# DataSinking

> DataSinking is a freemium MCP server for finance and payments. Full-text company financial reports from six markets as Markdown for RAG agents. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Platforms:** API, CLI
- **Website:** https://datasink.ing
- **Repository:** https://github.com/heubme2020/datasinking
- **MCP Registry name:** io.github.heubme2020/datasinking
- **Categories:** finance and payments, analytics and data
- **Listing updated:** 2026-11-15

## About

The point of this server is narrative text, not extracted numbers. Annual, semi-annual and quarterly filings are parsed from official disclosure PDFs into Markdown with headings, paragraphs and tables kept, plus YAML frontmatter and inline unit notes so a model does not confuse millions with units. Sources named on the site are SEC EDGAR, cninfo.com.cn, filings.xbrl.org, EDINET, DART and MOPS.

Coverage is stated as about 26,900 listed companies and over 1.27 million documents across the US, China, the UK and Europe, Japan, South Korea and Taiwan, with history reaching back to roughly 1991 for the US and 2020 for Europe. Tickers use FMP-style symbols such as `AAPL`, `600519.SS` and `7203.T`.

An agent can list a report's headings and fetch only the MD&A or risk section instead of a 300-page filing, which keeps RAG chunks small. The README describes eight tools. They are available as a hosted endpoint at `https://api.datasink.ing/mcp` with a bearer key, or as local stdio builds on npm and PyPI.

## Features

- **Clean Markdown reports:** Filings are parsed from PDFs into Markdown with tables and unit notes preserved.
- **Section-level retrieval:** List a report's headings and pull one section, such as MD&A, instead of the whole filing.
- **Six-market coverage:** US, China, UK and Europe, Japan, Korea and Taiwan across twelve exchanges.
- **FMP-style symbols:** Query by tickers like AAPL, 600519.SS or 005930.KS.
- **Hosted or local:** Use the hosted HTTP endpoint or run the npm or PyPI stdio build.
- **Backfill requests:** Ask for a full backfill of a stock and check its progress.

## Good for

- Feed an annual report's risk section into a RAG pipeline
- Compare management discussion across companies in different markets
- Read a Chinese A-share filing as Markdown
- Check which periods are available for a ticker
- Pull related-party transaction notes for analysis

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http datasinking https://api.datasink.ing/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://api.datasink.ing/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "datasinking": {
      "url": "https://api.datasink.ing/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "datasinking": {
      "type": "http",
      "url": "https://api.datasink.ing/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "datasinking": {
      "serverUrl": "https://api.datasink.ing/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "datasinking": {
      "type": "http",
      "url": "https://api.datasink.ing/mcp"
    }
  }
}
```

## FAQ

### Is there a free key?

Yes. The site says a free key is available by email at POST https://api.datasink.ing/free-key, with no signup.

### What report types are covered?

Annual, semi-annual, Q1 and Q3 reports, and amendments or supplements.

### How far back does it go?

Roughly 1991 for the US, 2000 for mainland China, 2005 for Korea, 2006 for Taiwan, 2015 for Japan and 2020 for Europe.

### Does it return extracted financial figures?

No. It returns full-text reports; structured-number APIs are described as a different product.

### How do I connect without installing anything?

Point an HTTP MCP client at https://api.datasink.ing/mcp with an Authorization: Bearer header.

### Is DataSinking free?

DataSinking has a free plan, with paid plans for more usage or features.

### How do I add DataSinking to Claude Code?

Run this command in your terminal: claude mcp add --transport http datasinking https://api.datasink.ing/mcp

### What are the best alternatives to DataSinking?

The closest alternatives to DataSinking are Agent-Native Analytics, Google Ads + Meta Ads + SEO/GEO MCP, Solana MCP by Vybe, Tapetide - Indian Stock Market MCP and World Monitor.

## Alternatives

- [Agent-Native Analytics](https://ai-powered.com/mcp/agent-native-analytics): Agent-Native Analytics is an open-source MCP server for analytics and data.
- [Google Ads + Meta Ads + SEO/GEO MCP](https://ai-powered.com/mcp/google-ads-meta-ads-seo-geo-mcp): Google Ads + Meta Ads + SEO/GEO MCP is a freemium MCP server for marketing and seo.
- [Solana MCP by Vybe](https://ai-powered.com/mcp/solana-mcp-by-vybe): Solana MCP by Vybe is an MCP server for finance and payments.
- [Tapetide - Indian Stock Market MCP](https://ai-powered.com/mcp/tapetide-indian-stock-market-mcp): Tapetide - Indian Stock Market MCP is a freemium MCP server for finance and payments.
- [World Monitor](https://ai-powered.com/mcp/world-monitor): World Monitor is a freemium MCP server for analytics and data.
- [Budget Tracker](https://ai-powered.com/mcp/budget-tracker-2): Budget Tracker is a freemium MCP server for finance and payments.
- [CompanyData](https://ai-powered.com/mcp/companydata): CompanyData is a paid MCP server for analytics and data.
- [ChartAnt](https://ai-powered.com/mcp/chartant): ChartAnt is a freemium MCP server for design and media.

---
Source: https://ai-powered.com/mcp/datasinking
