MCP tool reference
Every tool the Ornix MCP connector registers — 42 in total — grouped by access tier, with parameters and what each one touches.
The connector registers 42 tools, all prefixed ornix_. Your account's access tier — read, write, or full — is the most any authorized app can call, and you can limit each app further under Connected apps. Structural roadmap changes from any tier are proposals you apply on the roadmap.
Haven't connected yet? Start with connector setup.
Runs without asking, since nothing here changes your data — the default tier for every new connection.
ornix_get_contextPlansResume where the learner left off: the current roadmap, current week, what is due today, and a short learning-memory brief. Call it first in a new conversation.
plan?ornix_list_plansPlansList your roadmaps — status, progress, and current week for each.
status?, limit ≤100 (default 20), cursor?ornix_get_planPlansPull a roadmap's outline — phases, weeks, and which goals are done. Narrow to one phase or a set of week ids.
plan, format: concise | detailed, phase?, week_ids?ornix_get_weekWeeksZoom into one week: goals, resources, the concepts it teaches, its note list, flashcard counts, and what your learning memory says about it.
plan, week_id, include_notes?ornix_get_progressProgressStreaks, due-card count, and how each plan tracks against schedule. Scope to one plan to also get today's queue.
plan?ornix_list_notesNotesList the notes on a plan, optionally filtered to one week.
plan, week_id?, limit ≤200 (default 50), cursor?ornix_get_noteNotesRead one note in full, including its markdown body.
id — or plan + slugornix_get_due_cardsFlashcardsFetch the flashcards due for a study session, across one plan or all of them.
plan?, limit ≤200 (default 50)ornix_flashcard_statsFlashcardsDeck summaries — due/new counts, retention, a 7-day review count, and the review forecast.
plan?ornix_list_labsLabsList the interactive labs attached to one week (titles and summaries, no HTML).
plan, week_idornix_get_labLabsFetch one lab in full, including its HTML, so you can read or revise it.
lab_idornix_get_memoryMemoryRead a roadmap's learning memory — concept mastery with evidence, open misconceptions, next steps, your background, and past session recaps. Entries show #ids for ornix_remember.
plan, week_id?, kind?, include_resolved?, limit ≤100 (default 30), response_format? (concise | detailed), cursor?ornix_get_flashcardFlashcardsFetch one flashcard including its back, for grading a single answer.
card_idornix_get_visualNotesFetch one visual's full content (widget HTML or mermaid source) by id, after a note reports its visuals collapsed.
note, plan?, visual_idornix_list_resourcesLibraryList the documents you uploaded and the links you saved to your library.
status?, limit ≤100 (default 20), cursor?ornix_get_resourceLibraryRead a windowed slice of one library document's extracted text; page through large documents instead of pulling them whole.
id, offset_chars?, limit_chars ≤20000 (default 8000)ornix_search_resourcesLibraryFull-text search inside your uploaded documents, returning matching excerpts with resource ids.
q, limit ≤25 (default 10)ornix_searchSearchSearch across plans, notes, flashcards, and the public resource catalog.
query, types?, limit ≤50 (default 10)ornix_create_planPlansAuthor a brand-new roadmap in one call — phases, weeks, goals, and resources — and Ornix stores, schedules, and starts tracking it.
title, summary?, start_date?, prerequisites?, phases[] (≤10 phases, ≤60 weeks total)ornix_update_planPlansRename a roadmap, shift its start date, recover it from a failed status, or switch it between private/public visibility.
title?, start_date?, status? ("ready" to recover from failed), visibility?ornix_complete_goalsPlansMark one or more goals done or undone in a single batch; completing every goal in a week finishes it and extends the streak.
updates[]: week_id, goal_index, done (≤100 per call)ornix_get_timelinePlansSee the schedule for every week, plus how far it's drifted from the original dates.
planornix_shift_schedulePlansPush every remaining date out by N days, or resync the whole schedule to a resume date.
days or resume_date (exactly one)ornix_update_weekPlansEdit a single week's content — goals, focus, resources — without touching the rest of the plan.
plan, week_id, fields to updateornix_insert_weekPlansAdd a hand-authored week into the plan at a given position.
plan, position, week contentornix_remove_weekPlansRemove a week from the plan and renumber the weeks that follow.
plan, week_idornix_undo_plan_editPlansRevert the plan's last structural edit — available for 3 days after the edit.
planornix_create_noteNotesWrite a new note on a plan, optionally scoped to one week.
plan, week_id?, title?, body_md? (≤100k chars)ornix_update_noteNotesReplace a note's body, append to it, or rename it — pass body_md or append, never both.
body_md or append (exactly one), title?ornix_update_visualNotesEdit a generated visual in place — replace its widget HTML or mermaid source without appending a new one.
note, plan?, visual_id, html or source (exactly one), prompt?ornix_create_note_visualNotesAdd a visual to a note. You write it yourself: widget HTML (self-contained, one inline style and script, no network, up to 80,000 characters) or mermaid source (up to 8,000 characters). Ornix stores it and does not generate it from a prompt.
note_id, plan?, kind: widget | mermaid, html (widget) or source (mermaid), anchor?ornix_create_labLabsAuthor an interactive lab for a week and attach it to the week canvas. You write the HTML: one inline style and one inline script, no network, sized to fill the viewport, themed with the --ornix-* CSS variables, with a stepped story and Play/Pause/Step/Reset controls. Up to 100,000 characters.
plan, week_id, title, html, summary?ornix_update_labLabsRevise a lab in place: replace its HTML, title or summary.
lab_id, html?, title?, summary?ornix_rememberMemorySave what your AI learned about you on a roadmap — mastery with evidence, misconceptions, next steps, background, and a session recap — so the next session, in any AI app, picks up where this one stopped.
plan, memory_version, entries[]?, resolve[]?, recap? (≤12 entries per call)ornix_create_flashcardsFlashcardsTurn a note or a conversation into up to 50 flashcards in one batch.
plan, week_id?, note_id?, cards[]: front_md, back_md (≤50)ornix_review_flashcardFlashcardsGrade one flashcard and log a real spaced-repetition review, updating its due date.
card_id, rating: again | hard | good | easyornix_undo_reviewFlashcardsUndo your single most recent flashcard review, across any plan.
—Requires full tier, the highest access level — how much confirmation each tool adds varies (see below).
Confirmation varies by tool
ornix_delete_plan, ornix_delete_note, ornix_delete_flashcard, and ornix_delete_lab only propose the deletion: nothing is removed until you apply it on the roadmap. ornix_delete_plan also requires the caller to state the plan's exact title back. ornix_forget acts straight away and relies on your AI client's own confirmation prompt before it calls the tool.ornix_delete_planPlansPropose deleting a roadmap and everything on it — weeks, notes, and flashcards. Requires the plan's exact title as confirmation; nothing is removed until you apply it.
plan, confirm_title (must match exactly)ornix_delete_noteNotesPropose deleting a single note; it is removed once you apply it.
idornix_delete_flashcardFlashcardsPropose deleting a single flashcard; it is removed once you apply it.
idornix_delete_labLabsPropose deleting a lab from its week; it is removed once you apply it.
lab_idornix_forgetMemoryPermanently delete learning-memory entries by #id, for when you ask your AI to forget something.
plan, ids (1–50)Four of these are wired in as canned prompts on the connector itself — weekly_review, study_session, tutor_session, and capture_notes — they show up as slash commands in Claude Code and in claude.ai's + menu, so you don't have to type the prompt at all. The rest are plain prompts — copy, paste, and edit the specifics.
I want to learn systems design well enough to pass senior-level interviews in about 4 months. I can put in 6-8 hours a week, and I'm coming from 3 years as a backend engineer. Ask me whatever you need, then build the full roadmap in Ornix.Your AI interviews you, then authors the whole plan — phases, weeks, goals, and resources — as one structured roadmap with ornix_create_plan. Ornix takes it from there: storing it, scheduling it week by week, and tracking your progress.
Slash command: /weekly_review
Run my weekly review — what's my progress, what's due this week, and am I on track? Mark anything I've actually finished, and if I'm behind, suggest a replan.Slash command: /study_session
Quiz me on my due flashcards for the ML roadmap. Ask one at a time, don't show me the answer first, and log my rating after each one.Slash command: /tutor_session
Tutor me on my systems-design roadmap, week 4. Pick up from what you remember about me, teach one concept at a time, and save what my answers show as we go.Your AI reads the roadmap's learning memory first, so it starts from where you left off and what you still get wrong, then records mastery, misconceptions, and next steps as the session goes. Turn off AI updates in Memory and it only reads.
Slash command: /capture_notes
Turn what we just talked about into a note on week 6 of my systems-design plan, and pull 5 flashcards out of the key ideas.Walk me through week 4 of my AI roadmap like you're teaching it fresh, then quiz me on it and log my answers as flashcard reviews so it feeds my spaced repetition.I was out sick for 10 days and I'm three weeks behind on my chemistry roadmap. Replan the rest of it around where I actually am — don't touch the weeks I've already finished.