericht).

Parameters: decision_id (required), min_confidence (0–1, default 0.3).

find_leading_cases — Find the most-cited decisions, ranked by how many other decisions reference them. Filter by statute (law code + article), text query, court, or date range.

code

> What are the leading cases on Art. 8 EMRK?

1. BGE 135 I 143 (2009) — 3,840 citations
   Regeste: Anspruch auf Aufenthaltsbewilligung...
2. BGE 130 II 281 (2004) — 3,155 citations
   Regeste: Familiennachzug; gefestigtes Anwesenheitsrecht...

Parameters: query (optional text), law_code + article (optional statute), court, date_from, date_to, limit (default 20, max 100). At least one of query or law_code is recommended; without any filter it returns the globally most-cited decisions.

analyze_legal_trend — Year-by-year decision counts showing how jurisprudence on a topic or statute has evolved over time. Returns a table with counts and a visual bar chart.

code

> How has Art. 29 BV jurisprudence evolved?

**Filter:** Art. 29 BV
**Total:** 34,669 decisions

Year     Count  Bar
2000       275  █████
2005       733  ████████████
2010     1,028  █████████████████
2015     1,536  ██████████████████████████
2020     1,896  ████████████████████████████████
2025     2,400  ████████████████████████████████████████

Parameters: query (optional text), law_code + article (optional statute), court, date_from, date_to. At least one of query or law_code is required.

Statute lookup tools (local, federal + cantonal)

Two tools provide direct access to Swiss law text from the local mirror, covering both federal and cantonal jurisdictions with article-level FTS5 indexing and sub-millisecond lookup:

Federal: 5,525 laws / ~133,359 articles in each of DE/FR/IT from the Fedlex SPARQL endpoint, mirrored monthly into statutes.db. Covers every consolidated federal act in German, French, and Italian.
Cantonal: 15,600 laws / 361,430 articles in cantonal_laws.db, sourced via two layers:
- Direct portal scraping (primary) — 22 cantons whose official Gesetzessammlungen are published via the LexWork, SIL, ZH OpenData, or TI Raccolta delle Leggi platforms (AG, AI, AR, BE, BL, BS, FR, GE, GL, GR, LU, NE, NW, OW, SG, SH, SO, TG, TI, VS, ZG, ZH). The HTML is parsed natively — no PDF extraction, no OCR — yielding clean article-level data.
- LexFind PDF fallback — 4 cantons not yet covered by direct scrapers (JU, SZ, UR, VD). PDFs from LexFind.ch are extracted with PyMuPDF and segmented into articles. Bilingual secondary-language passes for BE / FR / VS / GR.
- Combined and federated via SQLite FTS5 with the federal table.

get_law — Look up any Swiss law (federal or cantonal) by SR number or abbreviation, optionally fetching a specific article with full text.

code

> Show me Art. 8 BV

# BV — SR 101
**Bundesverfassung der Schweizerischen Eidgenossenschaft vom 18. April 1999**

### Art. 8 — Rechtsgleichheit
1 Alle Menschen sind vor dem Gesetz gleich.
2 Niemand darf diskriminiert werden, namentlich nicht wegen der Herkunft, ...

> Show me Art. 1 of the Zurich Hundegesetz

get_law(canton="ZH", sr_number="554.5", article="1")

Parameters: sr_number or abbreviation (at least one required), article (optional — omit to see the full article list), language (de/fr/it, default de), canton (default CH; set to ZH, BE, etc. for cantonal lookup).

search_laws — Unified FTS5 search across every Swiss statute article, federal and cantonal. BM25-ranked per corpus, merged by rank interleaving so each response surfaces both jurisdictions.

code

> Search for statute provisions about Verjährung

1. [CH]  Art. 130 OR (SR 220): Die Verjährung beginnt mit der Fälligkeit der Forderung...
2. [ZH]  § 19 Kirchgemeindenreglement (SR 182.60): ... Verjährungsbestimmungen ...
3. [CH]  Art. 132 OR (SR 220): Bei der Berechnung der Frist ist der Tag...

Parameters: query (required, FTS5 syntax), sr_number (optional — one specific federal law, implies federal-only), canton (optional — restrict to one canton, or CH for federal-only), jurisdiction (all / federal / cantonal, default all), language (de/fr/it), limit (1–50).

Legislation discovery tools (LexFind-backed)

Three additional tools layer the live LexFind API on top of the local mirror for cases where the mirror isn't enough — newly published versions between refresh cycles, full version history, recent-changes feeds. These are the broader discovery surface; for plain "give me the current text" queries get_law / search_laws are faster and more reliable.

search_legislation — Broader discovery search across Swiss legislation, with optional single-call full-text enrichment. Useful when you don't know whether the law is federal or cantonal, or when you need a one-shot natural-language workflow.

code

> Search for the Bernese dog act with full text

search_legislation(query="Hundegesetz", canton="BE", fetch_top_n_texts=2)
→ returns top 2 matches with full_text_preview + sample_articles inline,
  no follow-up get_legislation call needed.

Parameters: query (required), canton (optional — CH, ZH, BE, etc.), active_only (default true), search_in_content (default false — searches titles/keywords; set true to search law text), language (de/fr/it), limit (1–60, default 20), fetch_top_n_texts (0–10, default 0 — set to N to enrich top N results with parsed full article text).

get_legislation — Get details for a specific law including metadata, version history, and links to official sources (Fedlex, cantonal portals).

code

> Show me the Obligationenrecht on LexFind

SR 220 — Bundesgesetz betreffend die Ergänzung des Schweizerischen
Zivilgesetzbuches (Fünfter Teil: Obligationenrecht)
Entity: Bund (CH) | Category: Gesetz | Keywords: OR
In force since: 01.01.2026
Sources:
  DE: https://www.fedlex.admin.ch/eli/cc/27/317_321_377/de
  FR: https://www.fedlex.admin.ch/eli/cc/27/317_321_377/fr

Parameters: lexfind_id (from search results) or systematic_number + canton (e.g., "220" + "CH"), include_versions (default false), language (de/fr/it).

browse_legislation_changes — Recent legislation changes for a canton or federal level. Shows new laws, amendments, and abrogations with dates and links.

code

> What legislation changed recently in Zürich?

1. [01.03.2026] version — Vollzugsverordnung zur Finanzverordnung (SR 181.131)
2. [01.03.2026] new — Studienordnung für den Masterstudiengang... (SR 414.253.125)
3. [01.03.2026] version — Organisationsverordnung der Finanzdirektion (SR 172.110.3)

Parameters: canton (default CH), language (de/fr/it).

Education tools

Three tools support legal study covering the three core student workflows: understanding a case, understanding a doctrine, and practicing exam subsumption. Tools return rich structured data; Claude acts as the tutor and generates all pedagogy dynamically.

get_case_brief — Any case reference ("BGE 133 III 121", docket number, or decision_id) → structured brief. Returns regeste, Sachverhalt, key numbered Erwägungen, Dispositiv, cited statutes with text excerpts, citation authority (incoming/outgoing count), and the top cited-by and cites cases.

get_doctrine — Statute article ("Art. 41 OR") or legal concept ("culpa in contrahendo", "Tierhalterhaftung") → doctrine overview. Returns the leading cases ranked by citation count, a chronological doctrine timeline showing how rules evolved, and the statute text (if applicable).

generate_exam_question — Legal topic ("Haftpflichtrecht", "Art. 41 OR", "Mietrecht") → real Fallbearbeitung. Picks a leading BGE, returns the anonymized Sachverhalt as fact pattern plus a hidden analysis (applicable statutes, legal test, correct outcome). The student writes a subsumption, then asks Claude to reveal the analysis for comparison and feedback. Pass exclude_ids to avoid repeating the same case.

draft_mock_decision can use optional Fedlex URLs and caches fetched statute excerpts in ~/.swiss-caselaw/fedlex_cache.json (configurable via SWISS_CASELAW_FEDLEX_CACHE).

Search quality benchmark

Use a fixed golden query set to track search relevance over time:

bash

python3 benchmarks/run_search_benchmark.py \
  --db ~/.swiss-caselaw/decisions.db \
  -k 10 \
  --json-output benchmarks/latest_search_benchmark.json

Metrics: MRR@k, Recall@k, nDCG@k, Hit@1

The repository also ships a frozen offline baseline at benchmarks/search_benchmark_2026-03-19_offline_full.json. On the full 100-query set against a 1,078,177-row local decisions.db, that run recorded MRR@10 = 0.4697, Recall@10 = 0.4958, nDCG@10 = 0.5250, and Hit@1 = 0.33. Treat it as a reproducible offline baseline rather than a fully provisioned hosted-deployment score.

You can enforce minimum quality gates (non-zero exit on failure):

bash

python3 benchmarks/run_search_benchmark.py \
  --db ~/.swiss-caselaw/decisions.db \
  -k 10 \
  --min-mrr 0.50 \
  --min-recall 0.75 \
  --min-ndcg 0.85

Build Reference Graph (Optional)

For statute/citation-aware reranking, build the local graph database:

bash

python3 search_stack/build_reference_graph.py \
  --source-db ~/.swiss-caselaw/decisions.db \
  --courts bger,bge,bvger \
  --db output/reference_graph.db

Then point the server to it:

bash

export SWISS_CASELAW_GRAPH_DB=output/reference_graph.db

Graph signals are enabled by default. To disable them, set SWISS_CASELAW_GRAPH_SIGNALS=0.

Build Statutes Database (Optional)

For statute lookup (get_law, search_laws), build the Fedlex statute database:

bash

# Download the top 100 most-cited federal laws from Fedlex
python3 -m scrapers.fedlex --top 100

# Build the SQLite FTS5 statutes database
python3 -m search_stack.build_statutes_db

Then copy to the data directory:

bash

cp output/statutes.db ~/.swiss-caselaw/

Or set the path explicitly:

bash

export SWISS_CASELAW_STATUTES_DB=output/statutes.db

2. Download the dataset

The full dataset is on HuggingFace as Parquet files — one file per court, 34 fields per decision including complete decision text.

Machine-consumable artifact metadata is published at artifacts/manifest.json. Besides daily Parquet/SQLite deltas, the manifest may point to an optional full compressed SQLite snapshot at artifacts/sqlite/snapshots/<date>.decisions.sqlite.zst for tools that want to bootstrap a local FTS5 database without rebuilding from Parquet.

With Python (datasets library)

Step 1. Install the library:

bash

pip install datasets

Step 2. Load the data:

python

from datasets import load_dataset

# Load a single court (~170k decisions, ~800 MB)
bger = load_dataset("voilaj/swiss-caselaw", data_files="data/bger.parquet")

# Load all courts (~900K decisions, ~6.5 GB download)
ds = load_dataset("voilaj/swiss-caselaw", data_files="data/*.parquet")

Step 3. Explore:

python

# Print a single decision
decision = bger["train"][0]
print(decision["docket_number"])   # "6B_1/2024"
print(decision["decision_date"])   # "2024-03-15"
print(decision["language"])        # "de"
print(decision["regeste"][:200])   # First 200 chars of the headnote
print(decision["full_text"][:500]) # First 500 chars of the full text

With pandas

python

import pandas as pd

# Load one court
df = pd.read_parquet("hf://datasets/voilaj/swiss-caselaw/data/bger.parquet")

# Filter by date
df_recent = df[df["decision_date"] >= "2024-01-01"]
print(f"{len(df_recent)} decisions since 2024")

# Filter by language
df_french = df[df["language"] == "fr"]

# Group by legal area
df.groupby("legal_area").size().sort_values(ascending=False).head(10)

Direct download

Every court is a single Parquet file. Download directly:

code

https://huggingface.co/datasets/voilaj/swiss-caselaw/resolve/main/data/bger.parquet
https://huggingface.co/datasets/voilaj/swiss-caselaw/resolve/main/data/bvger.parquet
https://huggingface.co/datasets/voilaj/swiss-caselaw/resolve/main/data/zh_gerichte.parquet
...

Full list of files: huggingface.co/datasets/voilaj/swiss-caselaw/tree/main/data

3. REST API

Query the dataset over HTTP without installing anything. This uses the HuggingFace Datasets Server.

Get rows:

bash

curl "https://datasets-server.huggingface.co/rows?dataset=voilaj/swiss-caselaw&config=default&split=train&offset=0&length=5"

Get dataset info:

bash

curl "https://datasets-server.huggingface.co/info?dataset=voilaj/swiss-caselaw"

Search by SQL (DuckDB endpoint):

bash

curl -X POST "https://datasets-server.huggingface.co/search?dataset=voilaj/swiss-caselaw&config=default&split=train" \
  -d '{"query": "SELECT docket_number, decision_date, language FROM data WHERE court = '\''bger'\'' LIMIT 10"}'

Note: The REST API queries the dataset as configured in the HuggingFace repo (per-court Parquet files, full 34-field schema). For bulk access or local analysis, use the download method above.

4. Web UI

A local chat interface for searching Swiss court decisions. Ask questions in natural language, and an AI assistant searches the full corpus and answers with cited decisions.

code

Browser (localhost:5173)  →  FastAPI backend  →  MCP server  →  Local SQLite FTS5 DB

Everything runs on your machine. No data leaves your computer (except LLM API calls to the provider you choose).

What you need

Requirement	How to check	Where to get it
Python 3.10+	`python3 --version` (macOS/Linux) or `python --version` (Windows)	python.org/downloads
Node.js 18+	`node --version`	nodejs.org — download the LTS version
An LLM provider	(see below)	At least one cloud API key or a local model via Ollama
~65 GB free disk	`df -h .` (macOS/Linux)	For the search index (downloaded on first run)

Windows users: Install Python from python.org and check "Add Python to PATH" during installation. Node.js installs npm automatically.

Cloud providers (choose at least one, or use Ollama below)

Provider	Env variable	Where to get a key	Cost
Google Gemini	`GEMINI_API_KEY`	aistudio.google.com/apikey	Free tier available
OpenAI	`OPENAI_API_KEY`	platform.openai.com/api-keys	Free credits for new accounts
Anthropic (Claude)	`ANTHROPIC_API_KEY`	console.anthropic.com	Pay-as-you-go

Important: A Claude Desktop or Claude Pro subscription does NOT include an API key. You need a separate developer account at console.anthropic.com.

Local models (no API key needed)

If you prefer not to use cloud APIs, you can run everything locally with Ollama:

Model	Command to install	Download size	RAM needed
Qwen 2.5 (14B)	`ollama pull qwen2.5:14b`	~9 GB	~16 GB
Llama 3.3 (70B)	`ollama pull llama3.3:70b`	~40 GB	~48 GB

Install Ollama from ollama.com (macOS, Linux, Windows), then:

bash

ollama serve          # start the Ollama server (leave running)
ollama pull qwen2.5:14b   # download a model (one-time)

The Web UI auto-detects Ollama and shows local models as available.

Step-by-step setup

Step 1. Clone the repository:

bash

git clone https://github.com/jonashertner/opencaselaw.git
cd caselaw-repo-1

Step 2. Create a Python virtual environment:

bash

python3 -m venv .venv

Activate it:

OS	Command
macOS / Linux	`source .venv/bin/activate`
Windows (PowerShell)	`.venv\Scripts\Activate.ps1`
Windows (cmd)	`.venv\Scripts\activate.bat`

You'll know it's active when your terminal prompt starts with (.venv).

Step 3. Install Python dependencies:

bash

pip install fastapi uvicorn python-dotenv mcp pyarrow pydantic

Then install at least one LLM provider SDK:

bash

pip install anthropic        # for Claude
pip install openai           # for OpenAI / GPT-4o / local models via Ollama
pip install google-genai     # for Google Gemini

Tip: The openai package is also used for local Ollama models (Ollama exposes an OpenAI-compatible API). If you only want to use local models, pip install openai is sufficient — no cloud API key required.

Step 4. Install the frontend:

bash

cd web_ui && npm install && cd ..

Step 5. Configure your API key:

bash

cp .env.example .env

Open .env in a text editor and paste your API key on the appropriate line. For example, if you have a Gemini key, change GEMINI_API_KEY=AI... to your actual key. Leave the other provider lines as-is — they will be ignored if empty.

You can also skip this step and configure keys from the Settings panel inside the UI after starting.

Step 6. Start the app:

OS	Command
macOS / Linux	`./scripts/run_web_local.sh`
Windows (PowerShell)	`.\scripts\run_web_local.ps1`

Open http://localhost:5173 in your browser.

What to expect on first run: The MCP server will automatically download the dataset (~7 GB) from HuggingFace and build a local search index (~58 GB). This takes 30–60 minutes depending on your connection and disk speed. You'll see progress in the terminal. After this one-time setup, the app starts instantly.

Features

5 models: Claude, OpenAI, Gemini (cloud) + Qwen 2.5 and Llama 3.3 via Ollama (local)
Local-first option: Run entirely on your machine with Ollama — no cloud API keys needed
Streaming: Responses appear token-by-token in real time
Tool-augmented chat: The AI calls search, get_decision, list_courts, etc. automatically
Decision cards: Clickable statute references with inline Fedlex article text
Filters: Narrow results by court, canton, language, and date range
In-app settings: Configure API keys and Ollama connection from the UI
Export: Download conversations as Markdown, Word, or PDF

Troubleshooting

Problem	Solution
`python3: command not found` (Windows)	Use `python` instead of `python3`, or reinstall Python with "Add to PATH" checked
`npm: command not found`	Install Node.js from nodejs.org
`ModuleNotFoundError: No module named 'fastapi'`	Activate your venv (`source .venv/bin/activate`) and re-run `pip install ...`
"No provider configured" banner	Click the gear icon (Settings) and paste an API key, or start Ollama
"Database not found" on first run	Wait for the initial download to finish (check terminal for progress)
Port already in use	Edit `BACKEND_PORT` or `FRONTEND_PORT` in `.env`
PowerShell script blocked (Windows)	Run `Set-ExecutionPolicy -Scope CurrentUser RemoteSigned` once

For advanced configuration (custom ports, MCP server path, timeouts), see .env.example.

What's in each decision

Every decision has 34 structured fields:

Core fields

Field	Type	Example	Description
`decision_id`	string	`bger_6B_1234_2025`	Unique key: `{court}_{docket_normalized}`
`court`	string	`bger`	Court code (full list)
`canton`	string	`CH`	`CH` for federal, `ZH`/`BE`/`GE`/... for cantonal
`docket_number`	string	`6B_1234/2025`	Original case number as published
`decision_date`	date	`2025-03-15`	Date the decision was rendered
`language`	string	`de`	`de`, `fr`, `it`, or `rm`
`full_text`	string	(complete text)	Full decision text, typically 5–50 pages
`source_url`	string	`https://bger.ch/...`	Permanent link to the original

Legal content

Field	Type	Description
`regeste`	string	Legal headnote / summary (Regeste)
`legal_area`	string	Area of law (Strafrecht, Zivilrecht, ...)
`title`	string	Subject line (Gegenstand)
`outcome`	string	Result: Gutheissung, Abweisung, Nichteintreten, ...
`decision_type`	string	Type: Urteil, Beschluss, Verfügung, ...
`cited_decisions`	string	JSON array of cited decision references
`bge_reference`	string	BGE collection reference if published
`abstract_de`	string	German abstract (primarily BGE)
`abstract_fr`	string	French abstract
`abstract_it`	string	Italian abstract

Court metadata

Field	Type	Description
`chamber`	string	Chamber (e.g., "I. zivilrechtliche Abteilung")
`judges`	string	Panel composition
`clerks`	string	Court clerks (Gerichtsschreiber)
`collection`	string	Official collection reference
`appeal_info`	string	Appeal status / subsequent proceedings

Technical fields

Field	Type	Description
`docket_number_2`	string	Secondary docket number
`publication_date`	date	Date published online
`pdf_url`	string	Direct URL to PDF
`external_id`	string	Cross-reference ID
`scraped_at`	datetime	When this decision was scraped
`source`	string	Data source identifier
`source_id`	string	Source-specific ID (e.g. Signatur)
`source_spider`	string	Source spider/scraper name
`content_hash`	string	MD5 of full_text for deduplication
`has_full_text`	bool	Whether `full_text` is non-empty
`text_length`	int	Character count of `full_text`

Full 34-field Parquet export schema: export_parquet.py

Coverage

Federal courts

Court	Code	Decisions	Period	Source
Federal Supreme Court (BGer)	`bger`	~173,000	1996–present	bger.ch
BGE Leading Cases	`bge`	~45,000	1954–present	bger.ch CLIR
Federal Administrative Court (BVGer)	`bvger`	~91,000	2007–present	bvger.ch
Federal Admin. Practice (VPB)	`ch_vb`	~23,000	1982–2016	admin.ch
Federal Criminal Court (BStGer)	`bstger`	~11,000	2004–present	bstger.weblaw.ch
EDÖB (Data Protection)	`edoeb`	~1,200	1994–present	edoeb.admin.ch
FINMA	`finma`	~1,200	2008–2024	finma.ch
ECHR (Swiss cases, BGer-published)	`bge_egmr`	~475	1974–present	bger.ch CLIR
ECHR Switzerland (HUDOC)	`hudoc_ch`	834	1959–present	HUDOC API
ECtHR Chamber judgments	`ecthr_chamber`	7,761	1960–present (FR or EN)	HUDOC API
ECtHR Grand Chamber	`ecthr_grand_chamber`	514	1960–present (FR or EN)	HUDOC API
ECtHR Committee judgments	`ecthr_committee`	0 — importance 4, out of scope		HUDOC API
Militärkassationsgericht (MKG)	`mkg`	1,244	1915–2025	oa.admin.ch + alexandria.ch
Federal Patent Court (BPatGer)	`bpatger`	~190	2012–present	bpatger.ch
Competition Commission (WEKO)	`weko`	~120	2009–present	weko.admin.ch
Sports Tribunal	`ta_sst`	~50	2024–present	ta-sst.ch
Federal Council	`ch_bundesrat`	~15	2012–present	bj.admin.ch

Cantonal courts

77 courts across all 26 cantons. The largest cantonal collections:

Canton	Courts	Decisions	Period
Vaud (VD)	3	~155,000	1984–present
Zürich (ZH)	20	~126,000	1980–present
Genève (GE)	1	~116,000	1993–present
Ticino (TI)	1	~58,000	1995–present
St. Gallen (SG)	7	~35,000	2001–present
Graubünden (GR)	1	~29,000	2002–present
Basel-Landschaft (BL)	1	~26,000	2000–present
Bern (BE)	6	~26,000	2002–present
Aargau (AG)	18	~21,000	1993–present
Basel-Stadt (BS)	3	~19,000	2001–present

All 26 cantons covered: AG, AI, AR, BE, BL, BS, FR, GE, GL, GR, JU, LU, NE, NW, OW, SG, SH, SO, SZ, TG, TI, UR, VD, VS, ZG, ZH.

Live per-court statistics: Dashboard

How it works

code

                        ┌──────────────────────────────────────────────────────┐
                        │                    Daily Pipeline                    │
                        │                                                      │
Court websites ────────►│  Scrapers ──► JSONL ──┬──► Parquet ──► HuggingFace   │
  bger.ch               │  (45 scrapers,        │                              │
  bvger.ch              │   rate-limited,        ├──► FTS5 DB ───┐             │
  cantonal portals      │   resumable)           │               ├► MCP Server │
                        │                        └──► Graph DB ──┘             │
                        │                                          ▲           │
Fedlex (SPARQL) ───────►│  Fedlex scraper ──► XML ──► Statutes DB ─┘           │
                        │                                                      │
                        │  01:00 UTC  scrape        04:00 UTC  publish         │
                        └──────────────────────────────────────────────────────┘

Step by step

Scrape (01:00 UTC daily) — 45 scrapers run in parallel, each targeting a specific court's website or API. Every scraper is rate-limited and resumable: it tracks which decisions it has already seen and only fetches new ones. Output: one JSONL file per court. A separate Fedlex scraper downloads federal law texts (Akoma Ntoso XML) via SPARQL for the statute database.
Build search index (04:00 UTC) — JSONL files are ingested into a SQLite FTS5 database for full-text search. On Mon–Sat, this runs in incremental mode: a byte-offset checkpoint tracks how far each JSONL file has been read, so only newly appended decisions are processed (typically < 1 minute). On Sundays, a full rebuild compacts the FTS5 index and resets the checkpoint (~3 hours). Decisions appearing in multiple sources are deduplicated by decision_id, keeping the version with the longest full text. A quality enrichment step fills in missing titles, regestes, and content hashes.
Export — JSONL files are converted to Parquet (one file per court) with a fixed 34-field schema.
Upload — Parquet files are pushed to HuggingFace. The MCP server and datasets library pick up the new data automatically. Optional artifact publishing can also update artifacts/manifest.json with daily deltas and a full compressed SQLite snapshot for external bootstrap tools.
Update dashboard — stats.json is regenerated (including scraper health status from the last run) and pushed to GitHub Pages.

Running locally (developer)

For contributors and developers who want to run scrapers, build the pipeline, or modify the codebase.

Prerequisites

Python 3.10+
pip

Install

bash

git clone https://github.com/jonashertner/opencaselaw.git
cd caselaw-repo-1
python3 -m venv .venv
source .venv/bin/activate   # macOS/Linux — on Windows: .venv\Scripts\Activate.ps1
pip install -e ".[all]"

This installs all dependencies including PDF parsing, crypto, and the FastAPI server. For a minimal install without optional dependencies, use pip install -e . instead.

Scrape decisions

bash

# Scrape 5 recent decisions from the Federal Supreme Court
python run_scraper.py bger --max 5 -v

# Scrape BVGer decisions since a specific date
python run_scraper.py bvger --since 2025-01-01 --max 20 -v

# Scrape a cantonal court
python run_scraper.py zh_gerichte --max 10 -v

Output is written to output/decisions/{court}.jsonl — one JSON object per line, one file per court. The scraper remembers what it has already fetched (state stored in state/), so you can run it repeatedly to get only new decisions.

45 court codes are available. Run python run_scraper.py --list for the full list, or see the dashboard for per-court statistics.

Build a local search database

bash

# Full build (reads all JSONL, optimizes FTS index — ~3h for 900K decisions)
python build_fts5.py --output output -v

# Incremental build (reads only new JSONL bytes, skips optimize — seconds)
python build_fts5.py --output output --incremental --no-optimize -v

# Full rebuild (deletes DB + checkpoint, rebuilds from scratch)
python build_fts5.py --output output --full-rebuild -v

This reads JSONL files from output/decisions/ and builds a SQLite FTS5 database at output/decisions.db. A full build of 900K decisions takes about 3 hours and produces a ~58 GB database. Incremental mode uses a checkpoint file (output/.fts5_checkpoint.json) to skip unchanged files and seek past already-processed bytes, completing in seconds when few new decisions exist.

Export to Parquet

bash

python export_parquet.py --input output/decisions --output output/dataset -v

Converts JSONL files to Parquet format (one file per court). Output goes to output/dataset/.

Data sources

Source	What	How
Official court websites	Federal courts (bger.ch, bvger.ch, bstger.ch, bpatger.ch)	JSON APIs, structured HTML
Federal regulatory bodies	FINMA, WEKO, EDÖB, VPB	Sitecore/custom APIs
Cantonal court portals	26 cantonal platforms (Weblaw, Tribuna, FindInfo, custom portals)	Court-specific scrapers

Decisions appearing in multiple sources are deduplicated by decision_id (a deterministic hash of court code + normalized docket number). The version with the longest full text is kept.

Legal basis

Court decisions are public records under Swiss law. Article 27 BGG requires the Federal Supreme Court to publish its decisions. The Bundesgericht has consistently held that court decisions must be made accessible to the public (BGE 133 I 106, BGE 139 I 129). This project scrapes only publicly available, officially published decisions.

Governance and removal

Republication changes discoverability, so the project ships a governance policy covering source withdrawals, re-anonymization, and verified correction/removal requests. See docs/governance-and-removal-policy.md.

Contributors

Maintainer: Jonas Hertner. A small group of first users, bug reporters, institutional partners, and consumer-side integrators have shaped the tool; see CONTRIBUTORS.md for the full list and how to add yours.

If you're using OpenCaseLaw in production — as a scraper contributor, dataset consumer, law-firm integrator, or research project — we'd like to know. Email team@jonashertner.com or open a discussion.

License

Code: MIT. See LICENSE.

Dataset packaging and added metadata: CC0-1.0 to the extent rights exist. The underlying decision texts remain official published court decisions sourced from the originating courts and public bodies.

Contact

Questions, feedback, or ideas? Reach out at team@jonashertner.com.

You can also open an issue on GitHub.

Project updates are posted on LinkedIn.

Install

Tools (42)

searchfetchsearch_decisionsget_decisionget_decisionslist_courtsget_statisticsfind_citations

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.opencaselaw.ch/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "swiss-caselaw": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.opencaselaw.ch/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.