Skip to main content
Glama

洋葱财报OnionData-MCP

财务取数(单公司多期 / 多公司单期)

company_records
Read-onlyIdempotent

读取 A 股上市公司财报明细(China A-share financial statements):唯一取数入口,覆盖利润表 income、资产负债表 balance、现金流量表 cashflow、业绩预告 predict。五种口径——new 最新报告期(latest)、quarter_t 单季度同比(single-quarter YoY)、quarter_h 单季度环比(single-quarter QoQ)、ttm 逐季度滚动四季合计(trailing twelve months)、year 年度(annual)。scode 传 1 个 → 单公司多期(periods 1–10,默认 1);传 2–10 个 → 多公司单期横切(省略 report_date 时取所选公司该口径的最近报告期)。多公司不支持 periods,periods 与 report_date 互斥(dimension_conflict)。repotype=basic/operation 可按指标配置把该报表细分为基础指标 / 运营指标,省略返回该报表全部指标。format=long 一行一指标;format=wide 一行一(公司, 报告期, 报表)的指标对象;业绩预告(predict)仅支持 format=long。结果上界按报表计:long 每张 250 行 / wide 每张 10 行,reponame 最多 4 张(逗号分隔);超出返回 result_too_large,不截断。notice_date_to 按当前公告日过滤(重述会移动公告日),notice_date_from 做增量(含重述)。数值为原始值(元),增幅以百分点表示(12.3 即 12.3%)。单公司与多公司横切均不要求 VIP;按实际返回与数据价值权重计积分,空结果不计。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "scode": "<scode>",
      "reponame": "<reponame>",
      "repoterm": "<repoterm>"
    },
    "name": "company_records"
  }
}

Input Schema

NameRequiredDescriptionDefault
scodeYesA 股 6 位代码列表(1–10 个):1 个=单公司多期,多个=多公司单期横切;只需传一次数组
formatNolong 一行一指标;wide 一行一(公司, 报告期)long
periodsNo报告期数 1–10,默认 1(最近一期),仅单公司可用(多公司传会报 dimension_conflict)
reponameYes报表名:income 利润表(income statement)/ balance 资产负债表(balance sheet)/ cashflow 现金流量表(cash flow statement)/ predict 业绩预告;多张报表用逗号分隔(最多 4 个),如 income,balance
repotermYes单一口径:new 最新报告期 latest / quarter_t 单季度同比 YoY / quarter_h 单季度环比 QoQ / ttm 逐季度 TTM / year 年度 annual
repotypeNo指标类别:basic 基础指标 / operation 运营指标;省略=该报表全部指标
report_dateNo报告期 YYYY-MM-DD;与 periods 互斥,多公司不传则取最近报告期
repoitem_keyNo指标 key 列表;省略=该报表全部指标
notice_date_toNo公告日上界(含)YYYY-MM-DD,用于时点快照
notice_date_fromNo公告日下界(含)YYYY-MM-DD;响应 meta.notice_date_max 可作下次水位线

Output Schema

NameRequiredDescriptionDefault
dataYes
metaYes
pageYes
quotaYes
formatYes
objectYes
datasetNo

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantive behavior: hard result caps per report (long 250 rows / wide 10 rows, max 4 reponame) with result_too_large instead of truncation, notice_date_to as a point-in-time snapshot where restatements move the announcement date versus notice_date_from as incremental, raw values in 元 with growth in percentage points, and no VIP requirement with credits weighted by actual returned data and empty results not charged.

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?

Purpose and calibers are front-loaded, then constraints, then output limits and pricing — a sensible order with little filler. It is a dense single block, though, and a few clauses (repotype/format restated) duplicate the schema rather than adding new information.

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

Completeness5/5

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

An output schema exists, yet the description still supplies the pieces an agent needs to call it correctly: which combinations are illegal, what happens at the row ceiling, and how the notice_date pair changes semantics. For a 10-parameter tool with 3 enums, nothing material is left ambiguous.

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; the description goes beyond it by explaining the conflict rule between periods and report_date, the multi-company default for omitted report_date, the per-report row ceilings that make reponame cardinality matter, and the incremental-vs-snapshot semantics of the notice_date bounds (including meta.notice_date_max as a watermark). Slight redundancy with schema text on repoterm/repotype keeps it off a 5.

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?

Starts with a specific verb and resource (读取 A 股上市公司财报明细) and immediately declares itself the single data-retrieval entry point covering income/balance/cashflow/predict, which separates it from the metadata siblings (list_indicators, get_dimensions, get_usage). The five repoterm calibers are enumerated by name and gloss, so an agent knows exactly what the tool returns without opening the schema.

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

Usage Guidelines5/5

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

Explicitly routes by argument shape: scode with 1 code = single company multi-period, 2–10 codes = multi-company single-period cross-section with report_date defaulting to the latest period. It names the mutually exclusive pair (periods vs report_date → dimension_conflict), states multi-company does not support periods, and notes predict only supports format=long — real when/when-not guidance rather than implied usage.

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