Folionomiq

Measures a stock/ETF portfolio from its price history, in plain sentences.

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Measure Portfolio: The complete measurement of one portfolio in a single call: how many independent bets it holds, which holding carries risk out of line with its money, the companies owned through it
  • Compare Portfolios: Two to eight separate portfolios (not a change to one) measured over one shared window of price history: growth, volatility, worst fall, and how each moved against the others. For
  • Test A Change: Any change to one portfolio, measured before it is made: the current and the proposed holdings side by side on the same price history (structure, risk, worst falls, and what the change

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Measures a stock/ETF portfolio from its price history, in plain sentences.

  • How many real bets the holdings add up to (correlation, not ticker count)
  • Look-through: what you own through your funds, with the share of money we can see
  • Past crises in money: what this mix did in 2008, 2020, 2022
  • Before/after of a proposed change, and side-by-side comparison of up to 8 portfolios

Descriptive only: no advice, no forecasts, no scores. No account, no auth, portfolios are not stored. Every result carries its method, data window and source.

Как подключить

Как подключить Folionomiq к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://folionomiq--dzainea.run.tools

  1. Откройте Claude (сайт claude.ai или приложение для компьютера).
  2. Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
  3. Нажмите Добавить пользовательский коннектор (Add custom connector).
  4. Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
  5. В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить Folionomiq к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://folionomiq--dzainea.run.tools

  1. Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
  2. Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
  3. Откройте Настройки → Коннекторы и нажмите Создать (Create).
  4. Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
  5. В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
  6. В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить Folionomiq к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://folionomiq--dzainea.run.tools

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

  1. В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
  2. Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
  3. Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (22)

Технические названия из tools/list. Нужны только разработчикам.

measure_portfolioThe complete measurement of one portfolio in a single call: how many independent bets it holds, which holding carries risk out of line with its money, the companies owned through its funds (with how much of the money that view covers), what past crises did to it in money and how long it took to come back, and the numbered report. Each part is also available on its own, faster: portfolio_structure, look_through, past_crises, portfolio_report. Descriptive: no forecast, no advice.
compare_portfoliosTwo to eight separate portfolios (not a change to one) measured over one shared window of price history: growth, volatility, worst fall, and how each moved against the others. For a before-and-after of one portfolio, test_a_change. Says what each was; does not say which to hold.
test_a_changeAny change to one portfolio, measured before it is made: the current and the proposed holdings side by side on the same price history (structure, risk, worst falls, and what the change adds or removes). For a single new holding, check_before_you_buy says more; for one holding at every weight, sweep_holding. The 'after' figures are counterfactual. Never says whether to make the change.
search_symbolsFinds the ticker when the holder gives a name, part of a ticker or an ISIN (for example 'Vanguard total world' gives VT), with the exchange it trades on. Useful before a measurement whenever a ticker is not certain. Listings nobody here has checked are marked unchecked.
validate_symbolsChecks a list of tickers before a measurement: which have usable price history, which do not, and the closest listing where a symbol is ambiguous.
portfolio_structureOnly the structure of one portfolio: how many independent bets its holdings add up to (from how their prices moved, not how many tickers there are), and each holding's share of the risk beside its share of the money, over the full record and over recent years.
look_throughOnly the companies owned through the funds of one portfolio, added up across funds: the largest names and their share of the whole portfolio, names reached through more than one fund, sectors, and how much of the money this view covers. Figures are minimums: funds publish their largest holdings.
past_crisesOnly past crises for one portfolio: 2008, 2020, 2022 and others inside its price history, with the fall, the worst day and the days it took to come back, in money when amounts are given. Crises before a holding existed are named as not tested. Measured, not forecast.
portfolio_reportOnly the written report on one portfolio: every figure numbered F1, F2... beside the method and window behind it, so each can be quoted by its number. The same report measure_portfolio includes, without the other sections.
factor_exposureHow one portfolio's daily moves line up with four common patterns (the market, small versus large companies, value versus growth, momentum), which of those sensitivities are distinguishable from zero, and how much of the movement the patterns explain.
currency_effectFor a portfolio held in one currency but priced partly in others: how much of it is outside the base currency, and what exchange-rate moves added to its growth, volatility and worst fall compared with the same holdings currency-hedged. Needs base set to the holder's currency to mean anything.
health_axesOne portfolio answered along three separate questions (what is its risk built from, how did it behave when markets broke, what did it pay for the risk taken), each with its own reading and figures. For whether anything is off in how it is built, rather than what it is. Readings, not a grade: no overall score is returned.
sweep_holdingOne holding already in the portfolio, measured at every weight from none to all (the rest of the money redistributed in proportion): volatility, its share of the risk and the independent bets at each point, and whether most of the change comes from the first slice. For how much of it is enough to change anything. Counterfactual; never says what weight to hold.
reverse_stressStarts from a loss the holder names (as a fraction: 0.25 is a quarter) and reports the least extreme combination of market moves that would produce it on this portfolio, beside the worst each of those moves actually did in the record. No probability is computed.
return_historyWhat one portfolio returned over its record: growth per year (and after inflation), best and worst months and years, the range of any 12 months in a row, monthly returns by year, and how far the weights drift between rebalances. Past record, not a forecast.
plain_findingsThree or four plain-language sentences about one portfolio (what its risk is built from and its worst historical fall), each with the window it rests on. The shortest and fastest answer, with no tables and no numbered report; every figure is in measure_portfolio.
last_priceThe latest daily close for each ticker, in the base currency and in its own, with the date, for turning a number of shares into an amount. A single figure per ticker; no price history is returned.
asset_infoOne fund or share on its own, no portfolio needed: name, type, exchange, yearly cost when published, its measured return, volatility and worst fall, and for a fund its largest holdings and sectors.
simulate_pathsSimulated, not a forecast: 4,000 paths resampled from one portfolio's own price history, with optional monthly additions; where the middle path and the outer tenths end after the years asked, in money and in today's money, and the share of paths ending below what was put in. It assumes the future pays what the record paid, and it is refused when the record is too short or too extreme for the years asked.
walk_forwardWhether re-optimising an allocation would have helped: refit on the years before each date, hold it on prices it had not seen, repeat, and compare that record with the portfolio actually held and with equal weight. Says whether refitting bought anything measurable. Returns the record, never an allocation to hold.
check_before_you_buyBefore adding one new holding, with a given amount, to an existing portfolio: how much of it is already owned through the current funds (from the fund's SEC filing when there is one), whether it adds an independent bet, and what past crises would have done with it included. For any other change (removing, reweighting, several at once), test_a_change. Counterfactual; never says whether to buy.
living_off_itFor someone living off a portfolio: replays a yearly withdrawal, raised with real inflation, from every start month the portfolio's own history allows; how many starts lasted the full span, how many ran out and when, the lowest point from the worst start, and the highest yearly rate that ran out from no start in the record. Replayed, not simulated; a count of starts, never a probability; a span the record is too short for is said, not invented.