Caliu

Archive a note. Archived notes are hidden from all listings (and tag/folder views) but are never auto-removed and keep their tags. Reverse with unarchive_note. Distinct from delete_note (trash, auto-purged after 30 days).

archive_note

Create a new note from markdown. The first line becomes the title. Tags are auto-detected from #hashtags in the content (including hierarchical #parent/child and multi-word tags written with a closing hash: #my project#) — no separate tag tools needed. Reuse the user's existing tags: call list_tags first and match an existing handle exactly (same casing and hierarchy), e.g. write #todo rather than coining #todos or #task when #todo already exists. Only invent a new hashtag when no existing tag fits; if you're unsure which tag the user wants, ask them instead of guessing. Link to another note by writing [[Note Title]] with the exact title of an existing note — the server resolves it into a real note link (clickable in the apps, counted in backlinks). Titles that don't match an existing note stay as plain text.

create_note

Get a one-time link to upload a file of any size up to 100MB (videos, large PDFs, archives) without sending its bytes through this tool: upload_file needs the whole file as base64, which only works for small files. Then send the file's raw bytes to the link with an HTTP PUT, e.g. run the returned `command` (curl -T) with the file's path. The link needs no credentials, works once and expires in an hour. Returns the `markdown` snippet right away: put it into note content via create_note or update_note (keep the URL exactly as returned); it shows the file once the PUT is done. Images get the inline form, other files a downloadable file chip.

create_upload_link

Download an attachment from the user's Caliu storage so you can view or process it. Accepts the attachment id or the full download URL found in note markdown (https://.../attachments/<id>/download). Images come back as viewable image content, text-based files (txt, md, csv, json, svg, ...) as text, audio as audio content, and other binaries as a base64 resource. Refuses files over 10MB.

get_attachment

Get the currently authenticated user's profile (id, email, name).

get_current_user

Get a single note by ID, with full content, tags, its content revision `rev` (pass it to update_note as `base_rev`), and backlinks (notes that link to it via [[wiki links]]) in one response. Works for active and archived notes, and for notes shared with the user, which carry `role` (editor or viewer) and `ownerId`: these are read-only here, since update_note and the other note-changing tools work on the user's own notes only (an editor changes a shared note in the Caliu apps); a trashed note returns not-found (restore it first).

get_note

List all tags with note counts. Each tag includes a `handle` — the full hierarchical path as you'd write it in note content (e.g. `#work/project/subtask` for nested tags, `#work` for a root tag, `#my project#` for a multi-word tag, which is written with a closing `#`). Copy the handle verbatim into content. Call this before writing #hashtags in create_note or update_note so you reuse the user's existing tags (matching handle and casing exactly) instead of scattering near-duplicates like #todo vs #todos vs #task.

list_tags

Soft-delete a note (move to trash). Restorable with restore_note. Hard deletion is intentionally not exposed via MCP.

delete_note

Restore a soft-deleted note from trash.

restore_note

Search and filter notes. With `query`, runs full-text search over title and content, ranked by relevance (title matches weighted highest). Plain words match whole words with light English stemming (plurals and verb forms), OR-combined so a note matching more of the query words ranks higher; it is NOT substring or prefix search, so prefer a few distinctive keywords over a full sentence. The query can also narrow the results with the Caliu apps' search syntax: `"exact phrase"`, `-word` to exclude, `#tag` (includes nested tags; `!#tag` for that tag only, `#multi word#` for a tag with spaces), `@title` (words match the title only), `@todo` (has an open checkbox), `@done`, `@task`, `@pinned`, `@tagged`, `@untagged`, `@images`, `@files`, `@attachments`, `@code`, `@wikilinks`, `@readonly`, `@untitled`, dates in UTC days (`@today`, `@yesterday`, `@last7days`, `@ctoday`, `@created7days`, `@date(2026-10)`, `@cdate(<2026-01-15)`; `<` before, `>` after), and `or` between alternatives that each carry their own filters. Every filter must hold; a query of only filters (`#work @todo`) lists every match. `query` cannot be combined with `tag` or `untagged` (use `#tag` / `@untagged` in the query instead); `pinned` still applies. Without `query`, lists notes filtered by the other params, most-recently-updated first. Use `linksTo` to find notes that reference a given note via [[wiki links]]. `includeTrashed: true` lists trashed notes and `includeArchived: true` lists archived notes; both are plain listings that ignore `query` and all other filters. Pagination via `cursor`. Results carry note metadata and a short `contentPreview` (not the full body or tags) — call get_note to read a note's content and tags. Search also covers notes other people shared with the user (with the user's own pin, archive and tags); those hits carry `role` (editor or viewer) and `ownerId`.

search_notes