OpenCidian: open Chinese ↔ Vietnamese dictionary (Hán Việt, pinyin, character br is an MCP server published by io.github.OpenCidian, hosted at opencidian-mcp.perxel.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 7 tools, including lookup, get_character, words_with, search_meaning, annotate_text.
Open Chinese-Vietnamese dictionary by Perxel: Hán Việt, pinyin, meanings, characters. Cited.
Nothing else in the archive shares these values.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| q * | string | Chinese characters (觉得, 覺得), pinyin with or without tones (jué de, jue2 de5, jue de) or Vietnamese (cảm thấy). |
| by | string | Force how q is read. Leave out to let the server tell hanzi, pinyin and Vietnamese apart. |
| limit | integer |
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
| Entries to return, 1-50 (default 10). |
{
"name": "lookup",
"title": "Look up a Chinese word",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"q"
],
"properties": {
"q": {
"type": "string",
"maxLength": 100,
"minLength": 1,
"description": "Chinese characters (觉得, 覺得), pinyin with or without tones (jué de, jue2 de5, jue de) or Vietnamese (cảm thấy)."
},
"by": {
"enum": [
"hanzi",
"pinyin",
"vi"
],
"type": "string",
"description": "Force how q is read. Leave out to let the server tell hanzi, pinyin and Vietnamese apart."
},
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Entries to return, 1-50 (default 10)."
}
}
},
"annotations": {
"readOnlyHint": true
}
}Everything known about one character: Hán Việt readings (Thiều Chửu first, Unihan when Thiều Chửu has none), pinyin readings, a short English gloss, stroke count, radical, its parts (decomposition) and how it was formed (etymology: the meaning part and the sound part, each with its Hán Việt), and its traditional or simplified forms. Every field carries `src`. For the words a character is in, use words_with; for a character used as a word, lookup.
| Parameter | Type | Description |
|---|---|---|
| char * | string | One Chinese character, simplified or traditional (觉 or 覺). |
{
"name": "get_character",
"title": "One Chinese character",
"description": "Everything known about one character: Hán Việt readings (Thiều Chửu first, Unihan when Thiều Chửu has none), pinyin readings, a short English gloss, stroke count, radical, its parts (decomposition) and how it was formed (etymology: the meaning part and the sound part, each with its Hán Việt), and its traditional or simplified forms. Every field carries `src`. For the words a character is in, use words_with; for a character used as a word, lookup.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"char"
],
"properties": {
"char": {
"type": "string",
"pattern": "^\\p{Script=Han}$",
"description": "One Chinese character, simplified or traditional (觉 or 覺)."
}
}
},
"annotations": {
"readOnlyHint": true
}
}Words of two characters or more that contain a character (simplified or traditional), HSK words first, then shorter words. Each comes as a full entry: pinyin, Hán Việt, Vietnamese and English senses, HSK level, `src` per field.
| Parameter | Type | Description |
|---|---|---|
| char * | string | One Chinese character, simplified or traditional (觉 or 覺). |
| limit | integer | Words to return, 1-100 (default 20). |
{
"name": "words_with",
"title": "Words that contain a character",
"description": "Words of two characters or more that contain a character (simplified or traditional), HSK words first, then shorter words. Each comes as a full entry: pinyin, Hán Việt, Vietnamese and English senses, HSK level, `src` per field.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"char"
],
"properties": {
"char": {
"type": "string",
"pattern": "^\\p{Script=Han}$",
"description": "One Chinese character, simplified or traditional (觉 or 覺)."
},
"limit": {
"type": "integer",
"maximum": 100,
"minimum": 1,
"description": "Words to return, 1-100 (default 20)."
}
}
},
"annotations": {
"readOnlyHint": true
}
}Vietnamese or English → Chinese: entries whose Vietnamese (CVDICT) or English (CC-CEDICT) senses match the meaning, HSK words first. These are candidates, not one translation: compare their senses and HSK levels before picking one, and say when several fit.
| Parameter | Type | Description |
|---|---|---|
| lang | string | The language of `meaning`: vi (default) or en. |
| limit | integer | Entries to return, 1-50 (default 10). |
| meaning * | string | A meaning to find Chinese words for, in Vietnamese (cảm thấy, with or without diacritics) or English (to feel). |
{
"name": "search_meaning",
"title": "Chinese words for a meaning",
"description": "Vietnamese or English → Chinese: entries whose Vietnamese (CVDICT) or English (CC-CEDICT) senses match the meaning, HSK words first. These are candidates, not one translation: compare their senses and HSK levels before picking one, and say when several fit.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"meaning"
],
"properties": {
"lang": {
"enum": [
"vi",
"en"
],
"type": "string",
"description": "The language of `meaning`: vi (default) or en."
},
"limit": {
"type": "integer",
"maximum": 50,
"minimum": 1,
"description": "Entries to return, 1-50 (default 10)."
},
"meaning": {
"type": "string",
"maxLength": 100,
"minLength": 1,
"description": "A meaning to find Chinese words for, in Vietnamese (cảm thấy, with or without diacritics) or English (to feel)."
}
}
},
"annotations": {
"readOnlyHint": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| text * | string | Chinese text, up to 2000 characters: a sentence, a lesson's dialogue, a sign. |
{
"name": "annotate_text",
"title": "Annotate a Chinese text",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "Chinese text, up to 2000 characters: a sentence, a lesson's dialogue, a sign."
}
}
},
"annotations": {
"readOnlyHint": true
}
}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.
| Parameter | Type | Description |
|---|---|---|
| word * | string | The word or character the fix is for, in hanzi (说, 觉得). |
| field * | string | What is wrong: hanviet (Hán Việt reading), vi (Vietnamese meaning), en (English), pinyin, missing (a word the dictionary lacks), other. |
| pinyin | string | The pinyin, only when the fix is for one reading of the word (觉 jiào, not jué). |
| current | string | The value OpenCidian gives now, copied from a lookup. |
| evidence * | string | Where the right value comes from: a dictionary (Thiều Chửu, hvdic.thivien.net, a textbook) with a page or link. Not your own guess. |
| suggested * | string | The value it should be. |
{
"name": "suggest_correction",
"title": "Suggest a correction",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"word",
"field",
"suggested",
"evidence"
],
"properties": {
"word": {
"type": "string",
"maxLength": 40,
"minLength": 1,
"description": "The word or character the fix is for, in hanzi (说, 觉得)."
},
"field": {
"enum": [
"hanviet",
"vi",
"en",
"pinyin",
"missing",
"other"
],
"type": "string",
"description": "What is wrong: hanviet (Hán Việt reading), vi (Vietnamese meaning), en (English), pinyin, missing (a word the dictionary lacks), other."
},
"pinyin": {
"type": "string",
"maxLength": 60,
"description": "The pinyin, only when the fix is for one reading of the word (觉 jiào, not jué)."
},
"current": {
"type": "string",
"maxLength": 2000,
"description": "The value OpenCidian gives now, copied from a lookup."
},
"evidence": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "Where the right value comes from: a dictionary (Thiều Chửu, hvdic.thivien.net, a textbook) with a page or link. Not your own guess."
},
"suggested": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"description": "The value it should be."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true
}
}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.
No parameters.
{
"name": "about",
"title": "About OpenCidian's data",
"description": "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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {}
},
"annotations": {
"readOnlyHint": true
}
}OpenCidian: a Chinese-Vietnamese dictionary. Use it for a word's pinyin, Hán Việt or Vietnamese meaning instead of guessing. lookup takes hanzi, pinyin or Vietnamese; search_meaning finds Chinese words for a Vietnamese or English meaning; get_character for one character's readings and parts; words_with for words that contain a character; annotate_text for a whole sentence. Every field has `src`: say which source a value comes from when it matters. `vi: null` means the dictionary has no Vietnamese for that word, and no entries means the word isn't in it: say so rather than make one up. Hán Việt is given per character; a word's reading joins them and can be irregular. If a value is wrong and the user wants it fixed, suggest_correction sends it for review (with evidence, never a guess).
Names, descriptions and schemas were written by the server and are shown as data.