mcpbeat Sign in

DataSinking MCP Server

by heubme2020 Your server? Claim it
answering

DataSinking is answering right now. Last checked 2 min ago. 1 323 installs a week from pypi. It exposes 8 tools. Last commit 30 Oct 2026.

Full-text financial reports (US, China, Japan, Korea, Taiwan, UK) as clean Markdown for RAG agents.

Installs per day peak 548 · avg 39 · -14% w/w
a month agotoday
Uptime history 42 days of history · worst day 95%
42 days agonow
100.0%
Uptime 24h
91 of 91 checks
8
Tools
read from the server
223 ms
Response time
average over 24h
1 323
Installs / week
npm and PyPI

What changed 4

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 29 October 2026. No other catalogue keeps this.

29 Oct 2 tools appeared get_feedback_status, submit_feedback
29 Oct a tool description was rewritten list_exchanges
29 Oct a tool changed version

What the code does

We read the source, 2 d ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

    r = subprocess.run(cmd, cwd=str(HERE))

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

run in your terminal
claude mcp add datasinking --transport http https://api.datasink.ing/mcp
Settings → Connectors → Add custom connector, then paste this address
https://api.datasink.ing/mcp
~/.codex/config.toml
[mcp_servers.datasinking]
url = "https://api.datasink.ing/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "datasinking": {
      "url": "https://api.datasink.ing/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "datasinking": {
      "type": "http",
      "url": "https://api.datasink.ing/mcp"
    }
  }
}

Available tools 8

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

exchanges
list_exchanges
List the exchanges DataSinking covers. Returns exchange codes (bj / br / by / jpx / koe / ksc / lk / lse / nasdaq / np / nyse / otc / pk / rs / sse / szse / tpex / twse) with the number of reports available per exchange. Call this first to discover coverage. Sources: US = SEC EDGAR, A-shares = cninfo.com.cn, Japan = EDINET, Korea = DART, Taiwan = MOPS, Europe = filings.xbrl.org (ESEF), Nepal = NEPSE, Brazil = CVM, Belarus = ЕПФР, Sri Lanka = CSE, Pakistan = PSX, Serbia = SEC register.
feedback
get_feedback_status
Check the progress of a submitted feedback request. status is one of pending / processing / done / failed.
report
get_report
Fetch one report's full text (metadata + Markdown body). The `source` field names the official disclosure platform; keep that attribution when you cite it. Expensive in tokens — prefer get_section when you only need one chapter. Content is annotated with block markers (`<!-- ds:block:N -->`) so you can cite a specific paragraph or table.
reports
list_reports
List a company's reports — metadata only (id, title, period), no body text. Each item carries a `source` field naming the official disclosure platform; keep that attribution when you cite it. Look up by `symbol` (FMP-style, e.g. AAPL / 600519.SS / NABIL.NP) or by `exchange` + `stock_code` (from list_stocks) for markets whose codes aren't ticker-shaped (e.g. Brazil CNPJ, Sri Lanka 'AAA.N0000').
section
get_section
Fetch only one section of a report by keyword — much cheaper than get_report, best for RAG. Content is annotated with block markers (`<!-- ds:block:N -->`) so you can cite a specific paragraph or table.
sections
list_sections
List every section of a report with its size, before you decide what to pull. Returns `sections` (titles, in order) plus `section_details` — same order, one entry per section with `title`, `has_tables`, `chars` and `estimated_tokens`. Use `estimated_tokens` to avoid pulling a chapter that would blow your context, and `has_tables` to know whether the chapter needs special handling (tables are the part RAG pipelines usually get wrong). Then call get_section with a heading keyword — the headings are in the report's own language.
stocks
list_stocks
List the stocks on one exchange, including the report count per company.
submit
submit_feedback
Request a full backfill of a stock whose reports look missing or broken, and return its current status. Idempotent — if the stock was already submitted recently (within the last 127 feedback records), it returns that existing status instead of queueing a duplicate; otherwise it queues a re-fetch from the IPO prospectus onward and returns status 'pending' plus the new id (poll get_feedback_status). Free keys: once per 3 seconds, 31 stocks per 7 days per key. Yearly keys: 3 per second, 8,191 stocks per 7 days per key.

Endpoints

URLTransportStateLatencyChecked
https://api.datasink.ing/mcp streamable-http answering 291 ms 2 min ago

Alternatives to DataSinking

same job, measured the same way
1gateway
by code0xff

Pay-per-call tools for agents via x402 (USDC on Base): Korean data, doc-to-Markdown, web utilities.

90 tools answering
Katana — Japan Stock Screener
by katanascreener

Screen every listed company in Japan by financials, custom formulas, and annual report text.

answering
memory-boost
by arnaugonzalez

Markdown memory for coding agents that audits itself: drift reports and session digests.

82 installs/wk local only
lintlab PDF To Markdown
by lintlab

Convert PDF URLs to clean Markdown and text for RAG and LLM input. Pay per PDF on Apify.

answering
Oviond
by oviond

Build branded agency client reports from 100+ marketing datasources.

answering
AsItIs
by katta041

Read-only MCP server for markdown and agent steering files: read, outline, lint, context budget.

95 installs/wk local only
Company Filing Index — SEC Reports, $0.001 a Company
by kriton-dev

Read recent company financial filing metadata from the official SEC JSON API

answering
Xero
by wyre-ai

MCP server for Xero accounting — contacts, invoices, payments, accounts, and financial reports.

local only

DataSinking — questions

Answers built from our own checks of this server.

What can DataSinking do?
It exposes 8 tools, read directly from the server on our last check. Among them: get_feedback_status, get_report, get_section, list_exchanges, list_reports, list_sections and 2 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is DataSinking working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 223 ms. The bar chart above shows every period we have measured.
How do I connect DataSinking?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does DataSinking need an API key?
No. DataSinking completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 8 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is DataSinking?
It answers our handshake in 223 ms on average, which is faster than 64% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use DataSinking?
The npm package datasinking-mcp was installed 1 323 times in the last week. Week over week that is -14%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is DataSinking open source?
The code is open source: it is published under the MIT licence, written in Python and 22 stars on GitHub. The licence covers the code in the repository, not the hosted service at api.datasink.ing, which runs on its operator's own terms.