# Latin dictionary access

> A grounding service over the English Wiktionary's Latin entries and the Morpheus
> morphological analyzer. Use it to read and write Latin with attested words and
> correct inflected forms instead of inventing them. Read-only.

## What it does
- Looks a Latin word up (any form — macrons optional) and returns its senses plus
  full declension/conjugation tables.
- Resolves an inflected query to its dictionary lemma automatically: first via
  paradigms already cached, then via the Morpheus analyzer — the result says so
  (search_method=lemma_index|morpheus, with resolved_from/resolved_lemma).
- Returns raw morphological analyses (person, number, tense, mood, voice, case)
  for any one form via lemmatize.

## How to connect (MCP)
Remote streamable-HTTP endpoint (no auth, read-only): https://latin.valksor.com/mcp
  Claude Code:  claude mcp add --transport http latin https://latin.valksor.com/mcp
  Cursor / Cline (~/.cursor/mcp.json):
    {"mcpServers": {"latin": {"url": "https://latin.valksor.com/mcp"}}}
  stdio-only clients — bridge with mcp-remote:
    {"mcpServers": {"latin": {"command": "npx",
       "args": ["-y", "mcp-remote", "https://latin.valksor.com/mcp"]}}}
Tools (each returns Markdown plus typed structuredContent per its outputSchema):
- search_latin(query, include_forms=true, max_forms=N)
    Senses plus inflection handles (vards_id = the lemma/page title, word_class =
    the part-of-speech section). With include_forms (default TRUE on MCP; the JSON
    API defaults it false), each match's full table comes back inline.
- get_inflections(vards_id, word_class)
    The full paradigm for one handle. Its structuredContent nests the paradigm
    under a "result" key (the other tools' payloads are unwrapped); the JSON API
    returns it directly. Both shapes are discriminated by "category":
    nominal gives cases -> {singular, plural}; verbal gives finite
    "<voice> <mood> <tense>" -> person -> form plus non-finite sections
    (infinitive, participle, gerund, supine); "not_found" when no table exists.
- lemmatize_latin(word)
    Morpheus analyses of one inflected form: lemma(s) + grammatical tags.
Search tips: one word per call; any form of the word works; macrons optional.

## How to call (JSON API)
- GET https://latin.valksor.com/api/search?query=aqua
- GET https://latin.valksor.com/api/inflections?vards_id=amo&word_class=verb
- GET https://latin.valksor.com/api/lemmatize?word=amavit
- GET https://latin.valksor.com/api/health
- Interactive docs: https://latin.valksor.com/api/docs  ·  schema: https://latin.valksor.com/api/openapi.json

## Caching and politeness
Dictionary responses are cached server-side with a long TTL (Wiktionary content
changes slowly); Morpheus analyses are cached permanently. Upstream calls are
serialised with a polite minimum interval per site. Calls are rate limited per
client IP — on a 429, wait a few seconds and retry.

## Source and licence
- Dictionary: Wiktionary, the free dictionary (en.wiktionary.org), Latin entries. Wikimedia Foundation. Text available under CC BY-SA 4.0; attribution and share-alike required when republishing.
- Morphology: Morpheus morphological analyses via the Perseids Project morphology service (morph.perseids.org), Tufts University / Perseus Digital Library.
- Licence: CC BY-SA 4.0 — attribute and share alike when republishing dictionary text.