A股数据 API (A-Share Data API)

ashare_screen

选股（量化筛股），五种模式用 mode 选（默认 condition）：condition 因子表达式（如 intersect([PE_TTM > 0, PE_TTM < 20, ROETTM > 15])）· label 属性标签（央企/ST/破净/次新/市值档位… 108 个）· ranking 全市场排行（综合/资金/基本面/风险/技术评分，type 默认 CompScore）· strategy 策略选股（MACD 金叉/突破年线/高股息/大师策略… 98 个）· event 事件选股（分红/业绩预告/定增/解禁/董监高… 42 个）。用户问'筛选/选股/符合条件的股票/哪些票…'用这个。⚠️ 不知道 type 有哪些取值 ⇒ 先传 list=true（返回该模式全部合法取值，带中文名与分组），⛔ 不要凭猜填 type（非法值会报错）。⚠️ 返回是排版好的表格；多标签/多策略会分多段返回 ⇒ 用 tables 取全部段。⚠️ 付费工具（需 Key）：Standard（¥29.9）及以上。

Input Schema

Name	Required	Description	Default
`date`	No	查询日期 YYYY-MM-DD（留空=最新交易日）
`expr`	No	因子表达式（mode=condition），如 intersect([PE_TTM>0, PE_TTM<20])
`list`	No	true=列出该模式全部可用取值（⭐ 不确定 type 时先用它）
`mode`	No	condition 因子 / label 标签 / ranking 排行 / strategy 策略 / event 事件（默认 condition）	condition
`type`	No	label/ranking/strategy/event 的取值；list=true 时作分组过滤
`asset`	No	资产类别：stock 股票（默认）/ etf（mode=label / ranking）
`limit`	No	条数（默认 20，MCP 侧上限 100）
`offset`	No	翻页偏移（配合 limit）
`preset`	No	预设名（mode=condition，与 expr 二选一）：LowPE/LowPB/HighDividend/PEG/HighROE 等 22 个
`orderby`	No	排序字段（mode=condition，如 ROETTM）

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedOct 22, 2026

addedInput schema / properties / asset

Added value: +{
+  "default": "",
+  "description": "资产类别：stock 股票（默认）/ etf（mode=label / ranking）",
+  "title": "Asset",
+  "type": "string"
+}

addedInput schema / properties / date

Added value: +{
+  "default": "",
+  "description": "查询日期 YYYY-MM-DD（留空=最新交易日）",
+  "title": "Date",
+  "type": "string"
+}

addedInput schema / properties / expr / default
```
Added value: +""
```

changedInput schema / properties / expr / description

Previous value: -"因子表达式，如 intersect([PE_TTM>0, PE_TTM<20])"New value: +"因子表达式（mode=condition），如 intersect([PE_TTM>0, PE_TTM<20])"

changedInput schema / properties / limit / description

Previous value: -"条数（默认 20）"New value: +"条数（默认 20，MCP 侧上限 100）"

addedInput schema / properties / list

Added value: +{
+  "default": false,
+  "description": "true=列出该模式全部可用取值（⭐ 不确定 type 时先用它）",
+  "title": "List",
+  "type": "boolean"
+}

addedInput schema / properties / mode

Added value: +{
+  "default": "condition",
+  "description": "condition 因子 / label 标签 / ranking 排行 / strategy 策略 / event 事件（默认 condition）",
+  "title": "Mode",
+  "type": "string"
+}

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "description": "翻页偏移（配合 limit）",
+  "title": "Offset",
+  "type": "integer"
+}

changedInput schema / properties / orderby / description

Previous value: -"排序字段（如 ROETTM）"New value: +"排序字段（mode=condition，如 ROETTM）"

addedInput schema / properties / preset

Added value: +{
+  "default": "",
+  "description": "预设名（mode=condition，与 expr 二选一）：LowPE/LowPB/HighDividend/PEG/HighROE 等 22 个",
+  "title": "Preset",
+  "type": "string"
+}

addedInput schema / properties / type

Added value: +{
+  "default": "",
+  "description": "label/ranking/strategy/event 的取值；list=true 时作分组过滤",
+  "title": "Type",
+  "type": "string"
+}

removedInput schema / required
```
Removed value: -[
-  "expr"
-]
```

Changed3 schema fields changedSep 23, 2026
- addedInput schema / properties / expr / description
```
Added value: +"因子表达式，如 intersect([PE_TTM>0, PE_TTM<20])"
```
- addedInput schema / properties / limit / description
```
Added value: +"条数（默认 20）"
```
- addedInput schema / properties / orderby / description
```
Added value: +"排序字段（如 ROETTM）"
```
First observedSep 21, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that results are a formatted table, that multi-label/multi-strategy calls return multiple segments requiring `tables`, that illegal `type` values error out, and that the tool is paid (Standard ¥29.9+ key). It omits rate limits and pagination behavior beyond what the schema states, so not a 5.

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-loaded with the core purpose and mode menu, then layered warnings. Dense but nearly every clause carries operational value; the emoji/warning markers aid scanning at a small cost to tightness.

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?

For a 10-parameter, 5-mode tool with an output schema, the description covers mode selection, the type-discovery workflow, error behavior, paid-tier prerequisite, and multi-segment return handling. An agent has everything needed to invoke it correctly on the first try.

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, but the description adds genuine meaning: it explains what `mode` selects with per-mode examples, defines the `list=true` workflow for `type`, and names example `preset` values (LowPE/LowPB/HighDividend...). This goes beyond restating the 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?

States a specific verb and resource (选股/量化筛股) and then enumerates all five modes with concrete examples for each (intersect([PE_TTM>0,...]), 央企/ST labels, CompScore ranking, MACD 金叉, 分红/解禁 events). This lets an agent distinguish it from neighbors like ashare_factors and ashare_strategies without opening either schema.

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?

Explicitly triggers on user phrasings ('筛选/选股/符合条件的股票/哪些票'), and gives a concrete decision rule: when `type` values are unknown, pass `list=true` first and don't guess. Strong intra-tool routing, but it never contrasts against sibling screening tools (ashare_factors, ashare_strategies), which is the remaining gap.

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

All A股数据 API (A-Share Data API) tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?