
全文财务报告(美国、中国、日本、韩国、台湾)作为干净的Markdown — REST API + MCP服务器,适用于LLM、RAG和量化
概览
DataSinking提供年度、半年和季度服务,内容包括干净、准备用于LLM阅读和RAG。通过FMP风格符号(AAPL、600519.SS、7203.T、005930.KS、2330.TW)或按交易所、报告期间筛选,或仅拉取MD&A/风险部分,而非整个申报,节省代币。每个数据均可追溯至其来源披露和区块。报告来源于官方披露平台,并解析为结构化Markdown,带有YAML前言,保留标题、段落和表格。 将DataSinking交付到任何AI代理(Claude / Cursor / Codex / Devin Desktop / n8n)作为MCP服务器——6个工具:列表交换、列表股票、列表报告、获取报告、列表部分、获取一个面板(对RAG支持代币友好)。 一个URL,没有包,没有Python,没有本地服务器。大多数客户端的形状如下: 无法设置头部的客户端可以将键放入URL中——https://api.datasink.ing/mcp?
概述(AI 翻译)
全文财务报告遍及美国和亚洲,作为纯净的Markdown。
DataSinking 提供全文财务报告 — 年度、半年刊
季度刊——来自美国、英国、中国、日本、韩国和台湾,作为干净的Markdown,准备阅读
以及 RAG。通过 FMP 风格符号(AAPL、600519.SS、7203.T、005930.KS、2330.TW)查询或通过
交易所、报告期或部分——只拉MD&A/风险部分,不要全部提取
归档、保存令牌。每个数据均可追溯至其来源披露和
block。报告来源于官方披露平台,并解析为结构化的Markdown
配有YAML前置,保留标题、段落和表格。
MCP服务器
将数据汇入发送到任何AI代理(Claude / Cursor / Codex / Devin Desktop / n8n)作为 MCP服务器——6个工具:列表交易所、列表股票, 列表报告、获取报告、列表部分、获取一个部分(用于 RAG 的标记友好)。
托管 — 无需安装
一个URL,没有包,没有Python,没有本地服务器。大多数客户端的形状如下:
克劳德代码,一句话:
无法设置头部的客户端可以将密钥放入URL中—— 'https://api.datasink.
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
DataSinking
Full-text financial reports across the US, Europe and Asia, as clean Markdown.
DataSinking serves full-text financial reports — annual, semi-annual
and quarterly — from the US, China, Europe, Japan, Korea and Taiwan as clean Markdown, ready for LLM reading
and RAG. Query by FMP-style symbol (AAPL, 600519.SS, 7203.T, 005930.KS, 2330.TW) or filter by
exchange, report period, or section — pull just the MD&A / risk section instead of the whole
filing, saving tokens. Every figure is traceable to its source disclosure and
block. Reports are sourced from official disclosure platforms and parsed into structured Markdown
with YAML frontmatter, preserved headings, paragraphs and tables.
MCP server
Ship DataSinking to any AI agent (Claude / Cursor / Codex / Devin Desktop / n8n) as an MCP server — 8 tools: list exchanges, list stocks, list reports, fetch a report, list sections, fetch one section (token-friendly for RAG), request a full backfill of a stock (idempotent — returns the current status if already queued), check a backfill’s progress.
Hosted — nothing to install
One URL, no package, no Python, no local server. Most clients take this shape:
{
"mcpServers": {
"datasinking": {
"type": "http",
"url": "https://api.datasink.ing/mcp",
"headers": { "Authorization": "Bearer YOUR_KEY" }
}
}
}
Claude Code, in one line:
claude mcp add --transport http datasinking https://api.datasink.ing/mcp \
--header "Authorization: Bearer YOUR_KEY"
A client that can’t set a header can put the key in the URL instead —
https://api.datasink.ing/mcp?apikey=YOUR_KEY — but only do that when you must: a key in a URL
ends up in logs and screen shares, and no client can redact it.
Two clients don’t fit the shape above: Codex’s config is TOML, and Devin Desktop’s remote field is
serverUrl, not url. Per-client files: docs/mcp/.
Local — run it yourself
If you’d rather keep everything on your own machine, there are two identical builds — pick whichever runtime you already have:
Node 18+ (no Python needed):
{
"mcpServers": {
"datasinking": {
"command": "npx",
"args": ["-y", "datasinking-mcp"],
"env": { "DATASINK_API_KEY": "YOUR_KEY" }
}
}
}
Python 3.8+:
pip install "datasinking[mcp]"
datasinking-mcp # requires DATASINK_API_KEY (free at https://datasink.ing)
Then use command: datasinking-mcp in your client.
Both run the same eight tools with the same schemas — npm/ and datasinking/mcp_server.py are
安装
npx -y datasinking-mcp配置
{
"mcpServers": {
"datasinking": {
"type": "http",
"url": "https://api.datasink.ing/mcp",
"headers": { "Authorization": "Bearer YOUR_KEY" }
}
}
}