list_cards: Lists cards by type, tag, whiteboard, or time, without reading their content.

list_tags: Lists your tags with their hierarchy and card counts.

list_whiteboards: Lists your whiteboards and their hierarchy.

search_by_keyword: Finds content by exact words or short phrases. PDF, video, and audio cards are matched by title only.

search_by_semantic: Finds content by meaning, even when it uses different words.

search_object_content: Searches for text inside one card, journal, or parsed PDF.

read_object: Reads a card, journal, or other object. Long content can be read in parts.

read_journal_range: Reads your journals in a date range, up to 185 days per call.

read_whiteboard: Reads a whiteboard's structure, or the content of the objects on it.

read_pdf: Reads pages of a parsed PDF card.

read_image: Reads an image, including images parsed from PDFs.

read_card_highlights: Reads the highlights on a note card or PDF card, with their notes.

read_backlinks: Finds the cards, journals, and whiteboards that link to, mention, or place an object. Needs Heptabase open.

read_database: Reads a tag database's properties, select options, and views.

query_database: Finds cards in a tag database with filters and sorts. Needs Heptabase open.

get_file_download_url: Downloads an original PDF, image, audio, video, or attachment.

create_object: Creates a note card, or a journal for a date that has none.

edit_note_card_content: Edits part of a note card without rewriting it: replaces exact text, adds content at the end, or rewrites the whole card. The changes in one call are saved together, or none are.

edit_journal_content: Edits a journal the same way, and creates the journal if that date has none.

import_file_from_url: Imports a file from a public link, up to 50 MB.

get_file_upload_url, import_file_from_upload: Upload a file from your computer, up to 2,000 MB. The assistant needs to be able to run commands, as in Codex or Claude Code.

create_pdf_card_from_file, create_image_card_from_file, create_audio_card_from_file, create_video_card_from_file: Create a card from an imported file.

parse_pdf: Parses a PDF card so its pages can be read. Long PDFs can take a few minutes.

create_web_card_from_url: Saves a web page as a web card.

create_video_card_from_url: Saves a YouTube video as a video card, with its captions as the transcript.

edit_card_properties: Sets property values on cards in a tag database.

update_database_card_membership: Adds cards to a tag database, or removes them from it without deleting the cards. Removing needs Heptabase open.

create_database: Creates a tag database.

edit_database: Renames a tag database and edits its properties, select options, and views. Needs Heptabase open.

create_tag_group: Creates a tag group in the Tags sidebar.

move_tags: Moves tags under another tag, into a tag group, or to the top level.

trash_cards: Moves cards to the trash. Trashed cards stay on their whiteboards until they are removed.

restore_cards: Restores cards from the trash, back where they were.

rename_object: Renames a whiteboard, section, or PDF, web, image, video, or audio card. Needs Heptabase open.

list_inbox_items: Lists what is in your Inbox: cards and messages you added, mentions, replies, quotes, and invites.

add_cards_to_inbox: Adds cards to your Inbox, optionally with a date to remind you.

update_inbox_items: Marks items done, read, or unread, or sets or clears a reminder date.

remove_inbox_items: Removes cards and messages you added from the Inbox, without deleting them. Mentions, replies, quotes, and invites can only be marked done.

create_whiteboard: Creates a whiteboard or a sub-whiteboard.

move_whiteboard: Moves a whiteboard to another place in the hierarchy.

create_whiteboard_shortcut: Shows a whiteboard on another whiteboard as a shortcut.

place_whiteboard_objects: Places existing cards and journals on a whiteboard.

move_whiteboard_objects: Moves objects within a whiteboard.

move_whiteboard_objects_across_whiteboards: Moves objects to another whiteboard, keeping their layout.

arrange_whiteboard_objects: Arranges objects in a row, column, or grid.

align_whiteboard_objects: Aligns objects by an edge or center.

resize_whiteboard_objects: Resizes, folds, or expands objects.

update_whiteboard_objects_color: Changes the color of objects and connections.

remove_whiteboard_objects: Removes objects from a whiteboard without deleting the cards.

create_section: Creates a section around objects.

create_connections: Connects objects, with or without labels.

update_connection: Changes a connection's route or color.

create_mind_map: Creates a mind map from text, cards, and highlights.

update_mind_map: Adds, edits, moves, or deletes mind map nodes, and changes its layout.

read_whiteboard_layout: Reads the position and size of every object.

lint_whiteboard: Checks a whiteboard for overlapping objects and crossing connections.

screenshot_whiteboard: Takes a simplified picture of a whiteboard so the assistant can check its layout.

render_cards: Shows cards in an interactive view in ChatGPT, Claude, and Codex.

open_heptabase: Opens a whiteboard inside the chat, where you can edit it and watch the assistant's changes.

navigate_heptabase: Switches the whiteboard open in the chat, or opens a card beside it.

read_heptabase_view: Checks which whiteboard and card you have open in the chat.

read_space_instructions: Reads your Space Instructions, the standing rules you set for how AI works in your space. The assistant reads them before it starts working and follows them.

set_space_instructions: Makes an existing note card your Space Instructions. To add a rule later, the assistant edits that card.