mirror of
https://github.com/MoonshotAI/kimi-code.git
synced 2026-08-21 14:47:17 +00:00
feat(datasource): add NDA/NBS, standards, IGO, xhcj, and caixin sources (#3115)
* feat(datasource): add NDA/NBS, standards, IGO, xhcj, and caixin sources * fix(datasource): narrow real-time-news ban to coverage gaps, require PublishTime citation * fix(datasource): scope the real-time-news limitation to coverage gaps only * fix(datasource): trim redundant clause in the real-time-news limitation * fix(datasource): stop on a result that covers the question, not the first success * fix(datasource): front-load trigger terms in the skill listing description * fix(datasource): exempt discovery calls from the one-call workflow
This commit is contained in:
qer
GitHub
parent
15da84606a
commit
03dcfcf6d0
8 changed files with 77 additions and 15 deletions
|
|
@ -328,9 +328,22 @@ describe('kimi-datasource MCP server', () => {
|
|||
'gildata',
|
||||
'sec_edgar',
|
||||
'sp_data',
|
||||
'china_nda',
|
||||
'china_nbs',
|
||||
'china_standards',
|
||||
'who',
|
||||
'fao',
|
||||
'unsd',
|
||||
'ecb',
|
||||
'eurostat',
|
||||
'unicef',
|
||||
'oecd',
|
||||
'fred',
|
||||
'xhcj',
|
||||
'caixin',
|
||||
]);
|
||||
expect(call?.description).toContain(
|
||||
'For a simple lookup, use one specialized source and stop after its first successful result',
|
||||
'For a simple lookup, use one specialized source and stop once a result covers the user',
|
||||
);
|
||||
expect(call?.description).toContain('When the user names a data source, use that source');
|
||||
expect(call?.inputSchema.properties['data_source_name']?.description).toContain(
|
||||
|
|
|
|||
|
|
@ -97,7 +97,7 @@ Kimi WebBridge installs in two parts: after the steps above, you also need to [i
|
|||
|
||||
Official plugins do not update automatically — when an update is available, you'll be prompted the next time you use the old version. To upgrade, repeat the installation steps above.
|
||||
|
||||
### Kimi Datasource <Badge type="tip" text="v3.3.0" />
|
||||
### Kimi Datasource <Badge type="tip" text="v3.4.0" />
|
||||
|
||||
Kimi Datasource is the official Kimi Code data plugin, letting you query financial market data, macroeconomic indicators, corporate registration records, academic literature, and Chinese laws and regulations in natural language — no manual API calls or data accounts required.
|
||||
|
||||
|
|
@ -131,6 +131,10 @@ You must first complete OAuth login with a Kimi Code account via `/login`; data
|
|||
| Corporate data | Business registration, equity chain, legal risk, and related-entity graph for mainland Chinese companies |
|
||||
| Academic literature | Millions of papers across physics, mathematics, CS, quantitative finance, economics — including preprints |
|
||||
| Legal | Chinese laws, regulations, and judicial cases — statute search and detail lookup across all authority levels, plus ordinary and authoritative case search |
|
||||
| Chinese government statistics | Open data catalogs from the National Data Administration, plus NBS macro indicators (national, provincial, and major-city time series) |
|
||||
| Chinese standards | National (GB), industry (HB), local (DB), and association (TT) standards lookup |
|
||||
| International organizations | Official open datasets from WHO, FAO, UNSD, ECB, Eurostat, UNICEF, OECD, and FRED — global health, food and agriculture, finance, and macro time series |
|
||||
| Financial news and data | Xinhua Finance announcements, news flashes, and policy updates; Caixin database with 600+ data APIs |
|
||||
| Smart screening | Well-known databases such as Gildata, covering natural-language screening for stocks, funds, and fund managers, plus macro-industry data, research reports, announcements, and news |
|
||||
|
||||
#### Billing and limitations
|
||||
|
|
|
|||
|
|
@ -97,7 +97,7 @@ Kimi WebBridge 分两步安装：完成上述步骤后，还需要[安装浏览
|
|||
|
||||
官方插件更新后会在使用旧版时提示更新，不会自动更新，要升级到新版本，重复上述安装步骤即可。
|
||||
|
||||
### Kimi Datasource <Badge type="tip" text="v3.3.0" />
|
||||
### Kimi Datasource <Badge type="tip" text="v3.4.0" />
|
||||
|
||||
Kimi Datasource 是 Kimi Code 官方数据插件，让你用自然语言直接查询金融行情、宏观经济、企业工商、学术文献和中国法律法规，无需手动调用接口或申请数据账号。
|
||||
|
||||
|
|
@ -131,6 +131,10 @@ Kimi Datasource 是 Kimi Code 官方数据插件，让你用自然语言直接
|
|||
| 企业数据 | 中国大陆境内企业工商信息、股权穿透、司法风险、关联图谱 |
|
||||
| 学术文献 | 物理、数学、计算机、金融、经济等领域百万量级论文，支持预印本查询 |
|
||||
| 法律法规 | 中国法律法规与司法案例：各效力层次的法规检索与详情，普通及权威判例检索 |
|
||||
| 中国政府统计 | 国家数据局开放数据目录与国家统计局宏观指标（全国、省、主要城市时间序列） |
|
||||
| 中国标准 | 国家标准（GB）、行业标准（HB）、地方标准（DB）、团体标准（TT）检索 |
|
||||
| 国际组织 | WHO、FAO、UNSD、ECB、Eurostat、UNICEF、OECD、FRED 官方开放数据集：全球健康、农业粮食、金融与宏观时间序列 |
|
||||
| 财经资讯 | 新华财经公告、快讯与政策新闻；财新数据库 600+ 数据接口 |
|
||||
| 智能筛选 | 恒生聚源等知名数据库，能力涵盖自然语言选股、选基金、选基金经理，以及宏观行业数据、研报、公告与新闻 |
|
||||
|
||||
#### 计费与限制
|
||||
|
|
|
|||
|
|
@ -5,8 +5,8 @@
|
|||
"id": "kimi-datasource",
|
||||
"tier": "official",
|
||||
"displayName": "Kimi Datasource",
|
||||
"version": "3.3.0",
|
||||
"description": "Official datasource workflows.",
|
||||
"version": "3.4.0",
|
||||
"description": "Stocks and financials from Wind, S&P Capital IQ, SEC EDGAR, etc.; news from Caixin, Xinhua Finance; macro from World Bank, IMF, FRED, NBS; corporate, academic, legal data, and more",
|
||||
"keywords": ["data", "mcp"],
|
||||
"source": "./official/kimi-datasource"
|
||||
},
|
||||
|
|
|
|||
|
|
@ -1,5 +1,9 @@
|
|||
# Changelog
|
||||
|
||||
## 3.4.0 - 2026-08-17
|
||||
|
||||
- Add thirteen data sources: `china_nda` (国家数据局开放数据目录), `china_nbs` (国家统计局宏观指标), `china_standards` (中国标准 — GB 国家标准 / HB 行业标准 / DB 地方标准 / TT 团体标准), eight international organization sources (`who`, `fao`, `unsd`, `ecb`, `eurostat`, `unicef`, `oecd`, `fred`), `xhcj` (新华财经快讯 / 公告 / 政策), and `caixin` (财新数据库).
|
||||
|
||||
## 3.3.0 - 2026-07-22
|
||||
|
||||
- Add five data sources: `wind` (万得), `imf` (IMF macro datasets), `gildata` (恒生聚源 smart screening), `sec_edgar` (US SEC filings), and `sp_data` (S&P Capital IQ, paid scope).
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: kimi-datasource
|
||||
description: |
|
||||
Universal data-source assistant. Use this skill when the user wants external structured data such as stocks, financial reports, technical indicators, A-share/HK/US markets, global macroeconomics, Chinese enterprise registry information, arXiv papers, Google Scholar results, Chinese laws/regulations and judicial cases, Wind financial data (intraday/minute quotes, funds, bonds), IMF macro datasets (FX rates, CPI, GDP forecasts), Gildata smart screening, US SEC filings (10-K/10-Q, Form 4, 13F), or S&P Capital IQ fundamentals (top holders, consensus estimates, valuation ratios).
|
||||
Universal data-source assistant for stocks (Wind, S&P, SEC EDGAR), macro (World Bank, IMF, FRED, NBS), Chinese government data and standards (GB/HB/DB/TT), corporate, academic, legal, WHO/FAO/OECD and other IGO data, financial news (Xinhua, Caixin).
|
||||
This plugin exposes tools via MCP server `plugin-kimi-datasource_data`; call them in the flow `mcp__plugin-kimi-datasource_data__get_data_source_desc` → `mcp__plugin-kimi-datasource_data__call_data_source_tool`.
|
||||
---
|
||||
|
||||
|
|
@ -20,7 +20,7 @@ description: |
|
|||
|
||||
## 1. 这个 skill 提供什么能力
|
||||
|
||||
本 plugin 后面挂了 12 个外部数据源。每一行的"数据源名"就是传给 `get_data_source_desc` 的 `name`。
|
||||
本 plugin 后面挂了 25 个外部数据源。每一行的"数据源名"就是传给 `get_data_source_desc` 的 `name`。
|
||||
|
||||
| 能力域 | 数据源名 | 典型问题 |
|
||||
|---|---|---|
|
||||
|
|
@ -36,6 +36,19 @@ description: |
|
|||
| **恒生聚源智能筛选** | `gildata` | "筛选净利润增速超 30% 且 ROE 大于 15% 的股票"、"基金经理筛选" |
|
||||
| **美股 SEC 披露文件** | `sec_edgar` | "特斯拉 10-K 年报"、"苹果 10-Q 季报"、"Form 4 内部人交易"、"13F 机构持仓" |
|
||||
| **S&P Capital IQ 美股基本面** | `sp_data` | "苹果分析师一致预期"、"美股估值比率对比"、"竞争对手关系" |
|
||||
| **中国政府开放数据目录（国家数据局）** | `china_nda` | "全国公共数据资源登记目录里有什么"、"各省开放数据平台有哪些数据集" |
|
||||
| **国家统计局宏观指标** | `china_nbs` | "中国历年 GDP 官方口径"、"各省市人口与就业统计"、"社会消费品零售总额" |
|
||||
| **中国标准查询（国标 / 行标 / 地标 / 团标）** | `china_standards` | "查 GB 国家标准全文"、"某行业的现行行业标准" |
|
||||
| **WHO 全球健康** | `who` | "全球婴儿死亡率"、"各国预期寿命" |
|
||||
| **FAO 农业粮食** | `fao` | "各国粮食产量"、"农产品价格" |
|
||||
| **联合国统计司 UNdata** | `unsd` | "联合国成员国统计年鉴表"、"国际贸易统计" |
|
||||
| **欧洲央行统计** | `ecb` | "欧元区基准利率"、"欧元区货币供应量" |
|
||||
| **欧盟统计局** | `eurostat` | "欧盟各国失业率"、"欧元区 CPI" |
|
||||
| **联合国儿童基金会** | `unicef` | "全球儿童营养指标"、"儿童免疫接种率" |
|
||||
| **OECD 数据** | `oecd` | "OECD 国家 GDP 对比"、"成员国教育支出" |
|
||||
| **FRED 美国/全球宏观** | `fred` | "美国 CPI 长时间序列"、"联邦基金利率走势" |
|
||||
| **新华财经新闻公告** | `xhcj` | "新华财经快讯"、"A 股公司公告"、"行业政策新闻" |
|
||||
| **财新数据库** | `caixin` | "财新数据接口检索"、"财新新闻与数据" |
|
||||
|
||||
### 选源原则
|
||||
|
||||
|
|
@ -51,8 +64,12 @@ description: |
|
|||
- `world_bank_open_data` 是 50 年以上的历史宏观序列；要 IMF 的预测值用 `imf`
|
||||
- `gildata` 的查询输入是自然语言条件（选股 / 选基金 / 基金经理筛选），`tianyancha` 是企业工商档案
|
||||
- `wind` 的 `indexes`/`indicators` 参数要求 Wind 原生字段名；PE/PB/ROE/总市值这类常用字段先调 `wind_search_fields` 映射（支持别名和中文，一次查一个），不要硬猜字段名
|
||||
- 中国官方统计口径：`china_nbs` 是国家统计局宏观指标序列（GDP / CPI / PPI 等，全国 / 省 / 主要城市），`china_nda` 是国家数据局的开放数据目录（回答"有什么数据集可用"）；`world_bank_open_data` 和 `imf` 是国际口径的历史与预测序列
|
||||
- WHO、FAO、UNSD、ECB、Eurostat、UNICEF、OECD、FRED 各自是独立数据源，按机构名直接选；IMF 自己的数据集（汇率 / CPI / GDP 预测）走 `imf`
|
||||
- 国家标准（gb）、行业标准（hb）、地方标准（db）、团体标准（tt）查 `china_standards`；法律法规与判例在 `yuandian_law`，别混
|
||||
- 新华财经（`xhcj`）偏公告 / 快讯 / 政策新闻；`caixin` 覆盖 600+ 财新数据接口，先用它的 `caixin_api_search` 找合适接口再调用
|
||||
|
||||
**不支持的能力**：通用 Web 搜索 / 实时新闻。问到这类问题，告诉用户当前数据源不覆盖。
|
||||
**不支持的能力**：通用 Web 搜索，以及 `xhcj` / `caixin` 覆盖之外的实时新闻。
|
||||
|
||||
## 2. 标准工作流：`get_data_source_desc` → `call_data_source_tool`
|
||||
|
||||
|
|
@ -65,7 +82,7 @@ description: |
|
|||
- 该数据源整体说明（含 ticker 格式、全局约束）
|
||||
- 每个 API 的描述 / 必填参数 / 可选参数 / 默认值 / 取值范围
|
||||
4. 选最匹配的 API，按文档拼 params
|
||||
5. 执行一次 call_data_source_tool；结果成功且已经覆盖问题时停止调用
|
||||
5. 执行 call_data_source_tool 取数；需要先发现接口 / 字段 / 实体的源（caixin_api_search、wind_search_fields、天眼查公司搜索），发现类调用不受“一次”限制，继续调到真正的取数 API。结果成功且已经覆盖问题时停止调用
|
||||
6. 读返回结果，用用户提问时使用的语言回答
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@ import { arch, homedir, hostname, release, type } from 'node:os';
|
|||
import path from 'node:path';
|
||||
import readline from 'node:readline';
|
||||
|
||||
const VERSION = '3.3.0';
|
||||
const VERSION = '3.4.0';
|
||||
const DEFAULT_KIMI_CODE_OAUTH_HOST = 'https://auth.kimi.com';
|
||||
const DEFAULT_KIMI_CODE_BASE_URL = 'https://api.kimi.com/coding/v1';
|
||||
const API_URL = datasourceApiUrl();
|
||||
|
|
@ -29,7 +29,7 @@ const TOOLS = [
|
|||
{
|
||||
name: 'call_data_source_tool',
|
||||
description:
|
||||
"Dispatch one call to the data source selected for the user's request. Always call get_data_source_desc(name) first, then use an api_name and params from that description. For a simple lookup, use one specialized source and stop after its first successful result; do not query fallback or comparison sources unless the user explicitly asks for a cross-source comparison. When the user names a data source, use that source.",
|
||||
"Dispatch one call to the data source selected for the user's request. Always call get_data_source_desc(name) first, then use an api_name and params from that description. For a simple lookup, use one specialized source and stop once a result covers the user's question; do not query fallback or comparison sources unless the user explicitly asks for a cross-source comparison. When the user names a data source, use that source.",
|
||||
inputSchema: {
|
||||
type: 'object',
|
||||
properties: {
|
||||
|
|
@ -72,6 +72,19 @@ const TOOLS = [
|
|||
'gildata',
|
||||
'sec_edgar',
|
||||
'sp_data',
|
||||
'china_nda',
|
||||
'china_nbs',
|
||||
'china_standards',
|
||||
'who',
|
||||
'fao',
|
||||
'unsd',
|
||||
'ecb',
|
||||
'eurostat',
|
||||
'unicef',
|
||||
'oecd',
|
||||
'fred',
|
||||
'xhcj',
|
||||
'caixin',
|
||||
],
|
||||
description:
|
||||
'Data source name. Capabilities: stock_finance_data / yahoo_finance = general quotes and financials ' +
|
||||
|
|
@ -81,7 +94,14 @@ const TOOLS = [
|
|||
'wind = A-share intraday minute series, funds, bonds (map PE/PB/ROE-style field names via wind_search_fields first); ' +
|
||||
'gildata = natural-language stock/fund screening; ' +
|
||||
'sec_edgar = US filings (10-K/10-Q, S-1, Form 4, 13F, 8-K); ' +
|
||||
'sp_data = S&P fundamentals (consensus estimates, valuation ratios, transcripts).',
|
||||
'sp_data = S&P fundamentals (consensus estimates, valuation ratios, transcripts); ' +
|
||||
'china_nda = CN government open data catalogs (National Data Administration registry + provincial platforms); ' +
|
||||
'china_nbs = CN NBS macro indicators and time series (national / provincial / major-city scopes); ' +
|
||||
'china_standards = CN standards (GB national, HB industry, DB local, TT association); ' +
|
||||
'who / fao / unsd / ecb / eurostat / unicef / oecd / fred = international organization open data ' +
|
||||
'(global health, food & agriculture, UN statistics, ECB & EU statistics, child indicators, OECD datasets, US & global macro series); ' +
|
||||
'xhcj = Xinhua Finance (CNFIC) news flashes, announcements, and policies; ' +
|
||||
'caixin = Caixin database (600+ data APIs, discover via caixin_api_search first).',
|
||||
},
|
||||
},
|
||||
required: ['name'],
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
{
|
||||
"name": "kimi-datasource",
|
||||
"version": "3.3.0",
|
||||
"description": "Finance, macro, enterprise, academic, and legal data tools for Kimi Code.",
|
||||
"version": "3.4.0",
|
||||
"description": "Stocks and financials from Wind, S&P Capital IQ, SEC EDGAR, etc.; news from Caixin, Xinhua Finance; macro from World Bank, IMF, FRED, NBS; corporate, academic, legal data, and more",
|
||||
"keywords": ["finance", "data-source", "mcp", "legal"],
|
||||
"mcpServers": {
|
||||
"data": {
|
||||
|
|
@ -12,7 +12,7 @@
|
|||
},
|
||||
"interface": {
|
||||
"displayName": "Kimi Datasource",
|
||||
"shortDescription": "Finance, macro, enterprise, academic, and legal data tools",
|
||||
"shortDescription": "Stocks and financials from Wind, S&P Capital IQ, SEC EDGAR, etc.; news from Caixin, Xinhua Finance; macro from World Bank, IMF, FRED, NBS; corporate, academic, legal data, and more",
|
||||
"developerName": "Moonshot AI"
|
||||
}
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue