MindDory vocabulary memory is an MCP server with 13 tools an agent can call, among them capture_grammar_mistake, capture_word, check_words. It answers at https://api.minddory.com/v1/brain/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 8 of 8 times since 7 September 2026; the last check, on 18 October 2026, succeeded.
| Tool | What it does |
|---|---|
capture_grammar_mistake | Log a grammar mistake the user just made in the target language, creating a grammar point in their Minddory deck. Use it proactively whenever the user writes a target-language sentence with a clear, correctable error (wrong tense, agreement Inputs: user_text, correction, error_type, explanation, lang |
capture_word | Capture a target-language word or phrase to the user's Minddory vocabulary deck (a flashcard in the "Chat Discoveries" folder when the word is new, otherwise a context encounter). The user connected Minddory so their assistant builds their Inputs: word, gloss, context, words, lang, source_lang |
check_words | Batch lookup: for a list of target-language words, tell me which ones are already in the user's Minddory deck and how well they know each. Use this BEFORE glossing or capturing vocabulary from a message - it answers "which of these are actu Inputs: words, lang |
get_active_vocab | Get the user's most actively encountered target-language words (from past capture_word + log_interaction events), ranked by frequency over a lookback window. Use to surface "frontier" words the user keeps touching when they ask "what should Inputs: lang, limit, lookback_days |
get_card | Single card detail by word (case-insensitive). Returns translation, mastery, and last 10 events. Inputs: word, lang |
get_known_words | Words the user has verified known via flashcard practice. Paginated keyset on flashcards.id. Inputs: lang, limit, cursor |
get_queue | Cards due now and due within the next 24 hours. Inputs: lang, max |
get_recent_activity | Event log slice with optional surface filter and keyset pagination on answers.id. Inputs: surface, limit, cursor |
get_system_instructions | Call this at the START of every new conversation, before your first reply, to load the user's Minddory setup and your role as their proactive language partner: CEFR level, target/source languages, due-card count, weak words, and how to capt Inputs: lang |
get_user_profile | Profile snapshot: CEFR level, target/source languages, due card count, weak words, recent lookups. Pass `lang` to scope the snapshot to one learning language (for users learning several); omit it for the user's primary language. Inputs: lang |
log_interaction | Append a generic interaction event to the answers log. Use for lookups, AI discussions, and reading-in-context signals. Inputs: type, word, lang, metadata |
mark_demonstrated | Confidence-weighted spaced-repetition boost when the user has used a word correctly: the card moves further out in the review schedule. Logs an answer row even if no flashcard exists. Inputs: word, lang, confidence, source, context |
mark_struggled | Spaced-repetition degrade for a word the user just got wrong: the card comes back sooner. ease_factor drops, interval resets, repetitions reset. Inputs: word, lang, source, context |
Every block below points at https://api.minddory.com/v1/brain/mcp. Pick your client and copy.
claude mcp add --transport http minddory-vocabulary-memory https://api.minddory.com/v1/brain/mcp
{
"mcpServers": {
"minddory-vocabulary-memory": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.minddory.com/v1/brain/mcp"]
}
}
}{
"mcpServers": {
"minddory-vocabulary-memory": {
"url": "https://api.minddory.com/v1/brain/mcp"
}
}
}{
"servers": {
"minddory-vocabulary-memory": {
"type": "http",
"url": "https://api.minddory.com/v1/brain/mcp"
}
}
}{
"context_servers": {
"minddory-vocabulary-memory": {
"url": "https://api.minddory.com/v1/brain/mcp"
}
}
}{
"mcpServers": {
"minddory-vocabulary-memory": {
"serverUrl": "https://api.minddory.com/v1/brain/mcp"
}
}
}{
"mcpServers": {
"minddory-vocabulary-memory": {
"url": "https://api.minddory.com/v1/brain/mcp"
}
}
}name: MindDory vocabulary memory
version: 0.0.1
schema: v1
mcpServers:
- name: MindDory vocabulary memory
type: streamable-http
url: https://api.minddory.com/v1/brain/mcp{
"mcpServers": {
"minddory-vocabulary-memory": {
"httpUrl": "https://api.minddory.com/v1/brain/mcp"
}
}
}{
"mcpServers": {
"minddory-vocabulary-memory": {
"type": "http",
"url": "https://api.minddory.com/v1/brain/mcp"
}
}
}{
"mcpServers": {
"minddory-vocabulary-memory": {
"url": "https://api.minddory.com/v1/brain/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.minddory.com%2Fv1%2Fbrain%2Fmcp&type=streamable_http&id=minddory-vocabulary-memory&name=MindDory%20vocabulary%20memory
It answered our last check on 18 October 2026 in 656 ms. Over 8 checks since 7 September 2026 it answered 8. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by minddory.com and served from api.minddory.com, the vendor's own domain: https://api.minddory.com/v1/brain/mcp.
13, as returned by the server's own tools/list on 7 September 2026: capture_grammar_mistake, capture_word, check_words, get_active_vocab, get_card, get_known_words, get_queue, get_recent_activity, and 5 more.
It answered our last check on 18 October 2026 in 656 ms. Over 8 checks since 7 September 2026 it answered 8.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.minddory.com/v1/brain/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: minddory.com. Endpoint host: api.minddory.com. ARD identifier: urn:air:minddory.com:mcp:brain.
First indexed 7 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.