livonian

An MCP server and JSON API over the real https://livonian.tech dictionary — so LLMs translate to and from Livonian with attested words and grammatical forms, not invented ones. Read-only.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://livonian--valksor.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "livonian": {
      "url": "https://livonian--valksor.run.tools"
    }
  }
}

能力清单

工具	说明
search_livonian	Look a word up in the real Livonian–Estonian–Latvian dictionary and return only attested content, so translations are grounded, not invented. Search the meaning you want (in English/Latvian/Estonian) to find the Livonian headword, or search a Livonian word to confirm it exists and check its sense, part of speech and usage examples. `search_language` selects the language your QUERY is in (default 'eng'); leave it at 'eng' for English→Livonian. By default this also returns each match's full INFLECTION TABLE inline, so you get the correct cases/tenses for writing (lyrics, verse, prose) in a single call — no separate get_inflections round-trip. For a broad query that matches many words, only the first N tables are expanded (a note says how many were left out); narrow the query or set `max_forms`. Returns Markdown: the handles table, the inline inflection tables, and the entries.
get_inflections	Fetch the full declension (nouns) or conjugation (verbs) table for a word identified by a search result's inflection handle. This keeps the correct grammatical FORM — the right case, number, tense — instead of a guessed ending. Returns a Markdown table, or a clean not-found message.
romanize_livonian	Strip Livonian orthography down to clean, pronounceable ASCII. Strips macrons, diacritics and capitals, maps each special letter to an English-readable spelling (ā→aa, š→sh, õ→u), softens a palatalized consonant (ņ ļ ŗ ţ ḑ) only before a vowel (ņ+a→nya, else plain so ikšiggiņ→ikshiggin, since a word-edge "ny" would be mis-sung as a diphthong), and inserts a hyphen where an English voice would otherwise blur two sounds into one: the broken tone (stød), splitting a doubled consonant the way the syllable breaks (si'zzõl→siz-zul), and a long vowel before another vowel so a diphthong keeps its glide (kīen→kee-en). An English-trained downstream — a voice/TTS, a search box — then approximates the word instead of choking on the orthography. Pure transform: no dictionary lookup, no network, and the output is always ASCII.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。