Open Chinese-Vietnamese dictionary by Perxel: Hán Việt, pinyin, meanings, characters. Cited.
Scored across 7 tools
Each tool has a clearly separate job: metadata (about), text segmentation (annotate_text), single-character detail (get_character), entry lookup (lookup), reverse Vietnamese/English search (search_meaning), compound listing (words_with), and feedback (suggest_correction). The only potential overlap, get_character vs lookup for a single character, is explicitly resolved in the description ('for a character used as a word, use lookup'), and the descriptions cross-reference each other where relevant.
Four tools use a clear verb_noun pattern (get_character, annotate_text, search_meaning, suggest_correction), but three are bare nouns or verbs with no object (about, lookup, words_with). The mix is still readable and lookup/words_with are natural dictionary-domain names, but the convention is not uniform.
Seven tools is well-matched to a dictionary server: one lookup path, one reverse-search path, character analysis, text annotation, compound listing, provenance, and correction reporting, with no filler. Nothing feels redundant or missing from the count itself.
The surface covers the core lifecycle: Chinese→Vietnamese/English lookup, English/Vietnamese→Chinese search, per-character decomposition, text annotation, compound discovery, provenance, and error reporting. Minor gaps remain, such as no dedicated simplified↔traditional conversion tool, no browse/list by HSK level or radical, and no way to read the status of a submitted correction beyond the initial issue link.
The dataset's version and build date, its licence (CC BY-SA 4.0), the full attribution to quote when reusing it, and every source with its pinned version and licence (CC-CEDICT, CVDICT, Thiều Chửu, Unihan, Make Me a Hanzi, the HSK lists). Use it to say where an answer comes from or how to cite OpenCidian.
Inputs: no named parameters.
Splits Chinese text into words (longest match against the dictionary) and gives each its pinyin, Hán Việt per character, Vietnamese and English senses and entry id. kind is word, unknown (Chinese not in the dictionary: say so) or other (punctuation, Latin, digits). otherReadings > 0 means the word has more readings than the one shown: look it up when the reading matters. The split is by dictionary match, not grammar, and can be wrong (哪国人 comes out 哪 + 国人): check a split that changes the meaning.
Inputs: text (required).
Everything known about one character: Hán Việt readings (Thiều Chửu first, Unihan when Thiều Chửu has none), pinyin readings, a short English gloss, stroke count, radical, its parts (decomposition) and how it was formed (etymology: the meaning part and the sound part, each with its Hán Việt), and its traditional or simplified forms. Every field carries src. For the words a character is in, use words_with; for a character used as a word, lookup.
Inputs: char (required).
Dictionary entries for a Chinese word, a pinyin syllable or a Vietnamese word: simplified and traditional forms, pinyin, Hán Việt per character (Thiều Chửu), Vietnamese senses (CVDICT), English senses (CC-CEDICT), HSK level. Every field carries src, the source it came from. kinds says how the query was read and each entry's match which reading found it. vi: null means CVDICT has no Vietnamese for that word: say so, don't translate the English as if it were the dictionary's. No entries means the word isn't in the dictionary: say so, don't guess.
Inputs: q (required), by, limit.
Vietnamese or English → Chinese: entries whose Vietnamese (CVDICT) or English (CC-CEDICT) senses match the meaning, HSK words first. These are candidates, not one translation: compare their senses and HSK levels before picking one, and say when several fit.
Inputs: meaning (required), lang, limit.
Sends a correction for a wrong or missing value (Hán Việt, Vietnamese meaning, English, pinyin, a missing word) as a public GitHub issue in OpenCidian/opencidian-data; a maintainer reviews it, nothing changes in the data until then. Returns the issue number and link. Only use it when the user asks to report a mistake or agrees to, with evidence from a dictionary or textbook, never for a guess. The issue is public: put no personal details in it. A few per minute for all callers together.
Inputs: word (required), field (required), evidence (required), suggested (required), +2 more.
Words of two characters or more that contain a character (simplified or traditional), HSK words first, then shorter words. Each comes as a full entry: pinyin, Hán Việt, Vietnamese and English senses, HSK level, src per field.
Inputs: char (required), limit.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Vietnamese Chữ Nôm & Hán: lookup, search, conversion, and original Đại Nam Quấc âm tự vị entries.
Chinese dictionary, pinyin, stroke order, HSK quiz words and your HanyuGuide study lists.
Chinese dictionary (124k entries), HSK levels, text segmentation and 195 grammar points.
MCP server for Chinese dictionary lookup: character definitions, pinyin, stroke order and word
Add one secure layer between your agents and this server.
