# China Stocks (npm · @pipeworx/mcp-china-stocks)

China A-shares MCP. Keyless.

- Trust score: 83/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-07

## Components

- remote · `gateway.pipeworx.io`: 86/100, [markdown](https://verifymcp.io/servers/pipeworx-io-china-stocks/china-stocks-mcp.md), [page](https://verifymcp.io/servers/pipeworx-io-china-stocks/china-stocks-mcp)
- npm · `@pipeworx/mcp-china-stocks`: 83/100 (this document), [markdown](https://verifymcp.io/servers/pipeworx-io-china-stocks/pipeworx-mcp-china-stocks.md), [page](https://verifymcp.io/servers/pipeworx-io-china-stocks/pipeworx-mcp-china-stocks)

## Channel facts

- Registry: `npm`
- Package: `@pipeworx/mcp-china-stocks`
- Version: `0.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-07.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to pipeworx-io/mcp-china-stocks).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 5371 tokens (~335/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 16 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the China Stocks MCP server?

China Stocks runs locally as an npm package, launched with npx -y @pipeworx/mcp-china-stocks. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add pipeworx-io-china-stocks -- npx -y @pipeworx/mcp-china-stocks
```

### Cursor

```json
{
  "mcpServers": {
    "pipeworx-io-china-stocks": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-china-stocks"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "pipeworx-io-china-stocks": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-china-stocks"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add pipeworx-io-china-stocks -- npx -y @pipeworx/mcp-china-stocks
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "pipeworx-io-china-stocks": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@pipeworx/mcp-china-stocks"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add pipeworx-io-china-stocks --command npx --arg -y --arg @pipeworx/mcp-china-stocks
```

### Hermes

```yaml
mcp_servers:
  pipeworx-io-china-stocks:
    command: "npx"
    args: ["-y", "@pipeworx/mcp-china-stocks"]
```

### Netclaw

```json
{
  "McpServers": {
    "pipeworx-io-china-stocks": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@pipeworx/mcp-china-stocks"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add pipeworx-io-china-stocks -t stdio -c npx -a -y @pipeworx/mcp-china-stocks
```

### Other

```json
{
  "mcpServers": {
    "pipeworx-io-china-stocks": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-china-stocks"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-06 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-04 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 80, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-31 (score 80, +1)

- [functional regression] Security disclosure: fail → unverified
- [functional] Package version: 0.2.0 → 0.2.1

### 2026-10-29 (score 79)

First indexed and scored.

## MCP tools (16)

### `ashares_limit_up` (~199 tokens)

The Chinese A-share market's LIMIT-UP board (涨停板) for a trading day — how many stocks hit their daily price limit (+10%, or +20% for STAR/ChiNext) and the ranked list of those stocks. Answers 'how many A-shares hit limit up today', 'top limit-up stocks', 'which stocks 涨停'. Each stock includes code, name, price, change %, turnover (成交额), float market cap, turnover rate (换手率), consecutive-board count (连板数 lbc), first/last seal time, seal fund (封板资金), and industry (行业). Source: Eastmoney (keyless).

Input parameters:

- `date` (string): Trading day as YYYYMMDD or YYYY-MM-DD (default: most recent trading day).
- `limit` (number): How many stocks to return, 1–100 (default 30). The total count is always returned regardless.

### `ashares_limit_down` (~228 tokens)

The Chinese A-share market's LIMIT-DOWN board (跌停板) for a trading day — how many stocks hit their daily DOWN price limit (-10%, or -20% for STAR/ChiNext) and the ranked list of those stocks. Answers 'how many A-shares hit limit down today', '跌停家数', 'which stocks 跌停', 'limit-down stock count for a China A-share trading day' — the counterpart to ashares_limit_up, together giving market-wide limit-up/limit-down breadth. Each stock includes code, name, price, change % (negative), turnover (成交额), float market cap, turnover rate (换手率), seal fund (封板资金), last seal time, industry (行业), and P/E. Source: Eastmoney (keyless).

Input parameters:

- `date` (string): Trading day as YYYYMMDD or YYYY-MM-DD (default: most recent trading day).
- `limit` (number): How many stocks to return, 1–100 (default 30). The total count is always returned regardless.

### `ashares_margin_financing` (~439 tokens)

China A-share margin financing and securities lending balance (融资融券余额/两融余额) — the market-wide leverage gauge: aggregate financing balance (融资余额, money borrowed to buy stock), securities-lending balance (融券余额, shares borrowed to short), and their combined total (融资融券余额), for the Shanghai (SSE) and Shenzhen (SZSE) exchanges separately and combined, with day-over-day change. Answers '融资余额', '两融余额', '融资融券余额', 'margin financing balance', 'China A-share margin debt', 'how much margin debt is in the A-share market', 'margin balance day over day change'. Pass a 6-digit SZSE code (0/3/159-prefixed) in `symbol` for that stock's own 融资余额/融券余额/融资融券余额 instead of the market aggregate — SSE (6xxxxx) per-stock detail is not available via any verified keyless route, so a SH code returns a clear not_available message rather than silently substituting. Margin data publishes T+1 (today's figures appear tomorrow morning); a request for a day with nothing published yet or a non-trading day (weekend/holiday) automatically falls back to the last trading day that published, and says so. Amounts in CNY (converted from each exchange's native 元/亿元/万元 units and labelled). Source: SSE query.sse.com.cn (keyless) + SZSE www.szse.cn ShowReport CATALOGID=1837_xxpl (keyless).

Input parameters:

- `date` (string): Trading day as YYYY-MM-DD or YYYYMMDD (default: most recent day with published data). Margin data is T+1, so "today" usually has nothing yet.
- `symbol` (string): Optional 6-digit SZSE code (0/3/159-prefixed, e.g. "000001" 平安银行) for that stock's own margin balance instead of the market-wide aggregate. SSE codes (6xxxxx) are not supported here — no verified key…

### `ashares_market_snapshot` (~161 tokens)

Overall snapshot of the Chinese A-share market — the headline index levels (Shanghai Composite, Shenzhen Component, ChiNext, STAR 50, CSI 300) with change %, day range and turnover, plus market-wide breadth as a sentiment gauge: how many stocks hit limit-up (涨停) and limit-down (跌停) today. Answers 'how is the China A-share market doing', 'Shanghai Composite today', 'A-share market snapshot at close', 'how did Chinese stocks close', '涨跌停家数', 'limit-up limit-down counts today'. For the ranked pools use ashares_limit_up / ashares_limit_down; for market-wide margin financing leverage use ashares_margin_financing. Source: Sina + Eastmoney (keyless).

### `ashares_quote` (~178 tokens)

Real-time quote(s) for Chinese A-share stocks by 6-digit code (Shanghai 6xxxxx, Shenzhen 0xxxxx/3xxxxx, STAR 688xxx, ChiNext 30xxxx, Beijing 8xxxxx/4xxxxx). Returns name, current price, change and change %, open, previous close, day high/low, volume, turnover, and the quote timestamp. Accepts one code or a comma-separated list. Example: ashares_quote({ symbols: "600519,000858" }) for Kweichow Moutai and Wuliangye. Source: Sina (keyless).

Input parameters:

- `symbols` (string, required): One 6-digit code or a comma-separated list, e.g. "600519" or "600519,000001,300750". sh/sz/bj prefixes are accepted but optional.

### `ashares_turnover_ranking` (~522 tokens)

Market-wide ranking of Chinese A-share stocks by turnover / 成交额排名, 成交额前30名, 成交量排名, or 涨跌幅排名 — the whole board (not specific codes), sorted server-side and returned as a ranked list. Answers 'A股成交额前30名', 'top 30 A-shares by turnover today', 'A股成交量排名', 'A-share market-wide ranking by amount/volume/change %', 'which A-shares traded the most today'. Each row has code, name, price, change %, volume (shares), turnover in CNY (成交额), turnover rate %, and industry (行业/板块, when resolvable). Omit `date` (or pass today) for the LIVE board (Sina, real-time). Pass a PAST trading day in `date` for that day's ranking instead of today's — this uses a different, Eastmoney-sourced historical path and only supports `sort:'changepercent'` (涨跌幅排名): no keyless bulk source for a PAST day's turnover amount or volume ranking was found (Sina's live board is the only amount/volume source), so `date` + `sort:'amount'|'volume'` throws a clear error naming that gap rather than silently substituting today's board. A non-trading `date` (weekend/holiday) walks back to the prior trading day automatically.

Input parameters:

- `board` (string): Which board to rank: hs_a = all Shanghai+Shenzhen A-shares (default, 沪深A股), sh_a = Shanghai only (沪市A股), sz_a = Shenzhen only (深市A股), cyb = ChiNext (创业板).
- `date` (string): A PAST trading day, YYYY-MM-DD or YYYYMMDD, for that day's ranking instead of today's live board. Only `sort:'changepercent'` is supported with a past date. Omit for the live board.
- `limit` (number): How many stocks to return, 1–100 (default 30).
- `order` (string): desc (default, highest first) or asc.
- `sort` (string): Rank by turnover amount (成交额, default), change % (涨跌幅), or share volume (成交量). For a PAST `date`, only 'changepercent' is available — 'amount'/'volume' throw a clear error for historical dates (no ke…

### `ashares_capital_flow` (~298 tokens)

Per-stock daily main-capital net inflow history (主力净流入 / 超大单+大单净流入, often called '超大单净流入' in retail trackers) for a Chinese A-share stock or ETF — one row per trading day with net inflow broken down by order size: 超大单 (super-large/institutional), 大单 (large), 中单 (medium), 小单 (small), plus 主力净流入 (main = 超大单+大单combined) in both CNY amount and as a % of that day's turnover. Answers '主力净流入历史', '超大单净流入', '000768最近20个交易日的主力资金流向', 'main capital net inflow history for a China A-share stock', 'which days did big money flow into/out of a stock'. A positive net inflow means net buying pressure from that order-size bucket that day, negative means net selling. Source: Eastmoney push2his fflow/daykline (keyless).

Input parameters:

- `code` (string, required): 6-digit A-share or ETF code, e.g. "000768" (中航西飞) or "515050". sh/sz/bj prefixes accepted but optional.
- `days` (number): How many of the most recent trading days to return, 1–200 (default 20).

### `ashares_billboard` (~283 tokens)

The Chinese A-share market's daily 龙虎榜 (dragon-tiger list / billboard) for a trading day — stocks flagged for unusual price/turnover deviation, with the top seats' buy/sell/net amounts, plus (when present that day) institution-seat (机构专用) net-buy detail and that day's most-active brokerage branches (营业部) market-wide as a 'top brokerages' signal. Answers '龙虎榜', 'dragon tiger list for a date', 'which stocks were on the billboard on 2026-09-24', '机构净买入', 'institution seat net buys', 'top active brokerage seats'. Each listed stock has the reason it was flagged (EXPLANATION, e.g. daily move ≥7%), close price, change %, and billboard buy/sell/net amounts in CNY; stocks that also had institutional-seat activity that day carry institution_net_buy_cny/institution_buy_seats/institution_sell_seats. A non-trading `date` (weekend/holiday) walks back to the prior trading day automatically. Source: Eastmoney datacenter-web (keyless).

Input parameters:

- `date` (string): Trading day as YYYY-MM-DD or YYYYMMDD (default: most recent trading day).
- `limit` (number): How many billboard-listed stocks to return, 1–100 (default 50).

### `ashares_etf_shares` (~327 tokens)

Disclosed fund-share-count (基金份额) and net-asset history for a Chinese-listed ETF — period-end total shares outstanding (期末总份额), the period's subscriptions/redemptions (期间申购/赎回), and period-end net assets (期末净资产), in shares and CNY. Answers '基金份额变动', 'ETF shares outstanding history', '515050规模变动', 'how many shares outstanding does this ETF have over time'. IMPORTANT: this is NOT a daily series — Chinese ETFs publicly disclose 份额 only at quarter-end plus occasional ad-hoc material-change dates (confirmed live for 515050/561980/588170/588200), not every trading day; a `from`/`to` window with no disclosure inside it returns found:false naming the nearest disclosed dates rather than fabricating daily rows. For a daily PRICE series use ashares_daily_history; this tool is share-count/AUM only. Source: Eastmoney fund F10 archive (keyless).

Input parameters:

- `code` (string, required): 6-digit ETF code, e.g. "515050", "561980", "588170", "588200", or "512000".
- `from` (string): Earliest disclosure date to include, YYYY-MM-DD or YYYYMMDD (inclusive). Default: no lower bound (full history, newest first, capped).
- `to` (string): Latest disclosure date to include, YYYY-MM-DD or YYYYMMDD (inclusive). Default: today (no upper bound in practice).

### `ashares_earnings_forecast` (~182 tokens)

Company-issued earnings guidance (业绩预告) for a Chinese A-share stock — the company's own forecast announcements with predicted profit range (lower/upper bounds in CNY), year-over-year change %, forecast type (略增/预增/扭亏 etc.), and the company's stated reason. Answers '业绩预测', '业绩预告', 'earnings forecast/guidance for a China A-share company like 华工科技 000988'. Most recent reports first. Source: Eastmoney datacenter (keyless).

Input parameters:

- `limit` (number): How many forecast announcements to return, 1–20 (default 4, newest first).
- `symbol` (string, required): 6-digit A-share code, e.g. "000988" (华工科技) or "600519" (贵州茅台).

### `ashares_analyst_consensus` (~122 tokens)

Analyst consensus estimates (盈利预测) for a Chinese A-share stock — per forecast year: consensus EPS, P/E at current price, net profit attributable to parent (归母净利润), and total operating revenue, in CNY. Answers "analyst estimates / 盈利预测 / forecast EPS for a China A-share like 000988". Source: Eastmoney datacenter (keyless).

Input parameters:

- `symbol` (string, required): 6-digit A-share code, e.g. "000988" or "300750" (宁德时代).

### `ashares_daily_history` (~347 tokens)

Daily OHLCV history (历史日线) for one or more Chinese A-share stocks over a date range — open, high, low, close, volume, and day-over-day change % per trading day. Answers '300418在2026-08-31到2026-09-03的收盘价和涨跌幅', 'daily closes for 600519 last week', 'history for 000858 and 300750 this month', '涨跌幅历史', '历史成交量'. Up to 20 comma-separated 6-digit codes. change_pct is computed from consecutive closes within the returned range (the first row has no prior close in range, so it is null); turnover amount (成交额) is not exposed by this daily-bar source, so amount_cny is reported as "not_available" rather than estimated — use ashares_quote or ashares_turnover_ranking for same-day turnover amount. Source: Tencent/gtimg fqkline (keyless).

Input parameters:

- `adjust` (string): Price adjustment for splits/dividends: qfq = forward-adjusted (default, prices comparable to today), hfq = backward-adjusted, none = raw unadjusted prices.
- `codes` (string, required): One 6-digit code or a comma-separated list, up to 20, e.g. "300418" or "300418,300364,002131". sh/sz/bj prefixes accepted but optional.
- `end` (string): End date, YYYY-MM-DD or YYYYMMDD (inclusive). Default: today.
- `start` (string, required): Start date, YYYY-MM-DD or YYYYMMDD (inclusive).

### `ashares_intraday_bars` (~590 tokens)

Intraday minute bars (分钟线/分时/分钟K线) for Chinese A-share stocks/ETFs on a given trading日/交易日, with cumulative volume and turnover (累计成交量/累计成交额) computed up to a requested time of day (截至<time>, e.g. 截至11:05) — answers '515050在2026-09-01这个交易日截至11:05的累计成交量和累计成交额', '600519某个交易日截至某时刻的累计成交量和成交额', 'cumulative volume for 600519 up to 11:05 on a past trading day', 'intraday minute bars for an A-share on a specific date'. ashares_quote is realtime-only (today, right now) and ashares_daily_history is end-of-day-only (no intraday granularity) — this tool is for a PAST trading日's intraday trajectory. Returns the interval bars for that day plus cumulative_volume_shares/cumulative_turnover_cny summed from the day's open through `up_to` (or the whole day if `up_to` is omitted). `symbols` takes a bare 6-digit code (e.g. "515050") or the sh/sz/bj-prefixed form, same as ashares_quote. Bounded lookback: the upstream caps total bars at ~1950 regardless of interval, so retention shrinks as the interval shrinks — roughly 8 trading days at 1-minute, 40 at 5-minute (the default), 110 at 15-minute, a year at 30-minute, two years at 60-minute — and it slides forward daily. A `date` older than a result's `earliest_bar_date_available` is out of range for that interval; try a coarser interval, or use ashares_daily_history for daily (not intraday) history further back. Source: Sina (keyless).

Input parameters:

- `date` (string, required): The trading day the bars are for, YYYY-MM-DD or YYYYMMDD, e.g. "2026-09-01".
- `interval` (string): Bar interval in minutes. Default "5". Smaller intervals keep a shorter lookback window — see the tool description.
- `symbols` (string, required): One 6-digit code or a comma-separated list, up to 5, e.g. "515050" or "600519,000001". sh/sz/bj prefixes accepted but optional. ETF codes work the same as stock codes.
- `up_to` (string): Time of day (24-hour, Beijing time) to cumulate volume/turnover through, e.g. "11:05". Omit for the whole trading day (or "as of now" if `date` is today and the market is open).

### `ashares_technical_indicators` (~688 tokens)

Technical indicators for Chinese A-share stocks and ETFs (均线/布林/MACD/KDJ) — MA (moving averages, any windows, default MA5/MA10/MA20/MA60), BOLL (Bollinger Bands, default 20-period ×2 std dev), MACD (DIF/DEA/柱, default 12/26/9), and KDJ (K/D/J, default 9/3/3), computed from this pack's own daily OHLCV history (same source and codes as ashares_daily_history — ETF codes like 515050/588170/561980 work the same as stock codes). Answers '515050通信ETF华夏最近20个交易日MA5/MA10/MA20/BOLL/MACD/KDJ', '603986兆易创新周线MACD是否死叉', 'MA20 and BOLL for an A-share ETF', '布林带', '均线', '金叉死叉'. Internally fetches extra lookback history before `start` so the indicators are warmed up (MA60/MACD need ~60+ trading days of prior data) — only the requested [start, end] range is returned. MACD histogram uses the common Chinese charting convention 柱=2×(DIF−DEA); KDJ smoothing is the standard 3/3 recursive form seeded at 50. Up to 5 comma-separated codes per call (indicator math is heavier than a plain OHLCV pull). Source: Tencent/gtimg fqkline (keyless), same as ashares_daily_history.

Input parameters:

- `adjust` (string): Price adjustment for splits/dividends: qfq = forward-adjusted (default), hfq = backward-adjusted, none = raw.
- `boll_mult` (number): BOLL standard-deviation multiplier, default 2.
- `boll_period` (number): BOLL period, default 20.
- `codes` (string, required): One 6-digit code or a comma-separated list, up to 5, e.g. "515050" or "600519,300750". sh/sz/bj prefixes accepted but optional. ETF codes work the same as stock codes.
- `end` (string): End date, YYYY-MM-DD or YYYYMMDD (inclusive). Default: today.
- `indicators` (array): Which indicator families to compute. Default: all four.
- `kdj_m1` (number): KDJ K smoothing factor, default 3.
- `kdj_m2` (number): KDJ D smoothing factor, default 3.
- `kdj_n` (number): KDJ RSV lookback period, default 9.
- `ma_windows` (array): MA window lengths in trading days. Default [5, 10, 20, 60].
- `macd_fast` (number): MACD fast EMA period, default 12.
- `macd_signal` (number): MACD signal (DEA) EMA period, default 9.
- `macd_slow` (number): MACD slow EMA period, default 26.
- `start` (string, required): Start date for the RETURNED indicator range, YYYY-MM-DD or YYYYMMDD (inclusive). Extra history before this date is fetched automatically to warm up the indicators.

### `ashares_sector_capital_flow` (~401 tokens)

China A-share INDUSTRY-SECTOR net capital inflow ranking (行业资金流向排名/板块资金流) for a trading day -- ranks Eastmoney's ~128 industry boards (行业板块) by main-capital net inflow (主力净流入), with the breakdown by order size (超大单/大单/中单/小单 net inflow in CNY), the day's change %, and each sector's single stock with the largest net inflow. Answers '今日行业资金流向排名', 'which industry sectors had the biggest net capital inflow today', '板块资金流排名', 'sector fund flow ranking', 'semiconductor sector money flow today'. This is a DIFFERENT metric from china-exchange-data's ashares_sector_flows, which is SZSE's own official per-industry TURNOVER ranking -- this tool is Eastmoney's vendor-computed NET INFLOW (主力净流入) classification, the sector-level counterpart to this pack's own per-stock ashares_capital_flow. A non-trading date (weekend/holiday, or before today's session has published -- publication usually lags a day) walks back automatically to the nearest prior trading day with data. Source: Eastmoney datacenter (keyless).

Input parameters:

- `date` (string): Trading day as YYYY-MM-DD or YYYYMMDD (default: most recent day with published data -- today's session often has not published yet).
- `limit` (number): How many sectors to return, 1-130 (default 20).
- `order` (string): desc (default, biggest net inflow first) or asc (biggest net outflow first).
- `sort` (string): Rank by net inflow amount in CNY (主力净流入, default), net inflow as a % of turnover (净流入占比), or the day's change % (涨跌幅).

### `ashares_stock_connect` (~351 tokens)

Stock Connect (沪深港通) daily channel statistics: GROSS TURNOVER for Northbound (mainland A-shares bought via Hong Kong -- 沪股通/深股通/combined) and Southbound (Hong Kong-listed stocks bought by mainland investors -- 港股通沪/港股通深/combined), plus a best-effort per-stock "top traded stocks" list for Northbound. Answers "northbound stock connect turnover today", "沪深股通成交额", "how much did northbound/southbound trade today", "stock connect top traded stocks". IMPORTANT: mainland regulators (CSRC) stopped publishing DAILY net fund-flow figures (net buy/sell, daily inflow, remaining quota) for NORTHBOUND Stock Connect in August 2024 -- every Northbound channel's net_flow field says so explicitly rather than returning null as if it were real data; gross turnover is unaffected and is published daily for every channel. Southbound net flow is still disclosed by Hong Kong Exchanges and Clearing and is returned when available. A turnover-ranked top-10-stocks list for Northbound depends on an Eastmoney report that has returned a server error on every live probe during this build -- the tool still attempts it live on every call and reports plainly under top_traded_stocks.northbound whether real data came back, rather than silently omitting the field or faking rows. Source: Shanghai Stock Exchange / Shenzhen Stock Exchange / Hong Kong Exchanges and Clearing, via Eastmoney datacenter (keyless).

Input parameters:

- `date` (string): Trading day as YYYY-MM-DD or YYYYMMDD (default: most recent day with published data -- today's session often has not published yet).

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/pipeworx-io-china-stocks/pipeworx-mcp-china-stocks#diagnostics

## Score history

- 2026-11-07: 83
- 2026-11-06: 83
- 2026-11-05: 82
- 2026-11-04: 82
- 2026-11-03: 81
- 2026-11-02: 81
- 2026-11-01: 80
- 2026-10-31: 80
- 2026-10-30: 79
- 2026-10-29: 79

## Common questions

### What is the China Stocks MCP server?

China Stocks is an MCP server listed in the public MCP registry as io.github.pipeworx-io/china-stocks. China A-shares MCP. Keyless. This page covers its npm package (@pipeworx/mcp-china-stocks).

### Is the China Stocks MCP server safe to use?

China Stocks scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 7 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the China Stocks MCP server expose?

China Stocks exposes 16 tools: ashares_limit_up, ashares_limit_down, ashares_margin_financing, ashares_market_snapshot, ashares_quote, and 11 more. Their descriptions and schemas cost roughly 5,316 tokens of context every time the server is loaded.

### Is the China Stocks MCP server still maintained?

China Stocks is still listed as active in the MCP registry. We last reached this channel on 7 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the China Stocks MCP server under?

China Stocks declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the China Stocks MCP server?

VerifyMCP ran 16 checks on China Stocks, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/@pipeworx/mcp-china-stocks
- Socket report: https://socket.dev/npm/package/@pipeworx/mcp-china-stocks
- Repository: https://github.com/pipeworx-io/mcp-china-stocks
- Website: https://pipeworx.io/packs/china-stocks
- Changelog RSS feed: https://verifymcp.io/servers/pipeworx-io-china-stocks/pipeworx-mcp-china-stocks.xml
- Changelog JSON feed: https://verifymcp.io/servers/pipeworx-io-china-stocks/pipeworx-mcp-china-stocks/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/pipeworx-io-china-stocks/pipeworx-mcp-china-stocks.json
- HTML version of this page: https://verifymcp.io/servers/pipeworx-io-china-stocks/pipeworx-mcp-china-stocks
