ceyloncharts

Live and historical market data for the Colombo Stock Exchange (CSE) — Sri Lanka's only stock exchange — via 13 tools covering prices, fundamentals…

От сообществаРаботаетБез входаRU / СНГБесплатноТолько чтение

Что умеет

  • Get Symbols: List available CSE symbols with metadata. Optionally search by company name and/or sector. Returns CSV (symbol,name,sector,industry,is_active,last_updated).
  • Get Ohlc Data: Get OHLCV (open, high, low, close, volume) data for a CSE symbol. Prices are adjusted for splits by default (clean price action), but NOT for rights issues or dividends, unless requeste
  • Get Financial Statement: Get full line-item detail for one financial statement (income statement, balance sheet, or cash flow statement) for a CSE symbol — every quarter available, one row per line it

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Live and historical market data for the Colombo Stock Exchange (CSE) — Sri Lanka's only stock exchange — via 13 tools covering prices, fundamentals, technicals, and macro data.

Market data

  • get_symbols — search listed companies by name or sector
  • get_ohlc_data — historical OHLCV price history, split-adjusted
  • get_market_summary, get_indices, get_index_data — index-level snapshots and history
  • get_technicals — moving averages, RSI, relative-strength rating

Screening

  • screen_stocks — filter by EMA position, RS rating, 52-week highs/lows, unusual volume
  • screen_indices — sector-level screening

Company & macro data

  • get_financial_statement — income statement, balance sheet, cash flow
  • get_corporate_actions — dividends, splits, rights issues
  • get_announcements — company disclosures
  • get_macro_data, get_macro_series — economic indicators

Access: OAuth 2.0 (authorization code + PKCE), scopes mcp:read and mcp:analyze. Dynamic client registration supported — no manual API key request needed. Full setup: auth.md.

Built and maintained by CeylonCharts — free charting and market data for Sri Lankan retail investors.

Как подключить

Как подключить ceyloncharts к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://ceyloncharts--creondesigns.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 ceyloncharts к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://ceyloncharts--creondesigns.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 ceyloncharts к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://ceyloncharts--creondesigns.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 (13)

Технические названия из tools/list. Нужны только разработчикам.

get_symbolsList available CSE symbols with metadata. Optionally search by company name and/or sector. Returns CSV (symbol,name,sector,industry,is_active,last_updated).
get_ohlc_dataGet OHLCV (open, high, low, close, volume) data for a CSE symbol. Prices are adjusted for splits by default (clean price action), but NOT for rights issues or dividends, unless requested. Defaults to the most recent 50 trading days; if more history is available the response says so and how to page further back with offset. Returns CSV (date,open,high,low,close,volume) preceded by a note if the symbol was resolved from a name/typo, if the company has other instruments, or if any corporate actions (splits/rights/dividends) fall within the requested range. If the input is ambiguous, returns JSON candidates instead.
get_financial_statementGet full line-item detail for one financial statement (income statement, balance sheet, or cash flow statement) for a CSE symbol — every quarter available, one row per line item. Cash-flow figures are cumulative (year-to-date) while income-statement figures are per-quarter — don't diff adjacent columns on the cash flow statement as if they were quarterly deltas. Returns CSV (label,canonical_key,<one column per fiscal period>), or JSON candidates if the input is ambiguous.
get_announcementsGet general CSE company disclosures for a symbol — board changes, AGM/EGM notices, listings, trading suspensions/resumptions, name changes, and other regulatory announcements. For dividends, rights issues, or share splits specifically, use get_corporate_actions instead — it has the parsed, structured detail (amounts, ratios, ex-dates) that this tool's raw announcement text does not. Returns CSV (date,type,description,pdf_url), or JSON candidates if the input is ambiguous.
get_macro_seriesList available macroeconomic series definitions. Optionally search by name. Returns CSV (id,name,description,frequency,unit,source).
get_macro_dataGet macroeconomic data for a specific series. Returns CSV (date,value), or JSON candidates if the input is ambiguous.
get_indicesList CSE market/sector indices (ASPI, S&P SL20, and industry sub-indices). Optionally search by name. Returns CSV (symbol,name,index_code,index_name,is_main_index).
get_index_dataGet historical data for a CSE market/sector index. Returns CSV (date,open,high,low,close,change,change_pct,sector_turnover,sector_volume,sector_trades,price_index,per,pbv,dy,companies_traded,companies_listed), or JSON candidates if the input is ambiguous. Headline indices (ASPI, S&P SL20) populate open/high/low/close; industry sub-indices instead populate sector_turnover/sector_volume/sector_trades and leave high/low empty.
screen_stocksScreen CSE stocks by pre-computed technical criteria (moving-average position, relative-strength rating, 52-week range, unusual volume). Every filter is optional and AND-combined; omit a filter to not constrain on it. E.g. above_ema50=true & above_ema200=true & rs_rating_min=80 finds market-leading uptrends; is_52w_high=true finds stocks making new highs today; vol_vs_sma50_pct_min=100 finds unusual volume (trading at 2x+ its 50-day average). Returns CSV, one row per matching stock.
screen_indicesScreen CSE sector/headline indices (ASPI, S&P SL20, and industry sub-indices) by the same pre-computed technical criteria as screen_stocks — moving-average position and relative-strength rating. There is no 52-week-range or volume filter here (those are not tracked for indices). Use this to find which sectors are in a sustained uptrend/downtrend, as distinct from get_indices/get_index_data which show a single day's performance. Returns CSV, one row per matching index.
get_technicalsGet pre-computed daily technicals (moving averages, relative-strength rating, 52-week range, volume anomalies) for a CSE stock OR a sector/headline index (ASPI, S&P SL20, industry sub-indices) — one tool for both. Returns CSV, one row per trading day, most recent last. Defaults to the most recent 50 trading days; if more history is available the response says so and how to page further back with offset. If the input is ambiguous, returns JSON candidates instead.
get_market_summaryGet a daily/weekly/monthly market-wide overview: top gainers/losers, top by volume/turnover/crossings, ASI and S&P SL20 performance, and top/bottom performing sectors. A weekly or monthly summary requested mid-period covers what has happened so far (e.g. Monday through today for a weekly summary requested on a Wednesday), not a wait for the period to finish and not the prior complete period — the response's isPartialPeriod field says which case applies. Returns JSON (not CSV — this is a bundle of several small lists, not one table).
get_corporate_actionsGet a calendar of corporate actions (dividends, rights issues, share splits) — announcement details, not just a price-adjustment factor. This is the tool for dividends/rights/splits specifically; for other company disclosures (board changes, AGM/EGM notices, trading suspensions, etc.), use get_announcements instead. Omit all filters to browse every corporate action in the dataset, past and future, oldest first; pass from=<today> to jump straight to upcoming ones, which is the most common need. Optionally scope to one company (matches every one of its share classes, not just one) and/or one kind. Returns CSV, one row per action. If the symbol is ambiguous, returns JSON candidates instead.