Skip to main content
Glama

Server Details

查A股个股/概念最近被多少机构/大V提及、热度高不高。只读数据,机构/大V用匿名ID。量化交易必备。

Ownership verified
Status
Healthy
Uptime
95.7% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
ChatGPT
–
Claude
–

TDQS

A3.6/5.0

Scored across 20 tools

Disambiguation3/5

Several clusters of near-sibling tools require careful reading to separate: get_market_hot_stocks vs get_weighted_hot_stocks vs get_accelerating_hot_stocks (three stock rankings), get_stock_heat_windows vs get_stock_news_heat vs get_stock_heat_panel vs check_portfolio (four per-stock heat views), and get_agency_ranking vs get_agency_pit vs get_agency_history. The descriptions do explicitly differentiate them (momentum vs weighting vs time windows vs PIT), so an attentive agent can pick correctly, but selection errors are likely without reading the fine print.

Naming Consistency4/5

Names are uniformly snake_case and follow a verb_noun pattern, with 16 of 20 using the get_ prefix and the rest using check_/list_/search_ appropriately. The only minor deviation is that get_* is stretched across very different semantics (single-stock, market, agency, news), but the pattern itself is predictable.

Tool Count3/5

20 tools is on the heavy side for the scope, and there is redundancy: get_morning_digest re-aggregates hot stocks/concepts/first-mentions that already have dedicated tools, and check_portfolio partly duplicates get_stock_heat_windows. The breadth (stocks, concepts, agencies, news, account) justifies many tools, but the surface could be trimmed to ~14 without losing capability.

Completeness4/5

Coverage is strong across the domain: market-level and per-entity heat, concept↔stock both directions, agency rankings/history/PIT/dates, news hits and keyword search, historical daily panels, batch portfolio check, and account balance. Minor gaps remain — no raw mention-record listing with pagination beyond keyword search, and no explicit stock-name/code lookup or concept history beyond the shared panel tool.

Available Tools

20 tools
check_portfolio自选股批量体检:一次查多只股票热度、概念与最新观点摘要A
Read-onlyIdempotent
Inspect

自选股批量体检:一次查多只股票热度、概念与最新观点摘要。输入 1~20 只 A 股代码或简称(逗号分隔),单次返回每只股票近 N 日提及数、覆盖机构数、关联概念及最多 3 条结构化观点摘要。(每次调用计费 1 次)

Inputs: codes (required), days.

get_accelerating_hot_stocks热度加速榜:谁在突然变热(动量排序)A
Read-onlyIdempotent
Inspect

热度加速榜:谁在突然变热(动量排序)。在全市场热榜候选上计算 heat_chg_1d / heat_chg_3d / heat_z20,并按动量降序。字段为纯统计量,便于量化因子与监控接入。(每次调用计费 1 次)

Inputs: limit, order, market, window, +1 more.

get_account查余额和用量(不扣钱)A
Read-onlyIdempotent
Inspect

查余额和用量(不扣钱)。返回余额、单价、预计还能调用几次、今天调用了几次。查这个不扣钱。(不计费)

Inputs: no named parameters.

get_agency_coverage个股机构/大V覆盖度时序A
Read-onlyIdempotent
Inspect

个股机构/大V覆盖度时序。返回每日滚动 7/30 日去重机构/大V数、区间累计新增覆盖、30 日高分占比。只给计数,不返回机构 ID 列表。纯统计量。(每次调用计费 1 次)

Inputs: days, ts_code, min_score, stock_name.

get_agency_history单个机构/大V的历史评分走势(PIT)B
Read-onlyIdempotent
Inspect

单个机构/大V的历史评分走势(PIT)。按日期从早到晚,返回该 agency_id 每个发布日的评分。(每次调用计费 1 次)

Inputs: agency_id (required), limit, end_date, start_date.

get_agency_pit机构/大V历史截面评分(PIT)A
Read-onlyIdempotent
Inspect

机构/大V历史截面评分(PIT)。查某一天当时的机构/大V分(PIT=只用那天已经知道的数据计算,不会“偷看未来”),适合回测。返回不晚于 as_of_date 的最近一个已发布日期的数据。(每次调用计费 1 次)

Inputs: limit, offset, agency_id, min_score, +1 more.

get_agency_ranking机构/大V评分排行(当前)A
Read-onlyIdempotent
Inspect

机构/大V评分排行(当前)。按 agency_id 返回机构/大V分(约 450~1500,1000 左右算中等)、有效样本数、胜率等。(每次调用计费 1 次)

Inputs: limit, order, offset, min_score.

get_concept_stock_heat概念板块热度:某个概念里哪些股票被提到最多A
Read-onlyIdempotent
Inspect

概念板块热度:某个概念里哪些股票被提到最多。统计最近一段时间,某个概念下每只股票被提到几次、有多少机构/大V提到(数据约 10 分钟更新一次)。(每次调用计费 1 次)

Inputs: concept (required), days, limit.

get_first_mention_stocks首提流:此前 7 天没人提、刚被第一次提到的 A 股A
Read-onlyIdempotent
Inspect

首提流:此前 7 天没人提、刚被第一次提到的 A 股。列出最近 N 小时内“首次被提到”的股票(此前 7 天一次都没被提过):首提时间、首提的 agency_id 和分数,以及首提之后到现在又被提了几次。适合发现新冒头的标的。(每次调用计费 1 次)

Inputs: hours, limit, min_score.

get_market_hot_concepts全市场概念热榜:最近哪些概念板块最热A
Read-onlyIdempotent
Inspect

全市场概念热榜:最近哪些概念板块最热。按时间窗(1 小时 ~ 3 天)统计每个概念被提到几次、有多少机构/大V提到,从高到低排(已去掉泛词);并附 heat_chg_1d / heat_chg_3d / heat_z20(纯统计量)。约 2 分钟更新。(每次调用计费 1 次)

Inputs: limit, window, min_score.

get_market_hot_stocks全市场个股热榜:最近谁被提得最多A
Read-onlyIdempotent
Inspect

全市场个股热榜:最近谁被提得最多。按时间窗(1 小时 ~ 7 天)统计全市场每只股票被提到几次、有多少机构/大V提到、第一次和最近一次被提到的时间,从高到低排;并附 heat_chg_1d / heat_chg_3d / heat_z20(纯统计量,非交易信号)。可按 min_score 只看高分机构/大V。约 1 分钟更新。(每次调用计费 1 次)

Inputs: limit, market, window, min_score.

get_morning_digest盘前/日度综合晨报:一次拿到热股、热概念、首提流A
Read-onlyIdempotent
Inspect

盘前/日度综合晨报:一次拿到热股、热概念、首提流。单次调用聚合窗口内最热 A 股、最热概念(已过滤不可见板块)与最新首次提及个股,适合 Agent 盘前简报与定时研究推送。(每次调用计费 1 次)

Inputs: limit, window.

get_news_stock_hits新闻命中个股:主流财经媒体新闻点名了哪些股票A
Read-onlyIdempotent
Inspect

新闻命中个股:主流财经媒体新闻点名了哪些股票。把新华网、财联社、新浪财经、同花顺等主流媒体的快讯/新闻与 A 股简称做匹配,给出每条新闻的发布时间、媒体、命中的股票(不输出标题和正文),以及窗口内被新闻点名最多的股票排行(附熔岩同期 24 小时热度)。不给股票时看全市场;给股票时只看点名它的新闻。约 2 分钟更新。(每次调用计费 1 次)

Inputs: src, hours, limit, ts_code, +1 more.

get_stock_concept_heat个股概念热度:某只股票关联哪些概念最热A
Read-onlyIdempotent
Inspect

个股概念热度:某只股票关联哪些概念最热。统计最近一段时间,某只股票关联的各个概念被提到几次、第一次和最近一次被提到的时间、有多少机构/大V提到。(每次调用计费 1 次)

Inputs: days, limit, ts_code, stock_name.

get_stock_heat_panel日频历史面板:按日回看提及/机构数/加权热度(可回测)A
Read-onlyIdempotent
Inspect

日频历史面板:按日回看提及/机构数/加权热度(可回测)。按自然日聚合个股或概念的 mentions、agencies、weighted_heat、is_first_mention_day。区间最长 92 天,单次最多 20 个标的。weighted_heat 用当前机构分口径加权(非当日 PIT)。适合回测与面板导出。(每次调用计费 1 次)

Inputs: to, from, type, codes, +2 more.

get_stock_heat_windows单股热度走势:1小时~7天多时间窗 + 近24小时逐小时A
Read-onlyIdempotent
Inspect

单股热度走势:1小时~7天多时间窗 + 近24小时逐小时。一次给出某只股票在 1h/4h/18h/24h/3d/7d 各时间窗的提及数、机构/大V数、高分机构/大V数、加权热度,最近 24 小时逐小时走势,以及 heat_chg_1d / heat_chg_3d / heat_z20(纯统计量)。适合盯单股热度怎么起来、怎么回落。(每次调用计费 1 次)

Inputs: ts_code, min_score, stock_name.

get_stock_news_heat个股消息面热度:某只股票最近被提到的记录A
Read-onlyIdempotent
Inspect

个股消息面热度:某只股票最近被提到的记录。按股票查最近一段时间的消息面记录:一句话摘要、要点、涉及的股票/概念、机构/大V ID(agency_id)和机构/大V分;同时给出被提到几次、有多少机构/大V提到等热度数字。适合量化与 AI Agent 接入。(每次调用计费 1 次)

Inputs: days, limit, ts_code, end_date, +3 more.

get_weighted_hot_stocks高分机构/大V加权热榜:靠谱的人在提哪些股A
Read-onlyIdempotent
Inspect

高分机构/大V加权热榜:靠谱的人在提哪些股。只统计机构/大V分达标(默认 ≥1050,约前 10%)的提及,并按分数加权:weighted_heat=每次提及的机构/大V分 ÷ 1000 再相加。分数用 PIT 面板(只用当时已知数据,不偷看未来);给 as_of_date 时消息只算到当天 15:00,适合回测。返回参与的 agency_id(最多 20 个)。(每次调用计费 1 次)

Inputs: days, limit, order, market, +2 more.

list_agency_pit_dates有历史评分(PIT)的日期列表A
Read-onlyIdempotent
Inspect

有历史评分(PIT)的日期列表。从新到旧列出已发布的评分日期,以及当天有多少机构/大V。(每次调用计费 1 次)

Inputs: limit.

search_news_flow按关键词搜消息面记录A
Read-onlyIdempotent
Inspect

按关键词搜消息面记录。在要点里搜关键词(最多 5 个词,用空格隔开,要全部包含),最新的排在前面。(每次调用计费 1 次)

Inputs: keyword (required), limit, since.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      11 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources