tw-finance

Taiwan finance open data: ETF, funds, TAIEX, sentiment, business climate, FX.

CommunityDegradedNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Taiwan finance open data: ETF, funds, TAIEX, sentiment, business climate, FX. Free & read-only.

    How to connect

    How to connect tw-finance to Claude

    The server address to paste into Claude settings:

    https://fininfostation.com/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect tw-finance to ChatGPT

    The server address to paste into ChatGPT settings:

    https://fininfostation.com/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect tw-finance to Cursor

    The server address to paste into Cursor settings:

    https://fininfostation.com/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (15)

    Raw names from tools/list. Only developers need these.

    search以一段查詢字串搜尋本站的 ETF、台股、基金與資料集，回傳可引用的清單（id／title／url）。id 可交給 fetch 取完整內容。A single query string; returns citable results for Taiwan ETFs, stocks, funds and datasets.
    fetch以 search 回傳的 id 取該筆的完整內容（id／title／text／url／metadata）。A string which is a unique identifier for the search document.
    taiwan_market_overview台灣加權指數（TAIEX）最新官方收盤、市場廣度（漲跌家數）、台股情緒分數、台指選擇權 Put/Call 比一次取得。Taiwan market snapshot: TAIEX close, breadth, sentiment, PCR.
    etf_lookup以代號查台灣上市 ETF：名稱/發行投信/追蹤指數/市價/折溢價/費用率等基本資料。Look up a Taiwan-listed ETF by code (e.g. 0050).
    etf_price_history取 ETF 每日收盤價序列（預設近 12 個月、可調 months 1-120）。Daily close history for a Taiwan ETF.
    fund_lookup以代號或名稱關鍵字查台灣可銷售基金（境內投信/境外/期信）：最新淨值/淨值日/幣別/類型/總代理/今年以來報酬。Search Taiwan-distributed funds by code or name keyword.
    fund_nav_history取基金每日淨值序列（預設近 12 個月、可調 months 1-120；境內主級別最深約 10 年）。Daily NAV history for a fund.
    market_sentiment台股情緒綜合分數（本站自製中性參考、含分項）與美股 CNN Fear & Greed（含 CNN 原始時點）。Taiwan + US (CNN F&G) market sentiment.
    business_climate國發會景氣燈號：最新月燈號/綜合分數/9 項構成指標逐項檢查值與分數/下期發布日（官方預告）。NDC business climate signal with all 9 components.
    fx_rates主要貨幣即期匯率（多源交叉：ECB/台銀）含當日與近 1 週/1 月/3 月變化；可指定 pair（如 USD/TWD）。Spot FX rates with multi-period changes.
    data_catalog列出本站「資料形狀 × 資料集」登錄表：有哪些 point（單值）／series（時間序列）／table（表格）／query（條件篩選＋群體聚合）資料集，各自的單位、識別碼種類、來源與深連結；query 母體另附可用欄位、運算子與可排序鍵。先呼叫本工具，即可組合出後續查詢。Catalog of datasets by shape (point/series/table/query) — call this first to compose queries.
    data_point取「一個標的 × 一個欄位 × 一個時點」的單值，如 0050 的折溢價、基金最新淨值、USD/TWD 匯率、景氣對策信號綜合分數。dataset 取自 data_catalog 的 point 清單；回應必附單位、資料日與來源。Single current value for one security and field.
    data_series取「一個標的 × 一個欄位 × 一段時間」的時間序列，如 ETF 日收盤、基金淨值歷史。每點只有日期與值；資料缺口會以 gapNote 誠實標示、不靜默補值。Time series for one security and field.
    data_table取「一個標的的多列資料」，如 ETF 全成分股與權重、景氣對策信號 9 項構成指標、主要貨幣對一覽。回應含欄位定義（columns）與列（rows），截斷時標 truncated。Multi-row table for one security.
    data_query對一個母體下條件篩出一組標的，並對整組計算聚合統計（count／coverage／min／max／mean／median／sum），如「費用率 0.4% 以下的被動 ETF，其費用率中位數」。where 語法為「欄位 運算子 值」以 and 連接（例 fee<=0.4 and type=passive）。回應必附母體大小 population 與欄位覆蓋率 coverage（有幾檔真的有這個欄位）。注意：績效欄位可用於 where 篩選與聚合統計，但不得作為排序鍵——排序即排名，本站不對個別商品做推薦。Filter a universe and aggregate over the matched set.