Log inSubmit server
China Stocks logo

China Stocks

Keyless MCP tools for Chinese A-share quotes, history, rankings, market flows, boards, and company forecasts.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install China Stocks

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "china-stocks": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-china-stocks"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 17 tools correctly (Today).

Overview

China Stocks MCP server exposes live and historical data for Shanghai, Shenzhen, STAR, and ChiNext A-shares through keyless public endpoints. It covers quotes, minute bars, daily OHLCV, limit-up and limit-down boards, turnover rankings, margin balances, capital flows, Stock Connect activity, earnings guidance, and analyst estimates. Reach for it when an agent needs market context or stock-level research without managing API credentials. Results include data freshness and availability details where upstream publication or retention limits affect interpretation.

Use cases

  • Track daily A-share quotes and index conditions
  • Compare turnover and volume across Chinese stocks
  • Inspect limit-up, limit-down, and capital-flow activity
  • Retrieve adjusted price history and intraday bars

Key features

  • Keyless access to public Chinese market-data endpoints
  • Real-time A-share quotes and major index snapshots
  • Daily adjusted OHLCV and bounded intraday history
  • Limit-up, limit-down, turnover, and capital-flow analysis
  • Margin, Stock Connect, earnings, and analyst-consensus data

Tools17

What China Stocks lets your agent do. Expand a tool for its parameters.

Verified live~6.0k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

9/9 checks healthy over the last 56d

What it can do

From the 17 tools this server returned when we ran it; 17 declare their own safety hints.

Makes network requests · 17Read-only tools · 17
Network at startup4 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age110 days
Maintainers1

Observed 2026-11-02 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 9d ago via OSV.dev · @pipeworx/mcp-china-stocks (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads1.5kPackage downloads in the last 30 days.
Last commit2d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed17Callable tools this server registers over MCP.

How China Stocks works

What China Stocks MCP server does

China Stocks provides MCP access to Chinese A-share market data across the Shanghai, Shenzhen, STAR, and ChiNext markets. It combines real-time quote feeds, historical price data, market-wide rankings, trading-board activity, financing balances, capital-flow history, Stock Connect statistics, and company forecast data. The integration is keyless and uses public unauthenticated upstream endpoints.

The available coverage suits agents that need to inspect a stock, compare market activity, or assemble a market snapshot. It is focused on Chinese mainland equities rather than a general global market-data interface.

How it works

Quote and index data come from Sina, while other requests use public endpoints from Eastmoney, SSE, SZSE, Tencent, and related data services. The server translates those sources into MCP tool calls and preserves important source status fields. Capital-flow responses include the latest date represented, retrieval time, and a stale flag. If a cached capital-flow response is served after an upstream failure, the response identifies that condition.

Date handling varies by source. Limit-up and limit-down pools are retained for roughly the last 20 trading days. Margin data may publish on different schedules for SSE and SZSE, so aggregate results use the latest trading day available from both exchanges rather than combining mismatched dates. Stock Connect results distinguish published gross turnover from Northbound net-flow figures, which regulators stopped publishing daily in August 2024.

Setup and configuration

No API key or other upstream credential is required. The package is intended to be connected to an MCP-compatible client, with access handled through the client’s normal server configuration. Requests use the public data services behind the integration.

Tools and capabilities

  • ashares_quote retrieves real-time quotes for comma-separated six-digit symbols.
  • ashares_market_snapshot returns headline levels for major indexes and limit-up or limit-down counts.
  • ashares_daily_history supplies daily OHLCV and percentage changes for up to 20 codes, with forward-adjusted, backward-adjusted, or raw prices.
  • ashares_intraday_bars returns minute bars for up to five symbols and can calculate cumulative volume and turnover through a specified time.
  • ashares_limit_up and ashares_limit_down return board counts and ranked stocks for a trading date.
  • ashares_turnover_ranking ranks the market by turnover, percentage change, or volume.
  • ashares_margin_financing provides market-wide exchange balances and supported SZSE stock-level balances.
  • ashares_capital_flow returns daily main-capital net-inflow history for a stock.
  • ashares_stock_connect reports Northbound and Southbound channel turnover and attempts Northbound top-traded-stock data.
  • ashares_earnings_forecast and ashares_analyst_consensus provide company guidance and forecast estimates.

Limitations and notes

Intraday retention is bounded by about 1,950 bars upstream. Approximate availability ranges from eight trading days at one-minute intervals to about two years at 60-minute intervals; each response reports its actual earliest and latest available dates. Use daily history for older daily data.

Daily-bar rows do not expose turnover amount, so amount_cny is reported as unavailable there. Use quotes or turnover rankings for same-day turnover. SSE per-stock margin detail is unavailable through the supported keyless route, and Northbound per-stock top-traded results may report unavailable when the upstream endpoint fails. An empty limit-down board is treated as a genuine zero only when the corresponding limit-up board confirms that the trading day has data.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about China Stocks

China Stocks is an MCP server that connects AI agents to public Chinese A-share data sources for Shanghai, Shenzhen, STAR, and ChiNext markets. Its main tools cover real-time quotes, daily and intraday history, limit-up and limit-down boards, turnover rankings, margin balances, capital flows, Stock Connect activity, and company forecasts.

No API key is required. China Stocks uses public, unauthenticated endpoints from upstream market-data providers, so client configuration does not need provider credentials.

Intraday lookback depends on the bar interval. The upstream retains about 1,950 total bars, giving roughly eight trading days at one-minute resolution, 40 days at five-minute resolution, 110 days at 15-minute resolution, one year at 30-minute resolution, and two years at 60-minute resolution.

Call `ashares_daily_history` and set `adjust` to `qfq`, `hfq`, or `none`. The default is forward-adjusted data (`qfq`), while `hfq` requests backward-adjusted prices and `none` returns raw prices.

Related MCP servers

All in Finance & Fintech All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewChina Stocks AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/china-stocks?style=directory)](https://allmcps.com/mcp/china-stocks)
HTML Embed
<a href="https://allmcps.com/mcp/china-stocks"><img src="https://allmcps.com/api/badge/china-stocks?style=directory" alt="China Stocks on AllMCPs" /></a>