aikstockdata

npx add-mcp 'https://mcp.aikstockdata.com/mcp'

Korean Stock MCP Server by aikstockdata — free, no authentication

Connect Claude or ChatGPT to Korean market data in about 30 seconds. Paste this endpoint as a custom connector — there is no API key and nothing to sign up for:

https://mcp.aikstockdata.com/mcp

Listed in the official MCP Registry as com.aikstockdata/mcp (domain-verified). Transport is Streamable HTTP, stateless JSON-RPC.

What the AI can then do

• Look up one stock by name or 6-digit code — close, market cap, latest filings.
• Read a day's market digest: index close, advance/decline, the most material filings.
• Pull a stock's daily closing-price history.
• Read the earnings board and growth rankings with the formula stated in the data.

The 12 tools, by name

Names are generated from the running server, not typed here. If a name below is missing from your client, the connector did not finish loading.

Tool	What it returns
get_today	Start here for "how was the Korean market today?" — index levels, breadth, 52-week high/low counts, top-3 disclosures, growth top-3, movers and disclosure-type counts in one call.
search_stock	Find a ticker from part of the name — Korean or Latin, case-insensitive — or a 6-digit code, across every listed stock we publish (no ETFs; markets are named in the response footer).
get_stock	One Korean stock by 6-digit code: T+1 confirmed close & change, market cap, latest financials from the latest periodic report (revenue / operating income / net income, with YoY; Korean reports are cumulative year-to-date, so H1 = Jan-Jun, not Q2 alone), PER(TTM) and PBR computed from public filings, and ranking signals.
get_rankings	Answers "which stocks scored highest on measured DART financials?" — kind='growth' is 성장 TOP8 (max 8 rows), kind='quiet' is 조용한 실적주.
get_market_summary	Index levels (KOSPI/KOSDAQ close, change, %) and up/down breadth — nothing else.
list_stocks	Return the LIST of stocks matching a condition — turnaround to profit, 52-week high/low, growth or quiet-performer rankings — with optional market-cap range and a cap-to-operating-income multiple ceiling.
get_earnings	Earnings from DART, INCLUDING preliminary (잠정) results filed ~2 weeks before the regular report.
get_history	Answers "is this stock near its high or deep in a drawdown, and is volume unusual?" — the stock's accumulated daily CLOSES, plus period high/low, drawdown from the high, and volume vs the 60-day average.
get_disclosure_impact	Answers "what usually happened after this kind of filing?" — median MARKET-ADJUSTED return at +1/+5/+20 trading days per DART filing type (+20 only where that type has enough samples — see h20_status), with 95% intervals, sample window and n.
get_disclosures	Answers "what was filed, and when exactly?" — DART filings with RECEIPT TIME (HH:MM) and session (pre-open / intraday / after-close), filterable by date, type and importance.
get_earnings_calendar	Answers "who has filed this quarter's results, who hasn't, and what came in since last time?" — filed / not-yet lists against the statutory deadline, plus a diff of filings new since the previous publish.
get_data_urls	Direct URLs for every public dataset (JSON/CSV) — no signup, no API key.

Setup

1. Open your AI client's connector or integration settings.
2. Add a custom MCP server with the URL above. Leave authentication empty.
3. Ask something like: "Summarise the Korean stock market for the latest trading day" or "What did Samsung Electronics report most recently?"

If your client does not support MCP, you can get the same data by pasting a JSON URL into the conversation — see the endpoint list. The AI-facing summary of this site lives at /llms.txt.

Why an AI answer from this source is checkable

• Every record carries its own price date and filing cut-off, so the model can state how old the number is instead of implying it is live.
• Per-stock JSON uses null for missing values, so the model cannot mistake "no data" for "zero". (The bulk quote files keep the source convention: open/high/low are 0 when a stock did not trade — check trqu = 0.)
• Every filing links back to the original DART document, so a claim can be traced.
• Response rules for AI are published at /llms.txt and /llms-full.txt.

What is not here

• No real-time or intraday prices. Closing prices only, published the next business day (T+1) by the government source. If you need live quotes, this is the wrong dataset.
• No target prices or analyst ratings. Those are brokerage-derived; this project publishes only public-sector data. (PER and PBR are here where the inputs exist — computed by us from DART financials and FSC closing prices: valuation.pe_ttm, valuation.pb in /data/public/s/{code}.json.)
• No investor-type flows (foreign / institutional / retail).
• No sector classification yet.
• Filing explanations are written in Korean. Field names and structure are English-friendly; the prose is not translated.

This site publishes public data as fact. It is not investment advice and does not recommend buying or selling any security. Source: Financial Services Commission open data portal (prices) and DART, the Financial Supervisory Service filing system. Terms: Non-commercial use with attribution; commercial redistribution is not permitted. (aiksd-public-1.1)

한국어 사이트로 · GitHub · Hugging Face dataset