# Vocabit (npm · vocabit-mcp)

Create flashcard sets in the Vocabit app and read back how the learner actually did.

- Trust score: 84/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-26

## Components

- npm · `vocabit-mcp`: 84/100 (this document), [markdown](https://verifymcp.io/servers/johnbilousov-vocabit-mcp/vocabit-mcp.md), [page](https://verifymcp.io/servers/johnbilousov-vocabit-mcp/vocabit-mcp)

## Channel facts

- Registry: `npm`
- Package: `vocabit-mcp`
- Version: `0.1.3`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-26.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to JohnBilousov/vocabit-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 87/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1018 tokens (~101/item across 10 items; 8 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 82% 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.
  - All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 10 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 Vocabit MCP server?

Vocabit runs locally as an npm package, launched with npx -y vocabit-mcp. 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 johnbilousov-vocabit-mcp -- npx -y vocabit-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "johnbilousov-vocabit-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "vocabit-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "johnbilousov-vocabit-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "vocabit-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add johnbilousov-vocabit-mcp -- npx -y vocabit-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "johnbilousov-vocabit-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "vocabit-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add johnbilousov-vocabit-mcp --command npx --arg -y --arg vocabit-mcp
```

### Hermes

```yaml
mcp_servers:
  johnbilousov-vocabit-mcp:
    command: "npx"
    args: ["-y", "vocabit-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "johnbilousov-vocabit-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "vocabit-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add johnbilousov-vocabit-mcp -t stdio -c npx -a -y vocabit-mcp
```

### Other

```json
{
  "mcpServers": {
    "johnbilousov-vocabit-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "vocabit-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-26 (score 84, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-25 (score 81, +26)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Provenance: fail → pass
- [security] The attested source repository moved: JohnBilousov/vocabit-mcp
- [functional improvement] Tool coverage: 50% → 100%
- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.1.2 → 0.1.3

### 2026-08-24 (score 55)

First indexed and scored.

## MCP tools (8)

### `vocabit_health` (~39 tokens)

Check Vocabit connection

Verify the server can reach Vocabit and report which mode it is in (live backend or in-memory demo). Call this first if anything else fails.

Output parameters:

- `baseUrl`
- `defaultUserId`
- `mode` (string)

### `create_study_set` (~270 tokens)

Create a study set

Build a flashcard set and publish it to the learner's Vocabit app. Returns a deep link that opens the set on their device. Prefer one focused topic and 8-15 cards per set — long sets get abandoned. Use the notes field for what you want to check afterwards; the learner never sees it.

Input parameters:

- `cards` (array, required): The flashcards, 1-300. Keep a set to one theme and around 8-15 cards for a single session
- `definitionLanguage` (string): Language of the definitions, e.g. 'en'
- `description` (string): Short description shown under the title
- `notes` (string): Your own notes about what to check when reviewing results. Never shown to the learner
- `notify` (boolean): Ping the learner on Telegram that the set is ready
- `termLanguage` (string): Language of the terms, e.g. 'de'
- `title` (string, required): Set title as the learner will see it in the app
- `topic` (string): Topic tag used to group sets and to filter them later, e.g. 'church vocabulary'
- `userId` (string): Firebase UID of the learner. Omit to use the server default
- `visibility` (string): Defaults to private

Output parameters:

- `appSchemeLink` (string)
- `cardCount` (number)
- `deepLink` (string): Universal link that opens the set in the app
- `notified` (boolean)
- `setId` (string)
- `title` (string)
- `userId` (string)
- `visibility` (string)

### `list_study_sets` (~120 tokens)

List study sets

List the sets you created for this learner, newest first, each with a progress summary. Use it to find a setId, or to see at a glance which sets were never opened.

Input parameters:

- `includeProgress` (boolean): Attach a progress summary to each set (default true)
- `limit` (integer): How many sets to return, newest first (default 20)
- `topic` (string): Only sets with this exact topic tag
- `userId` (string): Firebase UID of the learner. Omit to use the server default

Output parameters:

- `count` (number)
- `sets` (array)

### `get_study_set` (~54 tokens)

Get study set contents

Read the full contents of a set — every card, plus the topic and notes you attached when you created it.

Input parameters:

- `setId` (string, required): Set id returned by create_study_set or list_study_sets

Output parameters:

- `cardCount` (number)
- `cards` (array)
- `deepLink` (string)
- `description`
- `notes`
- `setId` (string)
- `title` (string)
- `topic`

### `get_set_results` (~109 tokens)

Get how the learner did

Read back real study results for a set: which cards the learner marked hard (weakCards), which they never reached (untouchedCards), and per-card review counts. This is the feedback half of the loop — read it before writing the next set, and build the follow-up out of weakCards.

Input parameters:

- `setId` (string, required): Set id returned by create_study_set or list_study_sets
- `userId` (string): Read progress for a different learner than the set owner

Output parameters:

- `cards` (array)
- `completed` (boolean)
- `demoNote` (string)
- `dueCardIds` (array)
- `notes`
- `setId` (string)
- `summary` (object)
- `title` (string)
- `topic`
- `untouchedCards` (array)
- `weakCards` (array)

### `update_study_set` (~159 tokens)

Update a study set

Change a set in place: retitle it, retag it, or add cards. Pass addCards to append (the usual case after reviewing results) or cards to replace the list wholesale — never both. Replacing the cards resets what the learner has already studied.

Input parameters:

- `addCards` (array): Append cards to the existing list. Cannot be combined with cards
- `cards` (array): Replace the whole card list. Cannot be combined with addCards
- `description` (string)
- `notes` (string)
- `setId` (string, required): Set id returned by create_study_set or list_study_sets
- `title` (string)
- `topic` (string)
- `visibility` (string)

Output parameters:

- `cardCount` (number)
- `setId` (string)
- `updated` (array): Which fields changed, e.g. ['title', 'addCards']

### `notify_learner` (~80 tokens)

Ping the learner

Send the learner a Telegram message that a set is waiting. Use sparingly — one ping per set, right after you create it.

Input parameters:

- `setId` (string, required): Set id returned by create_study_set or list_study_sets
- `text` (string): Custom message. Omit for the default 'your set is ready' ping

Output parameters:

- `notified` (boolean)
- `setId` (string)
- `telegramId` (number)

### `delete_study_set` (~61 tokens)

Delete a study set

Remove a set from the learner's app. Study history is kept on the backend, but the set disappears from their device. Ask before calling this.

Input parameters:

- `setId` (string, required): Set id returned by create_study_set or list_study_sets

Output parameters:

- `deleted` (boolean)
- `setId` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/johnbilousov-vocabit-mcp/vocabit-mcp#diagnostics

## Score history

- 2026-08-26: 84
- 2026-08-25: 81
- 2026-08-24: 55

## Common questions

### What is the Vocabit MCP server?

Vocabit is an MCP server listed in the public MCP registry as io.github.JohnBilousov/vocabit-mcp. Create flashcard sets in the Vocabit app and read back how the learner actually did. This page covers its npm package (vocabit-mcp).

### Is the Vocabit MCP server safe to use?

Vocabit scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 26 August 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 Vocabit MCP server expose?

Vocabit exposes 8 tools: vocabit_health, create_study_set, list_study_sets, get_study_set, get_set_results, and 3 more. Their descriptions and schemas cost roughly 892 tokens of context every time the server is loaded.

### Is the Vocabit MCP server still maintained?

Vocabit is still listed as active in the MCP registry. We last reached this channel on 26 August 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Vocabit MCP server under?

Vocabit declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/vocabit-mcp
- Socket report: https://socket.dev/npm/package/vocabit-mcp
- Repository: https://github.com/JohnBilousov/vocabit-mcp
- Changelog RSS feed: https://verifymcp.io/servers/johnbilousov-vocabit-mcp/vocabit-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/johnbilousov-vocabit-mcp/vocabit-mcp.json
- HTML version of this page: https://verifymcp.io/servers/johnbilousov-vocabit-mcp/vocabit-mcp