Study decks for 8 languages plus the K2 spaced-repetition engine, runnable on your items.
Scored across 7 tools
Most tools have clearly distinct purpose+resource: list_decks (catalog), search_deck (substring search), get_entry (exact-term full record), explain vs simulate for the K2 engine. The only mild overlap is search_deck vs get_entry, since both return entry data, but the descriptions draw a clear line (fuzzy/paginated vs exact/full-field).
All seven tools follow a consistent snake_case verb_noun pattern: explain_k2_algorithm, get_cube_algorithms, get_entry, get_site_info, list_decks, search_deck, simulate_k2_session. Verbs (explain/get/list/search/simulate) all read naturally against their objects with no style mixing.
Seven tools is well-scoped for a read-only study-deck/cube-trainer server. Each one covers a distinct need (meta, engine docs, simulation, deck catalog, search, entry lookup, cube algorithms) with no filler.
The read/search/get lifecycle for decks and the cube-algorithm sets is covered, and simulate_k2_session exposes the scheduling engine. Minor gaps: no way to enumerate a whole deck without a query (search requires a term), and no separate get-deck-by-id beyond the catalog. These are workable, not blocking, for a curated read-only surface.
The K2 spaced-repetition engine, described. K2 stores no review dates: each item holds a probability p that halves on a correct answer and doubles on a wrong one, and items are drawn by Monte Carlo rejection sampling, so the pool self-organizes around current weaknesses and expands when it cools. Returns the update rule (including the deliberate hinted-answer exception), the selection and pool-expansion mechanics, the live tuning constants, and notes for porting it. Read this before simulate_k2_session.
Inputs: no named parameters.
Rubik's cube last-layer algorithm sets used by the K2 cube trainer: full OLL (57 cases), full PLL (21), the two-look beginner subsets, full ZBLL, and Roux CMLL (42 cases plus a two-look subset; CMLL algorithms only need to solve the corners and keep both 1x2x3 blocks). Each case returns its primary algorithm plus alternates, with sources and finger-trick notes where recorded. Every algorithm in these sets is verified against a cube simulator by the repo's audit script (app/cube/scripts/audit-algorithms.mjs), run before data changes land. Filter by case_id or group; omit both for the set's structure and levels.
Inputs: set (required), group, limit, case_id.
One deck entry in full, matched on the exact term (the kanji, hanzi, jamo, or word itself). Case-insensitive. Returns every field the deck carries, including the deck-specific extras: stroke counts and JLPT level for kanji, component kanji for compounds, declension and English derivatives for Latin, IPA and pronunciation audio for French.
Inputs: deck (required), term (required).
What K2 is, which apps it runs, what this server does and does not expose, and every machine-readable surface. Also returns the full capability map — every tool, prompt, and resource — so a client with a stale or tools-only roster can still see the whole surface.
Inputs: no named parameters.
The catalog of K2 study decks: nine curated datasets spanning Japanese kanji and vocabulary, HSK Chinese, Korean Hangul, Spanish, French, classical Latin, medical Latin and nature birds. Returns each deck id (the value other tools take), what it teaches, how many entries it has, and what its fields mean. Call this before search_deck.
Inputs: no named parameters.
Search one deck. query substring-matches the term, its reading/pronunciation, its English meanings, and its category, so "bone" finds entries glossed as bone and "ㄱ" finds that jamo. Narrow with category (exact, from list_decks) or difficulty (1-5; for the kanji deck this is the school grade). Paginated via offset.
Inputs: deck (required), limit, query, offset, +2 more.
Run the real K2 engine over your own items. Give it a list of terms (any strings — your flashcards, cube cases, anything), a study mode, and a sequence of answers, and it returns the p-value trajectory per answer, which items are now mastered, when the pool expanded, and the probability distribution over what K2 would serve next. Use this to drive your own drilling with K2 as the scheduler instead of reimplementing it.
Inputs: steps (required), terms (required), mode, starting_level.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Language flashcards in your AI assistant: build decks, edit cards and review what's due in the chat.
Save vocabulary from any AI chat; see each word in every language you know; review it with FSRS.
Language flashcards: list your decks, read cards and review progress, save new decks from a chat.
Make Anki, Quizlet, Mochi and Brainscape decks and review your vocabulary from the chat.
Add one secure layer between your agents and this server.
