List available sub-collections in the database.

PURPOSE: Explore the database structure and find available collections.

WHEN TO USE:

• User wants to know what data is available

• Exploring the database structure

• Finding the correct collection name for other queries

Args: parent: Parent collection path (relative to data_path). Empty = root.

Returns: Collection object with path, collections list, and document_count

List files and subcollections in a collection.

PURPOSE: List files and subcollections without parsing document contents.

WHEN TO USE:

• User wants to see what's available in a collection

• Exploring collection structure

• Fast overview of files and folders

WHEN NOT TO USE:

• For document metadata → use get_file_info() afterward

• For specific keyword search → use edition-specific search tools

• For full document details → use get_document tools

Args: collection: Collection name/path (relative to data_path). Empty = root. limit: Maximum number of files to return ctx: FastMCP Context for progress reporting

Returns: Dict with 'collection_path', 'file_count', 'files', and 'subcollections'

Get basic metadata for a single document file.

PURPOSE: Extract basic TEI metadata from a document without full parsing.

WHEN TO USE:

• After browsing, to get details about specific files

• When you need title, date, or ID information

• For quick metadata extraction

WHEN NOT TO USE:

• For full document content → use get_document tools

• For multiple files at once → use browse then call this for each

Args: file_path: Full path to the file (relative to /db) or just filename ctx: FastMCP Context for progress reporting

Returns: Dict with 'id', 'title', 'date', 'path', 'mime_type', 'size_bytes', 'modified'

Get statistics about documents in a collection.

PURPOSE: Understand the size and content of a collection.

WHEN TO USE:

• User asks "how many documents are there?"

• Getting an overview before browsing/searching

• Verifying data availability

Args: collection: Collection path (relative to data_path). Empty = root.

Returns: CollectionStats object with document counts and metadata

Execute a raw XQuery against the database.

PURPOSE: Run custom queries for advanced users or debugging.

WHEN TO USE:

• Other tools don't provide the needed functionality

• Debugging or exploring data structure

• Complex custom queries

WHEN NOT TO USE:

• For common operations, use specific tools instead

• Don't use for write operations (read-only!)

Args: query: XQuery string to execute max_results: Maximum number of results to return

Returns: Raw query result as string (usually XML)

Check if the database is reachable and responsive.

PURPOSE: Verify database connectivity for troubleshooting.

WHEN TO USE:

• When other tools fail unexpectedly

• To verify setup is working

• Health monitoring

Returns: DatabaseStatus object with connection status, version, and paths

Retrieve raw XML document by its xml:id.

PURPOSE: Fetch raw XML for a document using its TEI xml:id attribute.

WHEN TO USE:

• After finding a document via search or browse

• When you need the raw XML for custom processing

• As a low-level building block for edition-specific tools

WHEN NOT TO USE:

• For exploring/discovering documents → use browse or search tools

• When you only have a file path → use get_raw_document_by_path()

Args: document_id: The xml:id attribute of the TEI document collection: Optional collection filter (relative to data_path) ctx: FastMCP Context for progress reporting

Returns: RawDocument with id and xml content

Retrieve raw XML document by its file path.

PURPOSE: Fetch raw XML for a document using its database path.

WHEN TO USE:

• When you have a file path from browse_collection

• When accessing documents with known paths

• Faster than ID-based lookup when path is known

WHEN NOT TO USE:

• When you have an xml:id → use get_raw_document_by_id()

• For exploring documents → use browse or search tools

Args: doc_path: Path to the document (relative to /db) ctx: FastMCP Context for progress reporting

Returns: RawDocument with id, xml content, and path

Retrieve complete document.

PURPOSE: Detailed view of a specific document as Markdown

WHEN TO USE:

• User wants to read a letter/diary entry

• After successful search → display details

• For citations and text analysis

WHEN NOT TO USE:

• For browsing/exploring → use list_collections() or list_collection_contents()

• For keyword search → use search_by_keyword()

Args: document_id: The xml:id of the document ctx: FastMCP Context

Returns: Formatted markdown string with document content

Search register using Lucene fulltext index.

PURPOSE: Find persons, places, works, or organizations using indexed search

WHEN TO USE:

• User searches for person, place, work, or organization

• For biographical/geographical/bibliographical information

• To get IDs for further searches

WHEN NOT TO USE:

• For fulltext search in letters/diaries → use search_by_keyword()

Args: query: Search term (name, title, etc.) register_type: Optional filter - 'person', 'place', 'work', 'org', or None for all max_results: Maximum results ctx: FastMCP Context

Returns: List of register entry dicts with id, title, desc, type

Get detailed information about a register entry.

PURPOSE: Complete register entry details, optionally with mentions

WHEN TO USE:

• After register search for details about a person/place/work

• For biographical information

• To find mentions in letters/diaries (set include_mentions=True)

WHEN NOT TO USE:

• For document details → use get_document_by_id()

Args: entry_id: xml:id of the register entry (e.g., "S0003676") include_mentions: If True, fetch mentions across letters, diaries, lectures max_mentions: Max mentions per category when include_mentions=True (default 20) ctx: FastMCP Context

Returns: PersonEntry, PlaceEntry, WorkEntry, or dict based on entry type

Search documents in Schleiermacher Digital via eXist-db with facets.

PURPOSE: Primary search tool for finding documents by text, type, year, etc.

WHEN TO USE:

• Full-text search in documents

• Filter by document type (letter, diary, lecture, etc.)

• Filter by year or date range

• Any search query for document discovery

WHEN NOT TO USE:

• For structured letter filtering by sender/receiver → use filter_letters()

• For register search (persons, places) → use search_register()

• For detailed text passages → use get_document_passages()

⚠️ CITATION WARNING: Only cite documents returned by this tool. Each result includes:

• document_id: Use this EXACT value for citations

• citation_url: Use this EXACT URL, do not construct your own NEVER invent document IDs or URLs that were not returned in the results.

Valid doc_types (from index):

• "letter" or "letter fs" (8071 documents)

• "lecture" or "lecture fs" (143 documents)

• "chronology" (61 documents)

• "intro" (42 documents)

• "chronology-intro" (29 documents)

• "diary" or "diary fs" (21 documents)

Args: query: Search terms (space-separated for multiple terms) doc_types: Filter by document types (letter, letter fs, diary, diary fs, lecture, lecture fs, chronology, intro) years: Filter by years (e.g., ["1810", "1811"]) date_from: Earliest date (ISO 8601, e.g., "1810-01-01") date_to: Latest date (ISO 8601, e.g., "1815-12-31") include_commentary: If True, search in commentary too (default: True) use_or_logic: If True, use OR between terms (default); if False, use AND limit: Maximum results (default: 50) ctx: FastMCP Context

Returns: List of SearchResult objects with document_id, title, type, date, kwic_snippets, and citation_url

Filter letters by sender, receiver, place, and time period.

PURPOSE: Filter letters by specific criteria (FAST - uses cache)

WHEN TO USE:

• User asks "letters from/to person X"

• User asks "letters from Berlin"

• User asks "letters between 1810 and 1815"

• For correspondence network analyses

WHEN NOT TO USE:

• For keyword search → use search_by_keyword()

• For register search → use search_register()

Args: sender: Person ID of sender (from register, e.g., "S0003676") receiver: Person ID of receiver (from register, e.g., "S0003677") send_place: Place ID or name of sending location (e.g., "S0000065" or "Berlin") not_before: Earliest date (ISO 8601, e.g., "1810-01-01") not_after: Latest date (ISO 8601, e.g., "1815-12-31") max_results: Maximum results ctx: FastMCP Context

Returns: List of Letter objects

Statistics about correspondents (for network analysis).

PURPOSE: Overview of most important correspondents

WHEN TO USE:

• User asks "Who was important for X?"

• User asks "Most frequent correspondents"

• For quantitative analyses

Args: year: Optional year filter min_letters: Minimum number of letters ctx: FastMCP Context

Returns: List of dicts with person_name, total, letters_sent, letters_received

Retrieve text passages from a specific document.

PURPOSE: Get actual text content from a document found via search

WHEN TO USE:

• After search returns relevant document IDs

• User wants to read specific sections

• Need actual quotes for citations

WHEN NOT TO USE:

• For discovery → use search_documents_direct()

• For full document → use get_document_by_id()

Args: document_id: The xml:id of the document query: Optional search term to highlight/filter passages division: Filter to specific div by @n value page: Filter to specific page by pb/@n context_size: Characters of context around matches max_passages: Maximum passages to return ctx: FastMCP Context

Returns: List of Passage objects with text and location info

Retrieve a specific diary entry by date.

PURPOSE: Access a specific day's entry from Schleiermacher's diary

Available years: 1808-1811, 1817, 1820-1834. Note: 1812-1816 and 1818-1819 are not extant.

WHEN TO USE:

• User asks for diary entry on specific date

• User wants to know what happened on a particular day

• After search → get full diary entry

WHEN NOT TO USE:

• For date range → use get_diary_entries()

• For keyword search → use search_in_documents()

Args: date: Date in ISO 8601 format (YYYY-MM-DD), e.g., "1808-01-01" ctx: FastMCP Context

Returns: Dictionary with date, content from left side, content from right side, and raw XML of the entry

Retrieve diary entries for a date range.

PURPOSE: Access multiple diary entries across a time period

Available years: 1808-1811, 1817, 1820-1834. Note: 1812-1816 and 1818-1819 are not extant.

WHEN TO USE:

• User asks for diary entries in a date range

• User wants to see activities over a period

• For temporal analysis of diary content

WHEN NOT TO USE:

• For single date → use get_diary_entry()

• For keyword search → use search_in_documents()

Args: date_from: Start date in ISO 8601 format (YYYY-MM-DD) date_to: End date in ISO 8601 format (YYYY-MM-DD) ctx: FastMCP Context

Returns: List of dictionaries, each with date, left_side, right_side content

Retrieve chronology entries for a specific date.

PURPOSE: Access events from Schleiermacher's life on a specific date

WHEN TO USE:

• User asks what happened on a specific date

• User wants biographical information for a particular day

• After search → get full chronology entry

WHEN NOT TO USE:

• For date range → use get_chronology_entries()

• For entire year → use get_chronology_year()

• For keyword search → use search_documents()

Args: date: Date in ISO 8601 format (YYYY-MM-DD), e.g., "1785-08-29" ctx: FastMCP Context

Returns: List of dictionaries with date info and event descriptions. Multiple events may occur on the same date.

Retrieve chronology entries for a date range.

PURPOSE: Access events from Schleiermacher's life across a time period

WHEN TO USE:

• User asks what happened during a specific period

• User wants biographical timeline for a date range

• For temporal analysis of Schleiermacher's life events

WHEN NOT TO USE:

• For single date → use get_chronology_entry()

• For entire year → use get_chronology_year()

• For keyword search → use search_documents()

Args: date_from: Start date in ISO 8601 format (YYYY-MM-DD) date_to: End date in ISO 8601 format (YYYY-MM-DD) ctx: FastMCP Context

Returns: List of dictionaries with date info and event descriptions, sorted chronologically. Includes both specific dates and date ranges that overlap with the query range.

Retrieve all chronology entries for a specific year.

PURPOSE: Access complete biographical timeline for a year in Schleiermacher's life

WHEN TO USE:

• User asks "What happened in 1785?"

• User wants overview of activities in a specific year

• For annual biographical summaries

WHEN NOT TO USE:

• For specific date → use get_chronology_entry()

• For date range spanning multiple years → use get_chronology_entries()

• For keyword search → use search_documents()

Args: year: Year (e.g., 1785) ctx: FastMCP Context

Returns: Dictionary with year, heading, and list of chronology entries. Entries are sorted chronologically within the year.

Browse files and subcollections in MoP.

PURPOSE: Überblick über verfügbare Dateien in der MoP-Edition

WHEN TO USE:

• User möchte sehen, was in der Edition verfügbar ist

• Exploration ohne konkreten Suchbegriff

WHEN NOT TO USE:

• Bei konkreter Suche → nutze search_documents()

• Für Metadaten → nutze get_document() danach

Args: collection: Collection-Name (Texte, Register) limit: Maximale Anzahl Dateien ctx: FastMCP Context für Progress

Returns: Dict mit 'files' und 'subcollections' Liste

Volltextsuche in MoP-Dokumenten.

PURPOSE: Dokumente finden, die einen bestimmten Begriff enthalten

WHEN TO USE:

• User sucht nach Person, Institution, Thema

• Explorative Suche zu höfischen Praktiken

WHEN NOT TO USE:

• Für strukturierte Registersuche → nutze search_register()

Args: keyword: Suchbegriff collection: Collection (Texte) max_results: Maximale Ergebnisse ctx: FastMCP Context

Returns: Liste von SearchResult-Objekten

Vollständiges Dokument abrufen.

PURPOSE: Detaillierte Ansicht eines spezifischen Dokuments

WHEN TO USE:

• User möchte ein Aktenstück lesen

• Nach erfolgreicher Suche → Details anzeigen

WHEN NOT TO USE:

• Für Übersicht → nutze browse_documents() oder search_documents()

Args: document_id: Die xml:id des Dokuments include_xml: Ob TEI-XML inkludiert werden soll ctx: FastMCP Context

Returns: Document-Objekt mit Metadaten und Content

Suche in MoP-Registern.

PURPOSE: Strukturierte Registereinträge finden

WHEN TO USE:

• User sucht nach Person, Ort, Institution, Hof

• Um IDs für weitere Suchen zu bekommen

WHEN NOT TO USE:

• Für Volltextsuche → nutze search_documents()

Args: query: Suchbegriff register_type: Register (personen, orte, institutionen, hoefe, werke, aemter) max_results: Maximale Ergebnisse ctx: FastMCP Context

Returns: Liste von Register-Einträgen mit id, name, type, gnd (optional)

Detailansicht eines Registereintrags.

PURPOSE: Vollständige Informationen zu Person, Ort, etc.

WHEN TO USE:

• Nach Registersuche für Details

• Für biographische/geographische Informationen

Args: entry_id: ID des Registereintrags register_type: Register-Typ ctx: FastMCP Context

Returns: Dict mit allen verfügbaren Informationen

Suche in MoP-Biogrammen (detaillierte Biografien).

PURPOSE: Detaillierte biografische Einträge finden

WHEN TO USE:

• User sucht nach Person für biografische Details

• Um Familienverhältnisse, Karriere, Besitztümer zu recherchieren

• Prosopographische Forschung zu Hofbeamten

WHEN NOT TO USE:

• Für einfache Registersuche → nutze search_register("personen")

• Für Volltextsuche in Dokumenten → nutze search_documents()

Args: query: Suchbegriff (Name) birth_year: Filter nach Geburtsjahr death_year: Filter nach Sterbejahr max_results: Maximale Ergebnisse ctx: FastMCP Context

Returns: Liste von Biogramm-Treffern mit id, name, birth, death, gnd

Vollständiges Biogramm mit allen Details abrufen.

PURPOSE: Detaillierte biografische Daten einer Person abrufen

WHEN TO USE:

• Nach search_biogramme() um Details zu bekommen

• Um Familiennetzwerk, Karriere, Besitz zu analysieren

• Für vollständige prosopographische Information

Args: biogramm_id: XML-ID des Biogramms (z.B. "P0005251") ctx: FastMCP Context

Returns: Dict mit allen biografischen Daten strukturiert

Familiennetzwerk aus einem Biogramm extrahieren.

PURPOSE: Verwandtschaftsbeziehungen analysieren

WHEN TO USE:

• Für genealogische Forschung

• Um höfische Netzwerke zu rekonstruieren

• Analyse von Familiendynastien am Hof

Args: biogramm_id: XML-ID des Biogramms ctx: FastMCP Context

Returns: Dict mit Familienrelationen strukturiert nach Typ

Fetch complete residential topography dataset for a specific year.

PURPOSE: Retrieve GeoJSON data with addresses and locations of court officials, royal family members, and other persons/institutions in Berlin and Prussia.

WHEN TO USE:

• User asks about where people lived in a specific year

• User wants to analyze residential patterns

• User needs geographic distribution of court members

• For mapping and spatial analysis

WHEN NOT TO USE:

• For biographical register data → use search_register()

• For document texts → use browse_documents() or search_documents()

Args: year: Year for which to retrieve data (1800, 1845, 1872, 1891, or 1914) ctx: FastMCP Context for progress reporting

Returns: Dict with: - year: The requested year - total_features: Total number of entries - features_with_coordinates: Number of entries with valid geographic coordinates - categories: Count of entries per category - cities: Count of entries per city - sample_features: First 10 features as examples - query_methods: Available search methods

Raises: ToolError: If year is not available or API request fails

Search residential topography data with multiple filters.

PURPOSE: Find persons/institutions by various criteria in historical address data.

WHEN TO USE:

• User searches for specific person by name

• User wants to know who lived at a specific address

• User wants to filter by profession, category, or location

• User needs to find all court members in a certain category

WHEN NOT TO USE:

• For biographical details → use get_register_entry()

• For full dataset overview → use get_residential_topography()

Args: year: Year for data (1800, 1845, 1872, 1891, or 1914) name: Last name (partial match, case-insensitive) vorname: First name (partial match, case-insensitive) kategorie: Category filter (e.g., "Königliche Familie", "Diplomatie") taetigkeit: Occupation/activity filter stadt: City filter (partial match) strasse: Street name filter (partial match) ediarum_id: Exact Ediarum-ID match only_with_coordinates: Return only entries with valid geographic coordinates max_results: Maximum number of results to return ctx: FastMCP Context

Returns: Dict with: - year: The queried year - filters_applied: List of active filters - total_matches: Number of matching entries - returned_results: Number of results in response (limited by max_results) - results: List of matching features

Raises: ToolError: If year is not available or no filters provided

List all available years for residential topography data.

PURPOSE: Show which years have Wohntopographie datasets available.

WHEN TO USE:

• User asks about available time periods

• User wants to know which years can be queried

• Before choosing a year for analysis

Returns: Dict with available years and description

Search in Adjutantenjournale (court adjutant journals).

PURPOSE: Find daily court journal entries documenting royal activities, audiences, meetings, and events. Each entry shows who was on duty and what happened.

WHEN TO USE:

• User asks "What did the king do on [date]?"

• User wants to know about daily court life

• User searches for specific events, persons, or places mentioned in journals

• User wants to track activities of a specific monarch

• User researches who served as adjutant when

WHEN NOT TO USE:

• For biographical data → use search_register()

• For correspondence → use letters search in Schleiermacher Digital

• For institutional documents → use browse_documents()

Args: query: Full-text search term (searches in journal text) monarch: Filter by monarch (Friedrich_Wilhelm_IV, Wilhelm_I, Wilhelm_II, Friedrich_III) date_from: Start date in ISO format (YYYY-MM-DD), e.g., "1861-01-01" date_to: End date in ISO format (YYYY-MM-DD), e.g., "1861-12-31" person_key: Filter by person mentioned (register key, e.g., "P0002157") place_key: Filter by place mentioned (register key, e.g., "P0003556") limit: Maximum number of results (default: 50) ctx: FastMCP Context for progress reporting

Returns: List of journal entries with: - id: Document ID - monarch: Which monarch's reign - date_from/date_to: Time range covered - place: Where the court was located - authors: Adjutants who wrote the entry - snippet: Text excerpt showing matched content - url: Link to full entry on website

Raises: ToolError: If monarch is invalid or query fails

Retrieve full text and metadata of a specific journal entry.

PURPOSE: Get complete details of a daily court journal entry.

WHEN TO USE:

• After finding entries with search_adjutanten_journals()

• User wants to read the full journal entry for a specific day

• User needs detailed information about activities on a specific date

WHEN NOT TO USE:

• For searching multiple entries → use search_adjutanten_journals()

• For biographical data → use get_register_entry()

Args: document_id: Document ID from search results (e.g., "P0005285") ctx: FastMCP Context for progress reporting

Returns: Dict with: - id: Document ID - monarch: Which monarch's reign - date_from/date_to: Time range covered - shelfmark: Archive reference - days: List of daily entries, each with: - date: ISO date - place: Location - authors: Adjutants on duty - text: Full journal text for that day - url: Link to online edition

Raises: ToolError: If document not found or retrieval fails

List all adjutants who served under a specific monarch.

PURPOSE: Identify who served as adjutant and when.

WHEN TO USE:

• User asks "Who served as adjutant under Wilhelm I?"

• User wants to know the rotation of adjutants

• User researches prosopography of court officials

WHEN NOT TO USE:

• For full biographical data → use search_register()

• For journal content → use search_adjutanten_journals()

Args: monarch: Monarch name (Friedrich_Wilhelm_IV, Wilhelm_I, Wilhelm_II, Friedrich_III) ctx: FastMCP Context for progress reporting

Returns: Dict with: - monarch: Monarch name - total_entries: Number of journal entries analyzed - adjutants: List of adjutants with: - name: Full name - person_key: Register ID - entries_count: How many times they wrote entries - date_range: First and last appearance

Raises: ToolError: If monarch is invalid or query fails

Check if the database is reachable and responsive.

PURPOSE: Verify database connectivity for troubleshooting.

WHEN TO USE:

• When other tools fail unexpectedly

• To verify setup is working

• Health monitoring

Returns: DatabaseStatus object with connection status, version, and paths

Execute a raw XQuery against the database.

PURPOSE: Run custom queries for advanced users or debugging.

WHEN TO USE:

• Other tools don't provide the needed functionality

• Debugging or exploring data structure

• Complex custom queries

WHEN NOT TO USE:

• For common operations, use specific tools instead

• Don't use for write operations (read-only!)

Args: query: XQuery string to execute max_results: Maximum number of results to return

Returns: Raw query result as string (usually XML)

Search for GND IDs by name using Lobid GND API.

PURPOSE: Find GND identifiers for persons, places, or corporate bodies.

WHEN TO USE:

• When you need a GND ID for correspSearch filtering

• To resolve person names to standard identifiers

• For enriching metadata with authority data

WHEN NOT TO USE:

• For full entity data → use get_gnd_entity() tools

• For non-GND authority data → use other services

Args: name_query: Name or term to search for (e.g., "Goethe", "Humboldt") limit: Maximum number of results to return

Returns: List of dicts with 'id' (GND URI) and 'label' for matching entities

Example: >>> results = await search_for_gnd_id("Wilhelm von Humboldt") >>> gnd_id = results[0]['id'].split('/')[-1] # Extract ID from URI >>> letters = await search_correspondences(person_gnd=gnd_id)

Search for GeoNames IDs by place name.

PURPOSE: Find GeoNames identifiers for places to use as filters.

WHEN TO USE:

• When you need a GeoNames ID for correspSearch place filtering

• To resolve place names to standard identifiers

• For geographic analysis of correspondence networks

WHEN NOT TO USE:

• For person or organization names → use search_for_gnd_id()

• When you already have a GeoNames ID

Args: place_query: Place name to search for (e.g., "Berlin", "Paris") country: Optional ISO-2 country code to restrict search (e.g., "DE", "FR") limit: Maximum number of results to return

Returns: List of dicts with place information: - geonameId: The GeoNames ID (use this for correspSearch) - name: Place name - countryCode: ISO-2 country code - lat, lng: Coordinates - adminName1: First-level admin division (e.g., state) - population: Population count (if available)

Example: >>> results = await search_for_geonames_id("Berlin", country="DE") >>> geonames_id = str(results[0]['geonameId']) >>> letters = await search_correspondences(place_geonames=geonames_id)

Get the GeoNames ID for a place (convenience function).

PURPOSE: Quick lookup of a single GeoNames ID for a place.

WHEN TO USE:

• When you just need the ID without details

• For quick place-to-ID conversion

• When you're confident about the place name

WHEN NOT TO USE:

• When the place name might be ambiguous → use search_for_geonames_id()

• When you need full place details

Args: place_name: Name of the place (e.g., "Berlin", "Paris") country: Optional ISO-2 country code to restrict search (e.g., "DE")

Returns: GeoNames ID as integer, or None if not found

Example: >>> berlin_id = await get_place_geonames_id("Berlin", country="DE") >>> # Returns: 2950159 >>> letters = await search_correspondences(place_geonames=str(berlin_id))

Search for occupation entities in Wikidata.

PURPOSE: Find Wikidata IDs for occupations to filter correspondence by profession.

WHEN TO USE:

• When you need a Wikidata ID for correspSearch occupation filtering

• To find letters by correspondent profession (writers, philosophers, etc.)

• For professional network analysis

WHEN NOT TO USE:

• For person names → use search_for_gnd_id()

• For places → use search_for_geonames_id()

• For non-occupation entities → use search_wikidata_entity()

Args: occupation_query: Occupation name to search for (e.g., "Dichter", "Philosoph", "Maler") limit: Maximum number of results to return

Returns: List of dicts with occupation entities: - id: Wikidata ID (e.g., "Q36180") - label: Occupation name in German - description: Brief description - uri: Full Wikidata URI

Example: >>> results = await search_for_wikidata_occupation("Schriftsteller") >>> occupation_id = results[0]['id'] # e.g., "Q36180" >>> letters = await search_correspondences(occupation_wikidata=occupation_id)

Search for any entity in Wikidata.

PURPOSE: General-purpose Wikidata entity search for various use cases.

WHEN TO USE:

• When searching for entities that aren't occupations

• For broader Wikidata lookups

• When you need flexibility in entity type

WHEN NOT TO USE:

• Specifically for occupations → use search_for_wikidata_occupation()

• For GND/GeoNames data → use respective tools

Args: query: Search term for any Wikidata entity limit: Maximum number of results to return language: Language code for labels (default: "de")

Returns: List of dicts with entity information: - id: Wikidata ID (e.g., "Q36180") - label: Entity name - description: Brief description - uri: Full Wikidata URI

Example: >>> results = await search_wikidata_entity("Aufklärung") >>> entity_id = results[0]['id']

Cross-Edition Briefsuche über correspSearch API.

PURPOSE: Briefe über Edition-Grenzen hinweg finden

WHEN TO USE:

• User möchte Briefe in ALLEN Editionen finden

• Cross-Referenzierung zwischen Editionen

• Für umfassende Korrespondenz-Netzwerk-Analyse

• Suche nach Korrespondenz einer historischen Person

WHEN NOT TO USE:

• Für schleiermacher-spezifische Suche → nutze sd_search_letters()

Args: person_gnd: GND-ID(s) - einzelne ID oder Liste (z.B. "118540238" oder ["118540238", "118607626"]) person_viaf: VIAF-ID(s) - einzelne ID oder Liste (alternativ zu GND) start_date: Start-Datum (ISO 8601, z.B. "1810-01-01") end_date: End-Datum (ISO 8601, z.B. "1815-12-31") place_geonames: GeoNames-ID eines Ortes (z.B. "2879139" für Leipzig) occupation_wikidata: Wikidata-ID eines Berufs (z.B. "Q36180" für Schriftsteller) edition_id: UUID einer Edition zur Filterung cmif_url: URL einer CMIF-Datei (z.B. "https://gams.uni-graz.at/context:hsa/CMIF") availability: "online", "print" oder "hybrid" text_query: Volltextsuche in Briefinhalten (experimentell, undokumentiert) gender: "male" (männlich), "female" (weiblich), oder "unknown" (unbekannt) role: "sent" (nur als Absender), "received" (nur als Empfänger), oder "mentioned" (nur erwähnt) place_role: "sent" (Schreibort) oder "received" (Empfangsort) page: Seite der Ergebnisse (1-indiziert, je 100 Treffer) max_results: Maximale Ergebnisse (zur Anzeige-Begrenzung) ctx: FastMCP Context

Returns: CorrespSearchResult mit Briefen und Paginierungs-Info

Note: Mehrere Personen (Liste) werden mit AND kombiniert - findet nur Briefe, die ALLE angegebenen Personen enthalten.

Informationen über eine Edition in correspSearch abrufen.

PURPOSE: Metadaten zu registrierten Editionen

WHEN TO USE:

• User fragt nach verfügbaren Editionen

• Für Edition-Discovery

• Um die Quelle von gefundenen Briefen zu identifizieren

Args: edition_id: Edition-UUID in correspSearch ctx: FastMCP Context

Returns: EditionInfo mit Metadaten zur Edition

Korrespondenz-Netzwerk einer Person analysieren.

PURPOSE: Netzwerkanalyse von Korrespondenzen

WHEN TO USE:

• User fragt "Mit wem korrespondierte Person X?"

• Netzwerk-Visualisierung vorbereiten

• Wichtigste Korrespondenzpartner identifizieren

Args: person_gnd: GND-ID der fokalen Person start_date: Optional: Start-Datum für Zeitfilter end_date: Optional: End-Datum für Zeitfilter max_correspondents: Maximale Anzahl Korrespondenten im Ergebnis max_letters_to_analyze: Maximale Anzahl Briefe zu analysieren (pro Richtung) ctx: FastMCP Context

Returns: Dict mit Netzwerk-Statistiken und Top-Korrespondenten