Skip to main content
Glama

Ashares Technical Indicators

ashares_technical_indicators
Read-onlyIdempotent

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 x2 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=2x(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.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "end": "2026-09-22",
      "codes": "515050",
      "start": "2026-09-01",
      "indicators": [
        "ma",
        "boll",
        "macd",
        "kdj"
      ]
    },
    "name": "ashares_technical_indicators"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoEnd date, YYYY-MM-DD or YYYYMMDD (inclusive). Default: today.
codesYesOne 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.
kdj_nNoKDJ RSV lookback period, default 9.
startYesStart 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.
adjustNoPrice adjustment for splits/dividends: qfq = forward-adjusted (default), hfq = backward-adjusted, none = raw.
kdj_m1NoKDJ K smoothing factor, default 3.
kdj_m2NoKDJ D smoothing factor, default 3.
boll_multNoBOLL standard-deviation multiplier, default 2.
macd_fastNoMACD fast EMA period, default 12.
macd_slowNoMACD slow EMA period, default 26.
indicatorsNoWhich indicator families to compute. Default: all four.
ma_windowsNoMA window lengths in trading days. Default [5, 10, 20, 60].
boll_periodNoBOLL period, default 20.
macd_signalNoMACD signal (DEA) EMA period, default 9.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the readOnly/idempotent annotations: discloses that extra lookback history is fetched internally but only [start, end] is returned, that MA60/MACD need ~60 prior trading days, the MACD histogram convention (柱=2x(DIF−DEA)), KDJ's 3/3 recursive form seeded at 50, and the keyless Tencent/gtimg source.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the indicator families and their Chinese aliases before conventions and caveats, so the essential purpose is readable in the first clause. The list of example queries is somewhat padded but each remaining sentence carries operational detail (warm-up, conventions, source).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 14 parameters, no output schema and thin annotations, the description still covers warm-up semantics, returned range, computational conventions, and data source. It stops short of describing the shape of returned records (which columns appear per indicator family), which matters given there is no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so defaults for ma_windows, boll_period/mult, macd periods and kdj_n/m1/m2 are already documented; the description mostly restates those defaults. It does add real meaning about the start parameter's warm-up behavior and the per-call code limit, but not enough to exceed the baseline for a fully documented schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names the specific resource (technical indicators: MA/BOLL/MACD/KDJ) and the exact asset scope (Chinese A-share stocks and ETFs), then explicitly positions itself against the sibling by noting it is computed from the same daily OHLCV history and codes as ashares_daily_history.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete example queries it is meant to answer ('MA20 and BOLL for an A-share ETF', '603986周线MACD是否死叉') and notes the 5-code cap because 'indicator math is heavier than a plain OHLCV pull', which implicitly steers raw-price requests to ashares_daily_history. It never states an explicit when-not or names an alternative outright.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.