
한국주식데이터 MCP server
Which servers in the official MCP registry are 한국주식데이터's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-24
- Registry namecom.aikstockdata/mcpverified in the MCP registry
The registry name sits under aikstockdata.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-24
- Tools12
- Server calls itselfaikstockdata-mcp
- Server version2.1.2
- Protocol version2025-06-18
On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 144 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 2 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
- Answeredmeasuring2 of the 7 daily checks it takes to print a share
- Median first answer130 ms
- Space in an agent's context≈ 2,870 tokensthe definitions of all its tools (12), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 12 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · pull daily KOSPI and KOSDAQ stock data via API
- not sure · feed Korean market data into Claude or ChatGPT through MCP
- not sure · download Korean stock datasets as CSV files
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
get_todayStart 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. Then drill down with get_stock / list_stocks /…
search_stockFind 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). Korean readings of Latin names also match ('네이버' finds…
get_stockOne 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…
get_rankingsAnswers "which stocks scored highest on measured DART financials?" — kind='growth' is 성장 TOP8 (max 8 rows), kind='quiet' is 조용한 실적주. Scores come from a published formula over ACTUAL filed financials only — no prices, no analyst estimates…
get_market_summaryIndex levels (KOSPI/KOSDAQ close, change, %) and up/down breadth — nothing else. Prices are the previous session's T+1 settled close, never real-time. Index and breadth routinely disagree — the index is cap-weighted, breadth is one vote…
get_data_urlsDirect URLs for every public dataset (JSON/CSV) — no signup, no API key. Call this BEFORE concluding something is unavailable: the tool list is not the extent of the data. Returns the endpoint catalog (quotes, disclosures, rankings…
get_earningsEarnings from DART, INCLUDING preliminary (잠정) results filed ~2 weeks before the regular report. Each row says whether the figure is year-to-date cumulative or a single quarter. Pass a code for one stock's history, or omit it for the…
get_historyAnswers "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. Close-based (this history file…
get_disclosure_impactAnswers "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…
get_earnings_calendarAnswers "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. Built for stateless agents…
get_disclosuresAnswers "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. OpenDART's filing-list API returns the receipt date only; we…
list_stocksReturn 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. Other tools give counts; this one…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"aikstockdata": {
"type": "http",
"url": "https://mcp.aikstockdata.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http aikstockdata https://mcp.aikstockdata.com/mcpclaude.ai, ChatGPT and other clients: add https://mcp.aikstockdata.com/mcp as a custom connector in the settings.
OpenAPI spec
39 paths, read 2026-10-24. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.