Skip to main content
Glama
This connector has been deprecated

Replaced by echopai-mcp.

Duplicate listing; superseded by io.github.echopai/echopai-mcp (official MCP Registry entry).

scan

Full-market real-time quote scan (~5800 A-share securities, ~3 MB unfiltered). Narrow server-side first: sort + order + limit return a real ranking (sort=pct_change, order=desc, limit=50 = the day's 50 strongest in a few KB); limit without sort is an alphabetical sample, not a ranking. When rows are dropped the response carries truncated: true and matched_total (the pre-limit count) — total is only how many rows came back. The universe includes ETFs (security_type on every row); money-market ETFs dominate sort=amount, so pass security_type=stock for a stock-only board (filtered before sort/limit). include_margin attaches the T+1 margin block; include_industry attaches industry (Shenwan L1/L2) and top_concept. Both are often absent — coverage, not failure: top_concept resolves for only a subset of A-shares and industry does not cover BSE:*; top_concept is not the limit-up LLM leading_concept, which is not served here. Live rows also expose top_base_concept {id,name,kind:base,pct_change} and top_concept_status / top_base_concept_status (ready, no_membership, no_snapshot, unavailable). The two layers rank independently; use kind=base for base detail. Historical rows carry neither current theme field nor their statuses. In pre_open / auction sessions read each row's auction block, not top-level price / pct_change (same rules as quote: only auction.status = matched with auction.pct_change = 0 is a flat auction; compute from auction.prev_close). Read market_trade_date, not snapshot_at, to decide whether a row is today's — a frozen feed keeps snapshot_at moving. is_margin_target is margin-list membership (T+1), not activity; the key is absent (never false) when the list cannot be loaded. trade_date=YYYY-MM-DD scans that past day's daily bars (see the parameter for allowed combinations). 竞价未匹配量 unmatched 为股,正买负卖;unmatched_as_of 是最后有效竞价观测的源时间(09:25 后冻结),历史未采集为 null。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
_jqNoJMESPath,对 data 求值(写 items[*].id)
sortNoServer-side ranking key, applied before `limit`; omit for `canonical_code` order. `margin_balance` / `margin_net_buy` turn `include_margin` on. Null sort values land last in both directions.
limitNoKeep the first N rows **after** sorting (1-10000). Always pair with `sort` — an unsorted limit is an alphabetical sample. When rows are dropped: `truncated: true` + `matched_total` (pre-limit count); `total` is only the returned count.
orderNoSort direction. Defaults to `desc` for numeric keys and `asc` for `canonical_code`. Ignored without `sort`.
_spillNotrue=全量落盘,只回摘要与取数地址
_fieldsNo逗号分隔的直接字段;有 items 时投影每行,否则投影 data;外层字段或嵌套结构用 _jq
_intentNo用户原问题一句话,仅分析用,可留空
includeNo`active` (default) drops ST / delisted / stale rows; `all` keeps them, flagged with `stale: true` and `stale_since`.
exchangeNoFilter by exchange (omit for all)
_max_bytesNo响应字节上限,默认约 50 KB
concept_idNoRestrict the scan to one concept's / industry's members. Applied **before** sort and limit, so `concept_id` + `sort=pct_change` + `limit=10` gives the top 10 movers **inside that concept** (and `matched_total` counts its members, not the whole market). An unknown / inactive / wrong-dimension id returns 404, so an empty result means the theme has no members in today's snapshot rather than a bad id. Get ids from `concepts_list` or `concepts_of`.
trade_dateNoPast trading day (YYYY-MM-DD) to scan instead of the live snapshot — rows are that day's daily bars. Only `price` / `pct_change` / `amount` / `turnover_rate` / `canonical_code` sort historically; `concept_id`, `include_margin` and `margin_target` cannot be combined. Today / future / non-trading days are rejected.
concept_kindNoDimension of `concept_id`: concept (hot-theme library, default), base (base labels), or industry (Shenwan). Ignored alone.
margin_targetNoKeep only margin-eligible securities (true) or only non-eligible (false); omit for both. Returns 503 if the list cannot be loaded.
security_typeNo`stock` keeps only stocks, `etf` only ETFs, `all` (default) both. Money-market / short-bond ETFs dominate `sort=amount` unless you pass `stock`. Filtered before sort / limit; every row carries `security_type` either way.
include_marginNoAttach the T+1 margin block (off by default, ~25% larger). `as_of` is normally the previous trading day; judge direction by `financing_net_buy_cny` (`financing_buy_cny` is gross); null = not published, not zero.
_max_bytes_modeNo正文超限处理,默认 truncate 保留前缀
include_industryNoAttach `industry` (Shenwan L1/L2 `{l1:{id,name}, l2:{id,name}}`) and `top_concept` (`{id,name,pct_change}`, highest-moving member concept now; not the limit-up `leading_concept`). Also attaches `top_base_concept` (kind=base) and separate availability statuses for both layers. Off by default (payload). Ids feed the concepts endpoints (`kind=industry` / `kind=concept`).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses truncation semantics (`truncated: true` plus pre-limit `matched_total`, versus `total` which is only rows returned), payload sizes (~3 MB unfiltered, ~25% larger with `include_margin`), failure modes (503 when the margin list can't load, absent key rather than `false`), and field-absence-as-coverage caveats for `top_concept` and `BSE:*` industry. It also explains non-obvious response pitfalls — frozen feeds keep `snapshot_at` moving so `market_trade_date` is the truth, and in `pre_open`/`auction` sessions rows must be read from the `auction` block rather than top-level `price`. No statement here contradicts the tool's behavior.

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

Conciseness3/5

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

The first two sentences are well front-loaded and high value, but the remainder collapses into a single dense paragraph of em-dashes and parentheticals covering ranking, ETFs, margin, industry, themes, auction sessions, margin membership and historical dates with no grouping. Substantial material duplicates the input schema verbatim in substance (truncation, security_type filtering order, margin_balance implies include_margin), diluting the parts that are genuinely new. The final Chinese sentence is left untranslated, which breaks the otherwise English document for some readers.

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?

For an 18-parameter scan with no output schema and no annotations, the description covers an unusually wide surface: scope, truncation, error codes, absence semantics, session-specific reading rules, and historical-mode restrictions. Remaining gaps are the response envelope itself (the `data` vs `items` structure only implied by `_jq`/`_fields`), any pagination beyond a single truncated pass, and auth/rate-limit expectations.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3 even without description help, and much of what the description says about `sort`, `limit`, `security_type`, `include_margin` and `trade_date` restates the schema. It earns above baseline by adding semantics the schema omits: `is_margin_target` is T+1 margin-list membership, not activity, and the key is absent (never `false`) when unloadable; `market_trade_date` vs `snapshot_at`; and the untranslated Chinese note that `unmatched` is in shares with positive=buy, negative=sell, and `unmatched_as_of` freezes after 09:25.

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

Purpose4/5

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

The opening sentence is specific: a full-market real-time quote scan over ~5800 A-share securities, with the unfiltered payload size stated. An agent immediately knows this is a market-wide screening tool rather than a single-symbol lookup. What is missing is explicit sibling differentiation — `quote` is only referenced incidentally for auction rules, and nothing says when to pick `scan` over `concepts_snapshot` or `quote`.

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?

The description gives strong operational 'how to use' guidance: narrow server-side first with sort/order/limit, `limit` without `sort` is an alphabetical sample rather than a ranking, pass `security_type=stock` for a stock-only board, and use `kind=base` for base detail. It also frames when each mode applies (live snapshot vs `trade_date` historical bars). It stops short of explicit tool-selection guidance — there is no 'use this instead of X when Y' routing against the many sibling quote/concept tools.

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.

Resources