Lets an AI client search, fetch, and extract sections of full-text financial reports from the US, Europe, and Asia as clean Markdown.
Also known as heubme2020/datasinking, datasinking-mcp
- Stars
- 23
- Tools
- —
- Downloads, 30 days
- 1,546
- Latest version
- 0.2.17
- Last commit
- Nov 5, 2026
- License
- MIT
What is DataSinking MCP?
DataSinking lets an AI client search, fetch, and extract sections of full-text financial reports from the US, Europe, and Asia as clean Markdown.
Summary generated from the project's README
About DataSinking MCP server
Extracting full-text financial reports from global markets as clean Markdown is what DataSinking enables for developers and researchers. It provides access to annual, semi-annual, and quarterly filings from the US, China, Europe, Japan, Korea, and Taiwan. Users can query specific companies using FMP-style symbols like AAPL or 7203.T to retrieve structured data including headings, paragraphs, and tables.
This MCP server can be deployed as a hosted service via a single URL or run locally using Node or Python environments. It integrates with AI clients such as Claude, Cursor, and Devin Desktop. The server includes eight specialized tools to list exchanges, stocks, and reports, or to fetch specific sections like MD&A to save tokens during RAG workflows. It also supports full backfills for a stock's entire filing history.
Data is sourced directly from official regulatory platforms like SEC EDGAR and EDINET. Every figure remains traceable to its original disclosure block. While free keys allow for limited document access, paid tiers provide higher request rates and larger document quotas for heavy research tasks.
What you can do with it
- 1Token-efficient RAG ingestionAn AI client can pull only specific chapters like risk factors instead of entire filings to save context window space.
- 2Automated financial researchDevelopers can use the server to gather structured Markdown data for analyzing long-term revenue or profit trends.
- 3Global stock monitoringUsers can query various international exchanges using standardized ticker formats to fetch recent quarterly reports.
- 4Bulk data backfillingA developer can request a complete historical collection of a company's filings through an idempotent background process.
Written from the project's README. Every use case is checked against a quote from it.
How to install DataSinking MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall DataSinking MCP in Claude Code
$ claude mcp add --env 'DATASINK_API_KEY=<YOUR_DATASINK_API_KEY>' datasinking -- uvx datasinkingInstall DataSinking MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"datasinking": {
"command": "uvx",
"args": [
"datasinking"
],
"env": {
"DATASINK_API_KEY": "<YOUR_DATASINK_API_KEY>"
}
}
}
}Install DataSinking MCP in VS Code
.vscode/mcp.json
{
"servers": {
"datasinking": {
"type": "stdio",
"command": "uvx",
"args": [
"datasinking"
],
"env": {
"DATASINK_API_KEY": "<YOUR_DATASINK_API_KEY>"
}
}
}
}Install DataSinking MCP in VS Code CLI
$ code --add-mcp '{"name":"datasinking","type":"stdio","command":"uvx","args":["datasinking"],"env":{"DATASINK_API_KEY":"<YOUR_DATASINK_API_KEY>"}}'Install DataSinking MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"datasinking": {
"command": "uvx",
"args": [
"datasinking"
],
"env": {
"DATASINK_API_KEY": "<YOUR_DATASINK_API_KEY>"
}
}
}
}Install DataSinking MCP in Codex
$ codex mcp add datasinking --env 'DATASINK_API_KEY=<YOUR_DATASINK_API_KEY>' --env 'DATASINK_API_KEY=<YOUR_DATASINK_API_KEY>' -- uvx datasinkingInstall DataSinking MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.datasinking] command = "uvx" args = ["datasinking"] [mcp_servers.datasinking.env] DATASINK_API_KEY = "<YOUR_DATASINK_API_KEY>"
Install DataSinking MCP in Gemini CLI
$ gemini mcp add -s user -e 'DATASINK_API_KEY=<YOUR_DATASINK_API_KEY>' -e 'DATASINK_API_KEY=<YOUR_DATASINK_API_KEY>' datasinking uvx -- datasinkingInstall DataSinking MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"datasinking": {
"command": "uvx",
"args": [
"datasinking"
],
"env": {
"DATASINK_API_KEY": "<YOUR_DATASINK_API_KEY>"
}
}
}
}Configuration
DATASINK_API_KEYRequiredSecretYour DataSinking API key. Free key at https://datasink.ing
DATASINK_API_KEYRequiredSecretYour DataSinking API key. Free key at https://datasink.ing
DATASINK_API_KEY
| Name | Description | |
|---|---|---|
| DATASINK_API_KEY | Your DataSinking API key. Free key at https://datasink.ing | RequiredSecret |
| DATASINK_API_KEY | Your DataSinking API key. Free key at https://datasink.ing | RequiredSecret |
| DATASINK_API_KEY | — |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubDataSinking
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
kept in lockstep by check_mcp_parity.py.
Full per-client setup: mcp-server.md (overview) ·
docs/mcp/ (one guide per client).
The hosted endpoint is POST-only and stateless — GET /mcp returns 405, and no session id is
issued. Most clients read MCP config at launch, so restart one after changing its config.

What this repo is
Examples, research and tutorials showing how to work with financial report data, including reproducing the presentation styles found in financial-report research papers.
datasinking/
├── examples/ # Example scripts: pull data from the API and analyze it
├── research/ # Research notes / blog posts (reproducing paper-style presentation)
├── datasinking/ # Python client + MCP server — pip install "datasinking[mcp]"
├── npm/ # The same MCP server on npm — npx -y datasinking-mcp (Node 18+)
├── r-datasinking/ # R client — remotes::install_github("heubme2020/datasinking", subdir="r-datasinking")
├── docs/mcp/ # Per-client MCP setup — Claude Code, Desktop, Cursor, Codex, WorkBuddy, Devin…
├── mcp-server.md # MCP server overview — endpoint, per-client table, tools, troubleshooting
├── llm-examples.md # Ask an LLM — no code needed (10 end-to-end examples)
├── api-examples.md # 8 examples × 3 interfaces (curl / Python / LLM)
└── README.md
Per-client MCP guides — one file each, with the exact config path, both scopes, verification and the errors that client actually produces:
| Client | Guide |
|---|---|
| Claude Code | docs/mcp/claude-code.md |
| Claude Desktop | docs/mcp/claude-desktop.md |
| OpenAI Codex CLI | docs/mcp/codex.md |
| WorkBuddy / CodeBuddy | docs/mcp/workbuddy.md |
| Doubao Work / 豆包工作 | docs/mcp/doubao.md |
| Cursor | docs/mcp/cursor.md |
DeepSeek Harness (dsh) |
docs/mcp/deepseek.md |
| Devin Desktop | docs/mcp/windsurf.md |
| OpenCode | docs/mcp/opencode.md |
| Qoder | docs/mcp/qoder.md |
| Reasonix | docs/mcp/reasonix.md |
Quick start
- Get an API key at datasink.ing
- One line (FMP-style
?apikey=):
curl "https://api.datasink.ing/documents?symbol=600519.SS&with_content=1&apikey=YOUR_KEY"
Or in Python:
pip install datasinking
from datasinking import DataSinking
ds = DataSinking("YOUR_KEY")
for r in ds.get_stock_reports("600519.SS", limit=3):
print(r["report_period"], r["title"], len(r["content"]), "chars")
The full reference (curl / Python / LLM): api-examples.md.
Ask an LLM (no code)
Don't want to write code? Point any LLM at datasink.ing,
give it your API key, and ask in plain language. See
llm-examples.md for ten end-to-end examples — explore
coverage, list a company's reports, and extract a figure with correct units.
RAG frameworks
Official integrations load reports straight into LlamaIndex, LangChain, or Haystack — one import, one call:
from datasinking.llama_index import DataSinkingReader
docs = DataSinkingReader(api_key="YOUR_KEY").load_data("AAPL", doc_type="annual")
from datasinking.langchain import DataSinkingLoader
docs = DataSinkingLoader(api_key="YOUR_KEY", symbol="AAPL").load()
from datasinking.haystack import DataSinkingFetcher
docs = DataSinkingFetcher(api_key="YOUR_KEY", symbol="AAPL").run()["documents"]
Pass split_by_section=True to load one Document per section (token-friendly for RAG). Each Document's
metadata keeps the official disclosure source. Install the client with pip install -U datasinking; each
framework is an optional dependency you install separately.
Examples (examples/)
| File | What it does |
|---|---|
01_quickstart.py |
The core functions: list exchanges / stocks / reports / fetch a report / fetch a stock's reports |
02_download_company.py |
Download a company's full reports to local Markdown files |
03_download_exchange.py |
Download an entire exchange's reports (all stocks) to local Markdown files |
rag_ingest.py |
Slice reports into RAG chunks (on the <!-- ds:block:N --> anchors, with source traceability) and ingest into a vector store |
Every example pulls from the live API and runs as-is.
03_download_exchange.pyfetches every report on an exchange (e.g. all of Shenzhen — 150k+ documents). Quotas count documents, not requests, over a rolling 7-day window: a free key gets 3 req/s and 8,191 documents per 7 days, inside a pool of 524,287 per 7 days shared by all free users and website visitors. A whole exchange will therefore take well over a week on a free key — a paid (yearly) key (31 req/s, 524,287 documents per 7 days) is strongly recommended.
Research (research/)
research/ hosts research notes and blog posts, each based on DataSinking data with the source cited. You can reproduce charts and presentations found in financial-report research papers, e.g.:
- Long-term revenue / profit trends
- Industry comparison and distribution
- Time series of financial metrics
Start from research/TEMPLATE.md.
Data overview
| Coverage | US (NYSE / NASDAQ / OTC) · China (SSE / SZSE / BSE) · Europe (ESEF) · Japan (TSE) · Korea (KOSPI / KOSDAQ) · Taiwan (TWSE / TPEx) |
| Document types | annual / semiannual / q1 / q3 / amendment |
| Update frequency | Daily — US/Korea/Japan via official SEC EDGAR / DART / EDINET APIs (new filings within ~24h of publication) |
| Format | Full-text Markdown (with YAML frontmatter) |
| API | REST — GET /documents, batch download, with_content=1 for full text, ?section= + /sections for chapter-level access, POST /feedback for full backfill of a stock's filings |
| Symbols | FMP style: AAPL / 600519.SS / 7203.T / 005930.KS |
| Auth | ?apikey= query parameter (FMP style) |
Data source
Reports are sourced from the official regulatory disclosure platform of each market and converted in-house to clean Markdown:
| Market | Source | Platform |
|---|---|---|
US (bare ticker, e.g. AAPL) |
SEC EDGAR | US Securities and Exchange Commission — sec.gov/edgar |
China A-shares (.SS .SZ .BJ) |
巨潮资讯网 cninfo | CSRC-designated disclosure platform |
| Europe | ESEF | European Single Electronic Format — filings.xbrl.org |
Korea (.KS .KQ .KN) |
DART | Financial Supervisory Service — opendart.fss.or.kr |
Japan (.T) |
EDINET | Financial Services Agency — disclosure2.edinet-fsa.go.jp |
Taiwan (.TW .TWO) |
公開資訊觀測站 MOPS | Taiwan Stock Exchange — mops.twse.com.tw |
Every document also carries a source field in the API response, so the attribution travels with the data. Please keep it when you redistribute.
How to cite
If you use DataSinking in a paper, add a data-availability note (and, optionally, an acknowledgment).
Data availability:
Full-text financial reports (annual, semi-annual, and quarterly filings across the US, China, Europe, Japan, Korea, and Taiwan) were obtained from DataSinking (https://datasink.ing) in Markdown format.
BibTeX:
@misc{datasinking2026,
author = {{DataSinking}},
title = {{DataSinking: Full-text financial reports as Markdown}},
year = {2026},
howpublished = {https://datasink.ing},
note = {Accessed: 2026-10-27}
}
DataSinking provides report text, not investment advice.
Affiliate
Earn $7 every purchase for every customer you refer — recurring, PayPal, $31 minimum withdrawal: datasink.ing/affiliate
License
DataSinking MCP questions
How do I add DataSinking MCP to Claude Code?
Run claude mcp add --env 'DATASINK_API_KEY=<YOUR_DATASINK_API_KEY>' datasinking -- uvx datasinking in your terminal. Add --scope user to make it available in every project.
How do I add DataSinking MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Which markets does DataSinking cover?
It covers the US, China, Europe, Japan, Korea, and Taiwan, sourced from each market's official disclosure platform.
What tools does the DataSinking MCP server expose?
It exposes eight tools: list exchanges, list stocks, list reports, fetch a report, list sections, fetch one section, request a backfill, and check backfill progress.
How do I authenticate to the DataSinking MCP server?
Pass an API key as a Bearer token in the Authorization header, or as an apikey query parameter when a client cannot set headers.
Can I fetch only one section of a report instead of the whole filing?
Yes, you can request chapter-level access to just a section such as MD&A or risk, which saves tokens.
What format are the reports returned in?
They come back as full-text Markdown with YAML frontmatter, preserved headings, paragraphs, and tables, and each figure is traceable to its source block.