# Lingard Vocab (remote · lingard.app)

Build and enrich your Lingard vocabulary: topic collections, flashcards, translations, examples.

- Trust score: 82/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `lingard.app`: 82/100 (this document), [markdown](https://verifymcp.io/servers/app-lingard-vocab/lingard.md), [page](https://verifymcp.io/servers/app-lingard-vocab/lingard)

## Channel facts

- Endpoint: `https://lingard.app/mcp`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.5.8`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 97/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3014 tokens (~137/item across 22 items; 15 tools + 7 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 20/100
  - Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 83/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 42% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Lingard Vocab MCP server?

Lingard Vocab is a hosted endpoint at https://lingard.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http app-lingard-vocab 'https://lingard.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "app-lingard-vocab": {
      "url": "https://lingard.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "app-lingard-vocab": {
      "type": "http",
      "url": "https://lingard.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.app-lingard-vocab]
url = "https://lingard.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "app-lingard-vocab": {
      "type": "remote",
      "url": "https://lingard.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add app-lingard-vocab --url 'https://lingard.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  app-lingard-vocab:
    url: "https://lingard.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "app-lingard-vocab": {
      "Transport": "http",
      "Url": "https://lingard.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add app-lingard-vocab -t streamable-http -u 'https://lingard.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "app-lingard-vocab": {
      "type": "http",
      "url": "https://lingard.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 82, +2)

No change was recorded against any check on this day. Endpoint Security went from 94 to 97. Other categories moved too: Stability & Change Management rose 3.

### 2026-11-04 (score 80, −1)

No change was recorded against any check on this day. Endpoint Security went from 97 to 94. Other categories moved too: Stability & Change Management rose 4.

### 2026-11-02 (score 81, +2)

No change was recorded against any check on this day. Endpoint Security went from 94 to 97. Other categories moved too: Stability & Change Management rose 3.

### 2026-11-01 (score 79, −1)

- [security] First check of Authorization: partial

### 2026-10-31 (score 80, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-30 (score 79)

First indexed and scored.

## MCP tools (15)

### `search` (~123 tokens)

Search Lingard Vocab

Searches the user's live Lingard account: vocabulary, learning context, English profile, totals, collection titles, saved words, flashcards, and missing vocabulary fields. Results are read from Firestore at the time of the call.

Input parameters:

- `q` (string): Alias for query.
- `query` (string): Search query, for example "English learning context" or "saved vocabulary collections".
- `targetLang` (string): Lingard target language code such as en, de, es, fr, it, pl, or pt. Defaults to en when the prompt asks about English.

Output parameters:

- `results` (array)

### `fetch` (~173 tokens)

Fetch Lingard Vocab Record

Fetches the full live Lingard JSON record for a search-result id (e.g. "learning-context:en") or a Lingard resource URI such as lingard://learning-context/en.

Input parameters:

- `id` (string): Preferred selector: a search-result id, e.g. "learning-context:en". Takes `id` OR `uri` (not both); if both are given, `id` wins.
- `targetLang` (string): Fallback used only when neither `id` nor `uri` is provided: a language code (en, de, es, fr, it, pl, pt) whose learning context to fetch.
- `uri` (string): Alternative selector, used only when `id` is omitted: a Lingard resource URI, e.g. "lingard://learning-context/en".

Output parameters:

- `data` (object)
- `id` (string)
- `text` (string)
- `title` (string)
- `uri` (string)

### `lingard_get_learning_context` (~192 tokens)

Get Lingard Learning Context

Returns the user's current Lingard learning context, read live from their account: English profile, vocabulary totals, saved collections and their titles, card counts, and missing-field stats. Earlier answers in the conversation may be out of date; this is the account as it stands now. The list covers every collection the account has, so the per-collection counts add up to the card total (totals.truncated marks a library too large to list in full). Every collection reports `source`: "user" (made by the user), "catalog" (a curated Lingard collection — read-only, its words come from the Lingard catalog) and "unfiled" (the bucket of cards saved while reading, which belong to no collection). Catalog and unfiled entries carry titles the user did not choose; they belong to the same account all the same.

Input parameters:

- `targetLang` (string, required)

Output parameters:

- `collections` (array)
- `notes` (array)
- `ok` (boolean)
- `profile` (object)
- `targetLang` (string)
- `totals` (object)

### `lingard_get_vocab_collection` (~184 tokens)

Get Lingard Vocabulary Collection

Returns live cards from one Lingard vocabulary collection by UUID or title, including curated Lingard collections and the "Words not in a collection" bucket of cards saved while reading. With includeExamples:true it also returns each card's example sentences and their translations, which editing examples starts from.

Input parameters:

- `collectionTitle` (string): Collection selector (alternative to `collectionUuid`): the collection title.
- `collectionUuid` (string): Collection selector (preferred): its UUID. One of `collectionUuid` or `collectionTitle` is required.
- `includeExamples` (boolean): Default false. True returns the full example rows (`examples`: example text, translation line, enabled flag) for every card instead of just the `exampleCount`.
- `limit` (integer): Optional max number of cards to return (1–1000).
- `targetLang` (string, required)

Output parameters:

- `cards` (array)
- `collection` (object)
- `hint` (string)
- `note` (string)
- `ok` (boolean)
- `targetLang` (string)

### `lingard_get_collection_gaps` (~186 tokens)

Get Lingard Collection Gaps

Returns live Lingard cards in a collection that are missing requested fields such as translation, POS, pronunciation, examples, or image. A curated Lingard collection always reports zero gaps: its words come from the Lingard catalog and are not the user's to fill.

Input parameters:

- `collectionTitle` (string): Collection selector (alternative to `collectionUuid`): the collection title.
- `collectionUuid` (string): Collection selector: its UUID. One of `collectionUuid` or `collectionTitle` is required (UUID wins if both are given).
- `fields` (array): Optional. An ARRAY of field-name strings, not a bare string: e.g. ["translation"] for one field or ["translation","image"] for several. Returns cards missing ANY listed field; without it every field…
- `limit` (integer)
- `targetLang` (string, required)

Output parameters:

- `cards` (array)
- `collection` (object)
- `ok` (boolean)
- `requestedFields` (array)
- `summary` (object)
- `targetLang` (string)

### `lingard_get_word_suggestion_context` (~100 tokens)

Get Lingard Word Suggestion Context

Returns live Lingard profile level, topic, collection context, and the words the user already has: the context for suggesting level-appropriate new cards that are not duplicates.

Input parameters:

- `collectionTitle` (string)
- `collectionUuid` (string)
- `count` (integer)
- `excludeLimit` (integer)
- `level` (string)
- `targetLang` (string, required)
- `topic` (string)

Output parameters:

- `collection`
- `exclusions` (object)
- `guidance` (object)
- `level`
- `nativeLang`
- `ok` (boolean)
- `requestedCount` (integer)
- `targetLang` (string)
- `topic`
- `wordRank`

### `lingard_preview_vocab_changes` (~151 tokens)

Preview Lingard Vocabulary Changes

Previews a Lingard vocabulary collection/card change without writing to Firestore. Cards are checked as on commit. Unless allowIncompleteCards is true, a new card needs title, translate, pos, pron/ipa, syns, and examples with translations; image is optional. A German or Romance noun title carries its dictionary article when one is used, e.g. der Hund, die Reise, das Haus. In example text and example translation the target word and the translated word are marked with {}. form is not part of speech: it holds the inflected-form category of the current word and stays empty for base forms.

Input parameters:

- `change` (object, required)
- `targetLang` (string, required)

Output parameters:

- `changes` (object)
- `collection` (object)
- `committed` (boolean)
- `mergeMode` (string)
- `ok` (boolean)
- `payload` (object)
- `summary` (object)
- `targetLang` (string)
- `upsertResult`

### `lingard_commit_vocab_changes` (~187 tokens)

Commit Lingard Vocabulary Changes

Commits a previously previewed or freshly supplied Lingard vocabulary change. Unless allowIncompleteCards is true, a new card needs title, translate, pos, pron/ipa, syns, and examples with translations; image is optional. A German or Romance noun title carries its dictionary article when one is used, e.g. der Hund, die Reise, das Haus. In example text and example translation the target word and the translated word are marked with {}. form is not part of speech: it holds the inflected-form category of the current word and stays empty for base forms. This is the tool that corrects existing cards: mergeMode:"overwrite_non_empty" replaces values that are already filled in and clearFields:["form"] clears a wrong grammatical form, which is why it is marked destructive.

Input parameters:

- `change` (object, required)
- `targetLang` (string, required)

Output parameters:

- `changes` (object)
- `collection` (object)
- `committed` (boolean)
- `mergeMode` (string)
- `ok` (boolean)
- `payload` (object)
- `summary` (object)
- `targetLang` (string)
- `upsertResult`

### `lingard_create_vocab_collection` (~245 tokens)

Create Lingard Vocabulary Collection

Creates a Lingard vocabulary collection, optionally with initial cards; commit=true writes it. Unless allowIncompleteCards is true, a new card needs title, translate, pos, pron/ipa, syns, and examples with translations; image is optional. A German or Romance noun title carries its dictionary article when one is used, e.g. der Hund, die Reise, das Haus. In example text and example translation the target word and the translated word are marked with {}. form is not part of speech: it holds the inflected-form category of the current word and stays empty for base forms.

Input parameters:

- `allowIncompleteCards` (boolean): Default false. True marks the cards as a sparse import that the user asked for; it lets them through without the complete-card fields (everything except image, the dictionary article on a German/Roma…
- `cards` (array)
- `collectionTitle` (string, required)
- `color` (string)
- `commit` (boolean)
- `icon` (string)
- `pic` (string)
- `targetLang` (string, required)
- `topic` (string)

Output parameters:

- `changes` (object)
- `collection` (object)
- `committed` (boolean)
- `mergeMode` (string)
- `ok` (boolean)
- `payload` (object)
- `summary` (object)
- `targetLang` (string)
- `upsertResult`

### `lingard_add_words_to_collection` (~348 tokens)

Add Lingard Words To Collection

Adds cards to an existing Lingard collection, deduplicating by normalized word title; commit=true writes them. Only collections with writable="full" accept new cards: curated Lingard collections are read-only and the unfiled bucket takes no new cards. Unless allowIncompleteCards is true, a new card needs title, translate, pos, pron/ipa, syns, and examples with translations; image is optional. A German or Romance noun title carries its dictionary article when one is used, e.g. der Hund, die Reise, das Haus. In example text and example translation the target word and the translated word are marked with {}. form is not part of speech: it holds the inflected-form category of the current word and stays empty for base forms. It only adds: a word already in the collection gets its empty fields filled (mergeMode "fill_missing", the default) or is left alone ("add_only"); a value that is already filled in is never changed or cleared.

Input parameters:

- `allowIncompleteCards` (boolean): Default false. True marks the cards as a sparse import that the user asked for; it lets them through without the complete-card fields (everything except image, the dictionary article on a German/Roma…
- `cards` (array, required)
- `collectionTitle` (string)
- `collectionUuid` (string)
- `commit` (boolean)
- `mergeMode` (string): What to do with a word that is already in the collection: "fill_missing" (default) fills its empty fields, "add_only" leaves it as it is.
- `targetLang` (string, required)

Output parameters:

- `changes` (object)
- `collection` (object)
- `committed` (boolean)
- `mergeMode` (string)
- `ok` (boolean)
- `payload` (object)
- `summary` (object)
- `targetLang` (string)
- `upsertResult`

### `lingard_fill_missing_card_fields` (~113 tokens)

Fill Missing Lingard Card Fields

Fills empty fields on existing Lingard cards. It never overwrites or clears a field that already has a value. Works on the user's own collections and on the "Words not in a collection" bucket; curated Lingard collections are read-only because their content comes from the Lingard catalog. commit=true writes.

Input parameters:

- `cards` (array, required)
- `collectionTitle` (string)
- `collectionUuid` (string)
- `commit` (boolean)
- `targetLang` (string, required)

Output parameters:

- `changes` (object)
- `collection` (object)
- `committed` (boolean)
- `mergeMode` (string)
- `ok` (boolean)
- `payload` (object)
- `summary` (object)
- `targetLang` (string)
- `upsertResult`

### `lingard_update_example_translations` (~221 tokens)

Update Lingard Example Translations

Rewrites only the translation line of examples that already exist on Lingard cards; the example sentence, its {} highlights and its audio/typing markers are left exactly as they are. It changes, adds, or removes example translations; an empty translation is a supported card state, not an error. `translations` holds one entry per existing example, in order, so it is built from the card's current examples (a collection read with includeExamples:true lists them). commit=true writes; without it the call returns the resulting examples as a preview.

Input parameters:

- `cards` (array, required): One entry per card to edit. Each entry needs a card selector (`cardId`, or `title` plus a collection when the word occurs in several) and `translations`.
- `collectionTitle` (string): Optional default collection title for cards addressed by title.
- `collectionUuid` (string): Optional default collection for cards addressed by title.
- `commit` (boolean): True writes. Default false returns the resulting examples without saving.
- `targetLang` (string, required)

Output parameters:

- `cards` (array)
- `committed` (boolean)
- `ok` (boolean)
- `skipped` (array)
- `summary` (object)
- `targetLang` (string)

### `lingard_attach_card_images` (~178 tokens)

Attach Lingard Card Images

Attaches supplied images to existing Lingard cards. It does not generate images: each entry carries the image itself as imageBase64 or dataUri, or an imageUrl that the server downloads. PNG, JPEG, WebP, and SVG inputs are converted to WebP and uploaded as private custom card images; an image the card already has is replaced. commit=true writes.

Input parameters:

- `collectionTitle` (string)
- `collectionUuid` (string)
- `commit` (boolean): True uploads and attaches. Default false returns a dry-run preview without writing.
- `images` (array, required): One entry per card to illustrate. Each entry needs a card selector (`cardId` or `title`) and exactly one image source (`imageBase64`, `dataUri`, or `imageUrl`).
- `targetLang` (string, required)

Output parameters:

- `committed` (boolean)
- `images` (array)
- `ok` (boolean)
- `skipped` (array)
- `summary` (object)
- `targetLang` (string)
- `upsertResult`

### `lingard_get_learning_pauses` (~122 tokens)

Get Lingard Learning Pauses

Lists, for one language, the user's collections and sources (books, the news) and which of them are on pause. A collection or source on pause gives the automatic «Now learning» sessions no words — no new words and no reviews — and is not counted in the day's goals or reminders; opening it in the app still studies it as usual. Each entry carries the exact uuid, bookKey, and title that pause changes take.

Input parameters:

- `targetLang` (string, required): The learned language, e.g. en, de, es, fr.

Output parameters:

- `collections` (array)
- `note` (string)
- `ok` (boolean)
- `pausedCount` (integer)
- `sources` (array)
- `targetLang` (string)
- `truncated` (boolean)

### `lingard_set_learning_pauses` (~253 tokens)

Set Lingard Learning Pauses

Puts collections and sources on pause or takes them off it, for one language — e.g. "study only my Travel collection this week", "pause the news words", "resume everything". action: "pause" or "resume" the listed ones; "only" — resume the listed ones and pause every other collection and source of the language; "resume_all" — take every pause off (lists ignored). Collections are named by uuid or exact title and sources by bookKey or exact title, as the learning-pause list reports them. A paused item gives the automatic «Now learning» sessions no words and is not counted in goals or reminders; opening it in the app still studies it. commit=true writes; without it the call returns a preview of the changes and the resulting state.

Input parameters:

- `action` (string, required)
- `collections` (array): Collections by uuid or exact title.
- `commit` (boolean): True writes. Default false returns a preview without writing.
- `sources` (array): Sources by bookKey (catalog:… / imported:…) or exact title.
- `targetLang` (string, required): The learned language, e.g. en, de, es, fr.

Output parameters:

- `action` (string)
- `changes` (array)
- `collections` (array)
- `committed` (boolean)
- `note` (string)
- `ok` (boolean)
- `pausedCount` (integer)
- `preview` (boolean)
- `sources` (array)
- `targetLang` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/app-lingard-vocab/lingard#diagnostics

## Score history

- 2026-11-05: 82
- 2026-11-04: 80
- 2026-11-03: 81
- 2026-11-02: 81
- 2026-11-01: 79
- 2026-10-31: 80
- 2026-10-30: 79

## Common questions

### What is the Lingard Vocab MCP server?

Lingard Vocab is an MCP server listed in the public MCP registry as app.lingard/vocab. Build and enrich your Lingard vocabulary: topic collections, flashcards, translations, examples. This page covers its hosted endpoint (https://lingard.app/mcp).

### Is the Lingard Vocab MCP server safe to use?

Lingard Vocab scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Lingard Vocab MCP server expose?

Lingard Vocab exposes 15 tools: search, fetch, lingard_get_learning_context, lingard_get_vocab_collection, lingard_get_collection_gaps, and 10 more. Their descriptions and schemas cost roughly 2,776 tokens of context every time the server is loaded.

### Does the Lingard Vocab MCP server require authentication?

Yes. Lingard Vocab asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Lingard Vocab MCP server still maintained?

Lingard Vocab is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://lingard.app/mcp
- Website: https://lingard.app/instruction_mcp
- Changelog RSS feed: https://verifymcp.io/servers/app-lingard-vocab/lingard.xml
- Changelog JSON feed: https://verifymcp.io/servers/app-lingard-vocab/lingard.json
- HTML version of this page: https://verifymcp.io/servers/app-lingard-vocab/lingard