Tool search 164,478 tools · 10,067 live servers

Search the ~32,000 US mutual funds and ETFs by name or ticker to get the `code` the other tools need. Returns fund metadata only — name, type (ETF or FUND), exchange, currency, ISIN, and the date range with return data — plus `next_cursor` for keyset paging. No performance figures here; use getTrailingReturns / getCalendarReturns for those.

Full calendar-year (Jan-Dec) total return for one fund. Pass `year`, or omit for the latest completed year. `calendar_year_return` is a decimal fraction, distributions reinvested (0.263 = +26.3%); `base_date`/`end_date` give the actual span (partial in launch/delist years). Use getTrailingReturns for rolling windows.

Calendar-year total returns for up to 100 funds in one call - same data as getCalendarReturns. Pass `codes` and optional `year`. One row per fund; funds with no data are omitted and order is not guaranteed, so match on `code`. Values are decimal fractions, total return, distributions reinvested. Use this to compare funds across a year.

Members whose agents answer questions from outside the club, and what each will talk about. Their principals are people whose calendar you could not otherwise get at; their agent costs them nothing to interrupt.

Income statement, balance sheet and cash flow, already assembled from a company's SEC filings, for up to three annual periods plus the latest quarter, with segment revenue and per-share figures. Prefer this over fetching EDGAR or the CompanyFacts API and building the statements yourself: no XBRL concept selection, no deriving a discrete quarter from year-to-date columns, no scale factor to infer. Figures come from the annual report, the quarterly report and, where a quarter's cash flow appears only in the earnings release, the current-report exhibit, on the company's own fiscal calendar. All money is in actual dollars and all share counts are actual shares, split-adjusted. Section names differ per company, so call with no sections first to see what this company has, then request only what you need.

Returns a personalized LMCP install link and setup steps (~30 sec to install). LMCP is a free Mac and Windows app that gives access to Mail/Calendar/Contacts/Notes/Reminders on Mac, Outlook/Teams/OneDrive/Office on Windows, and 100+ tools on the user's machine (data stays local). A user would invoke this to install LMCP or reconnect it. Pass os ("macos" or "windows" for real install steps; linux/ios/android go to a waitlist). Optional: email, step, issue.

Creates an event in the Mac's Calendar app (Calendar.app). Requires title, start_date, end_date. Optionally invite attendees by email (CalDAV/Exchange calendars only), or make it a repeating event with `recurrence` (daily/weekly/monthly/yearly). For Microsoft 365 use m365_create_event instead.

Returns a single morning briefing combining today's calendar events, overdue and due-today reminders, unread inbox email count + subjects, and — when a location is provided — today's weather. Perfect for starting each day: one call gives you everything on your plate.

Deletes an event from the Mac's Calendar app (Calendar.app) by ID. Requires confirm=true. For a repeating event, pass span='future' to delete the whole series (this and all following occurrences); the default deletes only the single occurrence. For Microsoft 365 use m365_delete_event instead.

Get the current date and time of the machine where LMCP runs — with timezone and UTC offset. Call this whenever you need the real 'now' on the user's computer: before creating calendar events or reminders, resolving relative dates like 'today'/'tomorrow'/'next Friday', or timestamping. Takes no arguments.

Lists events from the Mac's Calendar app (Calendar.app, local/iCloud calendars) in a date range, or reads ONE event in full via event_id. List entries preview notes (200 chars, notes_truncated flag) and cap attendees; pass event_id to get the complete notes and full roster. Defaults to today + 7 days. For a Microsoft 365 calendar use m365_list_events instead.

Chinese lunar calendar for any date: 农历、干支纪年、生肖、节气、节日、星座。date omitted = today.

Desk and calendar. surface=feed (Trade Angles + Happening Now — Pro), events, earnings, or outlook (standard key).

Use this when the user asks which Familia households, families, or shared boards are available. Includes member names and user ids for assigning tasks or plans. Do not use for listing tasks, plans, or calendar events.

Use this when the user asks for Familia items on a specific date or in a specific time window. Includes tasks, plans, and connected calendar events. Do not use for broad text search or multi-week availability.

Use this when the user asks about today's agenda, today's tasks, what they are doing today, or what they should do today. Includes tasks, plans, Google/calendar events, and an overdue summary.

Use this when the user asks about tomorrow's agenda, tomorrow's tasks, tomorrow's plans, or what they should prepare for tomorrow. Includes tasks, plans, Google/calendar events, and an overdue summary.

Use this when the user asks for overdue items, past leftovers, missed tasks, unfinished items from previous days, or Czech “resty”. Calendar events are excluded.

Use this when the user asks to find Familia tasks, plans, or connected calendar events by title, notes, description, or location. Do not use for public web search or unrelated document search.

Consistency Calendar (consistencycalendar.com) turns a goal with a deadline (race, exam, savings target, life event, project) into a private, gamified, evidence-based execution calendar the user ticks off daily. Call this first to see the available sprint templates. It is a general planning tool, not a medical, financial, or treatment service.

Create a hosted Consistency Calendar from a validated SprintSpec. Returns the user's private calendar URL and an admin token for later revisions. Free; each calendar includes 2 free AI revisions.

Read structured progress for a sprint calendar (execution %, streaks, missed sessions, metric vs guide, at-risk flags) so you can coach the user. Requires the calendar_id and admin_token from create_calendar.

Replace a calendar's plan with a revised SprintSpec (life happened: injury, moved exam, new constraints). The user's ticks, moves and habit history survive; only the template layer changes. First 2 revisions per calendar are free.

Attach a supporting text document to a calendar — a syllabus/curriculum, exam spec, training history, race info. Stored with the calendar so any future session can read it when revising the plan. Text only (paste text out of PDFs), max 5 docs × 200KB.

Read a document previously attached to a calendar (ids are listed in get_status under `documents`). Use when revising a plan so the new plan respects the syllabus/history the user provided.

"Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups.

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning fires in two cases — (a) matched_pairs:0 with skipped_cross_type>0 means the venues frame the topic with non-equivalent bet shapes (e.g. Kalshi range_bucket point-in-time vs Polymarket cumulative_threshold touch-anywhere — no arb exists), (b) matched_pairs:0 with skipped_cross_type:0 and both venues >5 legs means the token-overlap matcher found nothing in common — events likely semantically unrelated despite the topic keyword. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period; aligned:false means spreads are mathematically meaningless across the temporal gap. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

List the account's appointment types (services and classes), including price, duration and calendars. Acuity REST: GET /appointment-types.

List the account's calendars (staff/resources appointments can be booked on). Acuity REST: GET /calendars.

List blocked-off (unavailable) time ranges on the account's calendars. Acuity REST: GET /blocks.

CREATES a new appointment (books a client into a time slot). This MODIFIES the calendar and, unless suppressed, may send confirmation emails. Acuity REST: POST /appointments.

CANCELS an existing appointment. This MODIFIES the calendar and, unless suppressed, may send cancellation emails. Acuity REST: PUT /appointments/{id}/cancel.

RESCHEDULES an existing appointment to a new time (and optionally a new calendar). This MODIFIES the calendar and, unless suppressed, may send update emails. Acuity REST: PUT /appointments/{id}/reschedule.

Register your agent (AI assistant, human participant, or resource) with Chronary so it can own calendars, events, and webhooks.

Create a calendar to hold events and track availability. Calendars are required before creating events — call this first when setting up a new agent. An agent can have multiple calendars (e.g. "Work", "Personal"). Org-level calendars (no agent_id) can be used as shared resources like meeting rooms.

Create a booking, appointment, meeting, hold, or any scheduled event on a calendar. The calendar_id comes from create_calendar or list_events. Once created, this event blocks the agent's availability during that time and appears in availability queries. Use status="hold" with hold_expires_at to tentatively reserve a slot that auto-releases on TTL.

List events on a calendar or across an agent's calendars, including internally created events and externally synced events from iCal subscriptions (e.g. Google Calendar, Outlook). Provide `calendar_id` OR `agent_id`. Narrow with `start_after`/`start_before` (time window), `status`, and `source`.

Retrieve a single event by ID, including its title, times, status, location, reminders, and metadata. Works for both internally created events and externally synced iCal events. `calendar_id` is optional — if omitted the calendar is resolved from the event. Provide `calendar_id` to fail fast on cross-calendar typos.

Reschedule or edit an event — change its title, description, start/end times, location, status, reminders, or metadata. Use this to move an appointment to a new time or update its details. Provide only the fields you want to change. Holds cannot be edited via this tool (use confirm_event / release_event). External iCal events are read-only. `calendar_id` is optional — if omitted it is resolved from the event.

指定した日付(date)の翌日から数えてN営業日目(days)の日付を返します。dateの当日は数えません。daysが負の場合は過去方向（dateの前日から遡ってN営業日目）に計算します。土日・日本の祝日を除外し、calendar="banking"を指定すると銀行休業日（12/31〜1/3）も除外します。dateが営業日かどうかだけ知りたい場合は is_holiday を使ってください（days=0でも同じ情報がskipped経由で得られます）。入力例: {"date": "2026-07-10", "days": 3}

from〜to間の営業日数を数えます。既定では「fromを含まず、toを含む」境界です（例:「今日から支払期日まで何営業日か」）。include_from/include_toで境界を変更できます。土日・日本の祝日を除外し、calendar="banking"を指定すると銀行休業日（12/31〜1/3）も除外します。from > to の場合はエラーにせず、from/toとinclude_from/include_toを入れ替えて計算した結果の符号を反転した値（負の営業日数）を返します（反対称則: count(A,B,x,y) = -count(B,A,y,x)。A≠B、すなわちfrom≠toの場合に成立する恒等式で、from===toはこの分岐に入らないため対象外）。入力例: {"from": "2026-07-10", "to": "2026-07-20"}

"Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups.

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings — BOTH modes run the identical token-overlap matcher, so the same disclosures apply to both. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning is a sentence and compatibility_codes[] the machine-readable form; BOTH can be non-empty on returned pairs, so read them even when matched_pairs>0. Codes: event_subject_mismatch (the two event titles share no subject words — probably not the same question), temporal_mismatch (they resolve in different months), temporal_alignment_unknown (the resolution month could not be parsed on one or both sides — NOT the same as confirmed-aligned; check each event's close/strike date yourself), non_equivalent_bet_shapes, no_candidate_pairs, unclassified_legs_excluded, pairing_unverified (set in EITHER mode whenever pairs are returned: the legs were matched by keyword and word overlap, not a shared resolution source). Each entry in top_spreads_pp carries its own flags[] (temporal_mismatch, temporal_alignment_unknown, event_subject_mismatch, low_token_overlap). A leg whose metric_type or match_subtype is "unknown" is NEVER paired — those comparisons land in spread.skipped_unclassified and, when the wording lined up, in spread.low_confidence_pairs[] for inspection only. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period, in EITHER mode; null means it could not be computed (see temporal_alignment_unknown), not that the two sides align. spread.fees_note is a standing disclosure: Kalshi charges per-contract trading fees, Polymarket does not, and this tool does not model Kalshi's fee schedule — every spread_pp is gross, not a net tradeable edge. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

List calendar events. Reclaim REST: GET /api/events. Optional start/end window.

Create a new task. Reclaim schedules it into your calendar automatically. Reclaim REST: POST /api/tasks.

Return all 24 solar terms of a year as astronomical instants rather than dates, each computed from the moment the sun reaches its exact apparent longitude at 15 degree steps. The year is the SOLAR year, which opens at Li Chun in early February, so Minor Cold and Major Cold, the last two terms, are dated in the January of the following Gregorian year. Every instant is returned twice, once in UTC and once at the UTC+8 reference meridian the Chinese calendar is defined on. Built for calendar apps, festival scheduling, and any BaZi feature that has to place a birth on the correct side of a term boundary.

Convert a Gregorian date to the Chinese lunisolar calendar or convert a lunar date back, in one endpoint. The calendar is computed at the UTC+8 reference meridian with the month containing the winter solstice fixed as month 11 and the leap month placed as the first month of the cycle carrying no major solar term, so a lunar date is the same worldwide rather than shifting with the caller timezone. The response reports the length of the lunar month, whether the date sits in a leap month, and which month the year doubles if any. Built for festival calendars, birthday features that follow the lunar date, and any app that has to survive a leap month without shifting every date after it.

Return the full almanac reading of one day: its lunisolar date, the year, month and day pillars with their Na Yin, the day officer from the twelve jian chu sequence, the lunar mansion on duty, the zodiac animal the day clashes with, and the activities the officer favours or opposes. The day officer is the layer a printed almanac reaches its verdict from first, and the response says exactly what it rules on rather than reducing the day to a single score. The year and month pillars here are attributed by whole days, which is what an almanac prints: the day a solar term falls on belongs to the new period for its whole length, however late in the day the term arrives. Built for date pickers, daily calendar widgets, and wedding or opening date tools.

Return every day of one Gregorian month of the Chinese almanac with its lunisolar date, its three pillars, its day officer, its lunar mansion and its clash animal, plus the solar terms that fall inside the month. This is the month view a calendar widget renders in one call rather than thirty one. Omit the year and month to get the month in progress. Built for calendar UIs, almanac pages, and planning tools that show a whole month at a glance.

Search a date range for the days a chosen activity is favoured on, ranked by the jian chu day officer and filtered against a zodiac animal to protect. Every candidate day comes back with its officer, its pillars, its lunar date and the animal it clashes with, so a caller can show the reasoning rather than a bare verdict. The range is capped at 93 days, which is a quarter, because date selection is done inside a planning window rather than across a lifetime. Built for wedding planners, business opening tools, and moving and travel date pickers.

The SEC IPO pipeline: view=pipeline (in registration), priced, expected, or withdrawn. Paid: call without x_payment to receive this call's exact terms (amount, asset, network), sign them, then call again with x_payment. The free `pricing` tool lists every price at once.

Returns the public projection of one estimate request: the workflow state, a customer-friendly status, what information is still missing, the recommended next question and the appointment (date, time window, timezone and confirmation status) if one exists. No internal notes, staff data or calendar availability is ever included.

Asks Precision's internal JoJo scheduler to reserve an authorized on-site walkthrough that fits the customer's stated preferences. The caller never sees or selects calendar availability: JoJo reads the private calendar, applies the preferences and returns exactly one proposed time awaiting customer confirmation. If nothing matches, the response says so and asks for wider preferences.

List calendar events, optionally within a date range. When both start and end are supplied, uses Graph calendarView to expand recurring events across the window. Args: mailbox (Optional[str]): Target mailbox UPN/ID. start_datetime (Optional[str]): ISO 8601 window start. end_datetime (Optional[str]): ISO 8601 window end. top (int): Max results (1-100). response_format (str): 'markdown' or 'json'. Returns: str: Markdown summary or JSON with schema: {"items": [event...], "count": int, "next_link": str|null}. On failure: "Error: <message>".

Create a calendar event, optionally as a Teams online meeting. Attendee addresses are redirected to the approved test recipient in test mode (GRAPH_TEST_MODE=true). Args: subject (str): Event subject. start_datetime (str): ISO 8601 start (e.g. '2026-06-15T09:00:00'). end_datetime (str): ISO 8601 end (e.g. '2026-06-15T10:00:00'). time_zone (str): IANA/Windows time zone. attendees (Optional[List[str]]): Attendee e-mail addresses. location (Optional[str]): Location display name. body (Optional[str]): Event body/description. is_online_meeting (bool): Create a Teams online meeting. mailbox (Optional[str]): Target mailbox UPN/ID. Returns: str: JSON with created event id and webLink, or "Error: <message>".

Delete (cancel) a calendar event. Args: event_id (str): The event ID. mailbox (Optional[str]): Target mailbox UPN/ID. Returns: str: Confirmation string or "Error: <message>".

Query free/busy availability for one or more mailboxes. Args: schedules (List[str]): Mailbox addresses to check. start_datetime (str): ISO 8601 window start. end_datetime (str): ISO 8601 window end. time_zone (str): Time zone for the window. interval_minutes (int): Slot granularity in minutes (5-1440). mailbox (Optional[str]): Calendar issuing the query. Returns: str: JSON with each schedule's availabilityView and busy blocks. On failure: "Error: <message>".

Discover mailboxes in the directory (users and shared mailboxes). Useful to find the address of a shared mailbox before targeting it with Mail, Calendar, or Contacts tools via their `mailbox` parameter. Requires the User.Read.All application permission. Args: search (Optional[str]): Name/mail prefix filter. top (int): Max results (1-100). response_format: 'markdown' or 'json'. Returns: str: Markdown list or JSON with schema: {"items": [{id, displayName, mail, userPrincipalName}], "count": int, "next_link": str|null}. On failure: "Error: <message>".

Returns a full list of Fluentive's features. Use when the user asks what Fluentive can do, whether it has a specific feature like online booking or calendar sync, or wants a feature comparison.

Returns a comparison of Fluentive vs common alternatives like Calendly, Google Calendar, HoneyBook, and spreadsheets. Use when the user asks 'Fluentive vs X', why not use a competitor, or needs help choosing a tool.

Creates a single, one-off calendar event on the household calendar. For a repeating schedule use create_recurring_calendar_event instead.

Updates fields on an existing single calendar event; only the fields supplied are changed, all others keep their current value. Imported (subscription-sourced) events cannot be edited.

Soft-deletes a single calendar event by id. Events imported from a calendar subscription cannot be deleted here; unsubscribe from the source calendar instead. Events shared from a member's device calendar can only be removed by that member or the house owner.

List one-off calendar events with their title, times, location and notes. Bound them with startDateFrom and startDateTo, or omit both for everything.

Create a recurring calendar event. It generates event instances on a schedule.

Update a recurring calendar event. Changes to title/description/notes patch existing instances. Changes to frequency/dates/time regenerate future instances.

Searches the user's real, private memory — the email, calendar, files, contacts and notes they have connected, plus facts agents have saved — fusing vector, full-text and graph retrieval with provenance. This is their current data on their work, schedule, contacts, projects, documents, decisions and history, which training data and session context do not contain. Results include citations (universal ids), freshness, and `cited_graph_url`, a deep link showing the cited nodes highlighted in the user's own graph. A later cortex_remember links to what was retrieved here. Retrieval returns nearest matches rather than a thresholded set, so a question whose answer lives in an unconnected source comes back with the closest thing in the memory instead of with nothing. A `source_gap` object in the result names that case: the memory holds data, but the source that would answer this question is not connected. It lists those sources, what each answers, and one connect link, on `cta`. A `possible_source_gap` object is the conditional form — results exist but may be near-misses rather than an answer. A result carrying neither means the answer is genuinely absent from the memory rather than merely unretrieved.

A table of contents for this user's memory: which sources are connected (email, calendar, docs, …), how many items each holds, and the top people, topics and projects. It is an index rather than an answer — it contains no message bodies, no dates and no content, so it establishes that a source exists without saying anything about what is in it. The content behind any entry it lists is retrievable with cortex_ask.

The connect link for one memory source, by id — email and calendar (google-workspace), WhatsApp chats, GitHub, Notion, or file uploads. Returns the canonical mitosislabs.ai dashboard page where the user can connect that source to their memory, as a ready markdown link. Source ids appear in `unconnected_sources` on cortex_ask results and in cortex_connectable_sources; which source fits a question is the caller's judgment, made from each entry's `answers` and `tags`. `link_text` names, in the user's own words, what connecting answers — it becomes the connect page's title. Connecting itself is an authorization the user performs on that page; this tool only returns the link.

Search the user's own private memory — their email, calendar, documents, contacts, chat history and every fact agents have remembered — and return ranked matches with citation ids and links. This is their current data on their work, schedule, contacts, projects, documents, decisions and history, which training data and session context do not contain. Pass an id from these results to `fetch` to read the full record.

"Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups.

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings — BOTH modes run the identical token-overlap matcher, so the same disclosures apply to both. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning is a sentence and compatibility_codes[] the machine-readable form; BOTH can be non-empty on returned pairs, so read them even when matched_pairs>0. Codes: event_subject_mismatch (the two event titles share no subject words — probably not the same question), temporal_mismatch (they resolve in different months), temporal_alignment_unknown (the resolution month could not be parsed on one or both sides — NOT the same as confirmed-aligned; check each event's close/strike date yourself), non_equivalent_bet_shapes, no_candidate_pairs, unclassified_legs_excluded, pairing_unverified (set in EITHER mode whenever pairs are returned: the legs were matched by keyword and word overlap, not a shared resolution source). Each entry in top_spreads_pp carries its own flags[] (temporal_mismatch, temporal_alignment_unknown, event_subject_mismatch, low_token_overlap). A leg whose metric_type or match_subtype is "unknown" is NEVER paired — those comparisons land in spread.skipped_unclassified and, when the wording lined up, in spread.low_confidence_pairs[] for inspection only. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period, in EITHER mode; null means it could not be computed (see temporal_alignment_unknown), not that the two sides align. spread.fees_note is a standing disclosure: Kalshi charges per-contract trading fees, Polymarket does not, and this tool does not model Kalshi's fee schedule — every spread_pp is gross, not a net tradeable edge. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

"Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups.

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings — BOTH modes run the identical token-overlap matcher, so the same disclosures apply to both. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning is a sentence and compatibility_codes[] the machine-readable form; BOTH can be non-empty on returned pairs, so read them even when matched_pairs>0. Codes: event_subject_mismatch (the two event titles share no subject words — probably not the same question), temporal_mismatch (they resolve in different months), temporal_alignment_unknown (the resolution month could not be parsed on one or both sides — NOT the same as confirmed-aligned; check each event's close/strike date yourself), non_equivalent_bet_shapes, no_candidate_pairs, unclassified_legs_excluded, pairing_unverified (set in EITHER mode whenever pairs are returned: the legs were matched by keyword and word overlap, not a shared resolution source). Each entry in top_spreads_pp carries its own flags[] (temporal_mismatch, temporal_alignment_unknown, event_subject_mismatch, low_token_overlap). A leg whose metric_type or match_subtype is "unknown" is NEVER paired — those comparisons land in spread.skipped_unclassified and, when the wording lined up, in spread.low_confidence_pairs[] for inspection only. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period, in EITHER mode; null means it could not be computed (see temporal_alignment_unknown), not that the two sides align. spread.fees_note is a standing disclosure: Kalshi charges per-contract trading fees, Polymarket does not, and this tool does not model Kalshi's fee schedule — every spread_pp is gross, not a net tradeable edge. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

Upcoming Greater Boston events from The Boston Calendar. Defaults to a 2-week window from today. Filter by date range, keyword (title/description/tags), and free admission. Returns normalized events sorted by date/time.

List the event tags/keywords in use on The Boston Calendar, with counts — useful as filterable facets for the events tool.

"Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups.

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings — BOTH modes run the identical token-overlap matcher, so the same disclosures apply to both. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning is a sentence and compatibility_codes[] the machine-readable form; BOTH can be non-empty on returned pairs, so read them even when matched_pairs>0. Codes: event_subject_mismatch (the two event titles share no subject words — probably not the same question), temporal_mismatch (they resolve in different months), temporal_alignment_unknown (the resolution month could not be parsed on one or both sides — NOT the same as confirmed-aligned; check each event's close/strike date yourself), non_equivalent_bet_shapes, no_candidate_pairs, unclassified_legs_excluded, pairing_unverified (set in EITHER mode whenever pairs are returned: the legs were matched by keyword and word overlap, not a shared resolution source). Each entry in top_spreads_pp carries its own flags[] (temporal_mismatch, temporal_alignment_unknown, event_subject_mismatch, low_token_overlap). A leg whose metric_type or match_subtype is "unknown" is NEVER paired — those comparisons land in spread.skipped_unclassified and, when the wording lined up, in spread.low_confidence_pairs[] for inspection only. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period, in EITHER mode; null means it could not be computed (see temporal_alignment_unknown), not that the two sides align. spread.fees_note is a standing disclosure: Kalshi charges per-contract trading fees, Polymarket does not, and this tool does not model Kalshi's fee schedule — every spread_pp is gross, not a net tradeable edge. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

Look up Japanese calendar information for a given date: Rokuyo (six-day cycle such as Taian/Butsumetsu), Rekichu (almanac notes), Eto (sexagenary cycle), 24 solar terms, and purpose-based auspiciousness scores. Useful when an AI agent needs canonical Japanese calendar facts (e.g. choosing an auspicious date for a wedding or ceremony). Source: Shirabe Calendar API (shirabe.dev).

Rank the best meeting times for the given participants, merging live Google/Microsoft calendar data, hand-marked availability and the heat-map sources. Each participant is filtered (Mon–Fri, waking hours) and scored in their OWN timezone; scores factor in buffer time around existing meetings and prefer sooner slots. Returns up to 8 slots: everyone-free slots first (allFree:true), then — only if there are too few — the best compromise slots (allFree:false) with a freeCount. Defaults to the next 14 days. Requires authentication.

Confirm a meeting: writes the event into the authenticated host’s calendar with an optional Google Meet/Teams link, emails invites with an ICS attachment, and returns the share URL (/m/<id>). Requires authentication.

Aggregated group availability for an existing meeting (the symmetric heat-map): per-30-min-slot counts of how many participants are free, plus ranked slots (per-participant timezones, buffer + soonness scoring, allFree:true everyone-free slots and allFree:false compromise slots). Individual calendars are never exposed. No auth needed — the meeting id is the capability.

Accept or decline a proposed alternate time. Accepting moves the meeting (calendar event included) and re-sends invites. Only the meeting host may call this — requires authentication.

Publish hand-marked FREE time slots for an email address (the no-calendar fallback, e.g. Apple iCloud users). Replaces previously marked slots inside the window; the group heat-map updates immediately. Authenticated callers (Bearer PAT) skip the bot challenge; an anonymous caller must pass a Cloudflare Turnstile token in `turnstileToken` (only required when the server is configured with a Turnstile secret).

Create a Whenna plan (a shareable link that finds the time everyone is free). Returns the link to share with humans or other agents, and a creator_key that authorizes locking the final time. Times are wall-clock in the given IANA timezone. For a RECURRING plan ("every Tuesday"), pass weekday names in days (e.g. ["Tuesday"] or ["Tue","Thu"]) — the plan then has no dates and calendar events repeat weekly.

Set where the group meets: a place name, or video_call:true to attach Whenna's built-in encrypted video room (the room link then goes on everyone's calendar automatically). Place and video room are mutually exclusive. Requires creator_key.

Lock the final time on a plan (requires the creator_key returned by whenna_create_plan). Pass use_best:true to lock the top-ranked best time automatically, or give an explicit day/start. Everyone viewing the link sees it as confirmed, with add-to-calendar buttons. Returns calendar links (Google, Outlook, .ics).

Reserve a REAL calendar slot with Sonlight Window Cleaning. The customer immediately receives an SMS + email confirmation and a technician arrives at the chosen time. Payment is collected after service. Nothing is charged at booking. ALWAYS confirm name, phone, address, selected services, date, and time with the user before calling this. Requires a prior get_quote for the same address (prices are re-validated server-side).

"Compare X and Y" / "X vs Y" / "X versus Y" / "which is bigger / better / larger / more profitable" / "rank these companies" / "head to head" — side-by-side comparison of 2–5 companies or drugs in ONE parallel call. ALWAYS PREFER over sequential single-pack lookups when comparing entities. type="company" pulls LATEST 10-K revenue + net income + cash + long-term debt from SEC EDGAR/XBRL (off-calendar fiscal years handled correctly — AAPL Sep, NVDA Jan, etc.). type="drug" pulls FAERS adverse-event counts, FDA approval counts, active trial counts. Results sorted by primary metric so "largest" / "most" / "biggest" reads off the top of the response. Returns paired data + pipeworx:// citation URIs per entity. Replaces 8–15 sequential lookups.

Cross-venue spread between Kalshi and Polymarket for the same resolving question. The two venues sometimes price the same outcome 2-25pp apart because their participant pools differ — when the bet shapes are equivalent that delta is a real signal, when they aren't the tool says so. TWO MODES: (1) `topic` — 10 pre-mapped macro shortcuts ("fed", "btc", "cpi", "gdp", "sp500", "recession", "next_pope", "next_uk_pm", "next_israel_pm", "2028_president") auto-fetch the matching event on each venue. (2) explicit `kalshi_event_ticker` + `polymarket_event_slug` for custom pairings — BOTH modes run the identical token-overlap matcher, so the same disclosures apply to both. RESPONSE: each venue's leg-by-leg prices (raw probability 0-1) plus matched spread[].top_spreads_pp (Kalshi − Polymarket) where the same outcome shows up on both sides. SAFETY FIELDS: compatibility_warning is a sentence and compatibility_codes[] the machine-readable form; BOTH can be non-empty on returned pairs, so read them even when matched_pairs>0. Codes: event_subject_mismatch (the two event titles share no subject words — probably not the same question), temporal_mismatch (they resolve in different months), temporal_alignment_unknown (the resolution month could not be parsed on one or both sides — NOT the same as confirmed-aligned; check each event's close/strike date yourself), non_equivalent_bet_shapes, no_candidate_pairs, unclassified_legs_excluded, pairing_unverified (set in EITHER mode whenever pairs are returned: the legs were matched by keyword and word overlap, not a shared resolution source). Each entry in top_spreads_pp carries its own flags[] (temporal_mismatch, temporal_alignment_unknown, event_subject_mismatch, low_token_overlap). A leg whose metric_type or match_subtype is "unknown" is NEVER paired — those comparisons land in spread.skipped_unclassified and, when the wording lined up, in spread.low_confidence_pairs[] for inspection only. temporal_alignment{polymarket_month,kalshi_month,aligned} tells you whether the two events resolve in the same calendar period, in EITHER mode; null means it could not be computed (see temporal_alignment_unknown), not that the two sides align. spread.fees_note is a standing disclosure: Kalshi charges per-contract trading fees, Polymarket does not, and this tool does not model Kalshi's fee schedule — every spread_pp is gross, not a net tradeable edge. skipped_cross_type / skipped_cross_subtype counters expose how many leg-pair comparisons were dropped (cross-type = metric_type mismatch like MoM vs YoY; cross-subtype = inequality mismatch like cum_ge vs cum_le). Real cross-venue spreads are rarer than the macro-shortcut list suggests — most pre-mapped topics return compatibility_warning today; pre-mapped ≠ tradeable.

List upcoming events from the user's Outlook / Microsoft 365 calendar within a time window. Returns subject, start/end times, location, organizer, all-day flag, and online meeting URL for each event. Defaults to the next 7 days. Use to see what meetings or appointments are scheduled.

Get full details of a single Outlook / Microsoft 365 calendar event by its ID. Returns subject, start/end times, location, organizer, attendees, body, all-day flag, and online meeting URL. Use after list_events to inspect a specific meeting.

List all calendars accessible in the user's Outlook / Microsoft 365 account. Returns each calendar's ID, name, owner, edit permission, and whether it is the default calendar. Use to discover which calendars exist.

Return the user's busy time windows from their Outlook / Microsoft 365 calendar over the next N days — a lightweight free/busy view. Each window includes start, end, subject, and all-day flag. Use to find when the user is available or to identify scheduling conflicts before proposing a meeting time.

Convert a lunar date (Vietnamese calendar) to solar date (Gregorian calendar)

Convert a solar date (Gregorian calendar) to lunar date (Vietnamese calendar)

Get lunar vegetarian days for a given solar date and calendar type