Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.
OpenCidian: open Chinese ↔ Vietnamese dictionary is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Open Chinese-Vietnamese dictionary by Perxel: Hán Việt, pinyin, meanings, characters. Cited.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http opencidian-open-chinese-vietnamese-dictionary-mcp https://opencidian-mcp.perxel.com/mcp
# 2 — ask your agent for something these tools do
# lookup, get_character, words_with and 4 more
OpenCidian: open Chinese ↔ Vietnamese dictionary costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http opencidian-open-chinese-vietnamese-dictionary-mcp https://opencidian-mcp.perxel.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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 Vietnam
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Chinese characters (觉得, 覺得), pinyin with or without tones (jué de, jue2 de5, jue de) or Vietnamese (cảm thấy). |
| by | string | no | Force how q is read. Leave out to let the server tell hanzi, pinyin and Vietnamese apart. |
| limit | integer | no | Entries to return, 1-50 (default 10). |
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 w
| Parameter | Type | Required | Notes |
|---|---|---|---|
| char | string | yes | One Chinese character, simplified or traditional (觉 or 覺). |
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 | Required | Notes |
|---|---|---|---|
| char | string | yes | One Chinese character, simplified or traditional (觉 or 覺). |
| limit | integer | no | Words to return, 1-100 (default 20). |
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 | Required | Notes |
|---|---|---|---|
| meaning | string | yes | A meaning to find Chinese words for, in Vietnamese (cảm thấy, with or without diacritics) or English (to feel). |
| lang | string | no | The language of meaning: vi (default) or en. |
| limit | integer | no | Entries to return, 1-50 (default 10). |
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 dict
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Chinese text, up to 2000 characters: a sentence, a lesson's dialogue, a sign. |
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| word | string | yes | The word or character the fix is for, in hanzi (说, 觉得). |
| pinyin | string | no | The pinyin, only when the fix is for one reading of the word (觉 jiào, not jué). |
| field | string | yes | What is wrong: hanviet (Hán Việt reading), vi (Vietnamese meaning), en (English), pinyin, missing (a word the dictionary lacks), other. |
| current | string | no | The value OpenCidian gives now, copied from a lookup. |
| suggested | string | yes | The value it should be. |
| evidence | string | yes | Where the right value comes from: a dictionary (Thiều Chửu, hvdic.thivien.net, a textbook) with a page or link. Not your own guess. |
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 parameter schema on file.
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install OpenCidian: open Chinese ↔ Vietnamese dictionary or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| lookup | no tags | |
| get_character | no tags | |
| words_with | no tags | |
| search_meaning | no tags | |
| annotate_text | no tags | |
| suggest_correction | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| about | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 0.3.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish OpenCidian: open Chinese ↔ Vietnamese dictionary can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.