Skip to main content
Glama

Korea DART MCP

Read Korean corporate filings in English, through Claude or any MCP client.

CI PyPI License: MIT M8ven Score

Korea has one of the world's largest stock markets, yet its disclosure system, DART, is almost entirely in Korean. Samsung's annual report, a KOSDAQ company's convertible bond terms, and a chaebol's ownership chart are all public, but you can only use them if you read Korean and know what to look for.

This server gives an AI agent both of those skills. Ask in English:

"What has Samsung Electronics disclosed in the last six months, and is anything a red flag?"

The agent gets back English filing titles, events grouped by type and severity, and plain-English warnings. Every answer links to the original filing.

The output looks like this (shortened):

get_material_events("Samsung Electronics", days=180)
→ counts_by_category: { capital_return, periodic, ownership, earnings, ... }
→ events:   [{ title_en: "Treasury Stock Buyback Decision",
               title_ko: "주요사항보고서(자기주식취득결정)",
               category: "capital_return", severity: "notable",
               why_it_matters: "Shareholder returns: buybacks, cancellations, dividends, or a Value-up plan.",
               url: "https://dart.fss.or.kr/dsaf001/main.do?rcpNo=…" }, …]
→ red_flags: []

Why this one

Several DART MCP servers already exist, and most are built for Korean speakers: Korean docs, Korean output, one tool per API endpoint. This one is built for people who don't read Korean.

Typical DART wrapper

Korea DART MCP

Find a company

By Korean name or the 8-digit corp_code

English name, Korean name or ticker (Samsung Electronics, 삼성전자 and 005930 all work)

Filing titles

[기재정정]주요사항보고서(전환사채권발행결정)

Adds [Amended] Convertible Bond (CB) Issuance Decision

Financials

Raw strings with Korean account names

Integer KRW, English account labels, plus margins, growth, ROE and leverage

"Anything I should worry about?"

You read every filing

get_material_events: 13 categories, severity levels and red-flag rules for Korea

Reading a 300-page annual report

Download a ZIP

section="business", "mdna" or "risk_factors" jumps to the part you need

Context

None

US comparisons (13D, Form 4, 10-K) and a primer on chaebol, KOSDAQ and Value-up

Translation

Up to the LLM, sometimes wrong

A curated glossary for jargon. Korean is always returned too, so the model can verify

Related MCP server: Korea Stock Insight MCP

Tools

Tool

Ask it…

get_material_events

"What's going on at this company? Any red flags?" or "Which KOSDAQ companies issued convertible bonds this month?"

get_financial_statements

Balance sheet, income statement and cash flow with English labels and key_metrics

compare_companies

Revenue, margins, ROE and leverage for up to 10 companies side by side

get_filing_text

Read any filing by section (business, mdna, risk_factors, audit, ...), by keyword, or page by page

get_recent_filings

Filings for a company or the whole market, with English titles. Ranges longer than 90 days are split automatically

get_insider_trades

Korea's Form 4: each insider's holdings and share changes, with totals for directors and 10%+ holders

get_major_shareholder_changes

Korea's 13D/13G: who crossed or changed a 5% stake

get_largest_shareholders

Controlling shareholder and related parties, i.e. the chaebol control structure

get_dividends

Dividend per share, payout ratio and yield

get_company_profile

CEO, market, industry, fiscal year-end, IR site

search_company

Which "Samsung"? Shows the candidates, listed companies first

translate_terms

Glossary for DART jargon (유상증자, 최대주주, 리픽싱 ...), no API call needed

It also has a company_brief prompt, which builds a full English brief from these tools, and a dart://guide/korea-primer resource that explains Korean disclosure rules and common pitfalls.

All tools are marked read-only, so clients can approve them automatically.

Quick start

1. Get a free DART API key (2 minutes, 20,000 requests/day). The OpenDART site is in Korean, so follow the English walkthrough.

2. Add it to your client.

Claude Code:

claude mcp add dart -e DART_API_KEY=your_key -- uvx korea-dart-mcp

Claude Desktop, Cursor, Windsurf and other MCP clients:

{
  "mcpServers": {
    "dart": {
      "command": "uvx",
      "args": ["korea-dart-mcp"],
      "env": { "DART_API_KEY": "your_key" }
    }
  }
}

uvx comes with uv. To run it from source instead, use "command": "uv", "args": ["--directory", "/path/to/dart-mcp", "run", "korea-dart-mcp"].

3. Ask a question.

  • "Write an English investment brief on Samsung Electronics." (or use the company_brief prompt)

  • "Compare Samsung Electronics and SK hynix on margins and ROE for 2024."

  • "Who controls Samsung Electronics? Show the largest shareholder and related parties."

  • "How many shares did Samsung Electronics directors and major shareholders add or dispose of this year?"

  • "Summarize the business section of Samsung Electronics' latest annual report in English."

  • "Which KOSDAQ companies announced convertible bond issues in the last 30 days?"

Remote / team deployment

docker build -t korea-dart-mcp .
docker run -e DART_API_KEY=your_key -p 8000:8000 -v dart-cache:/data korea-dart-mcp
# serves MCP over streamable HTTP at http://localhost:8000/mcp

The HTTP transport has no authentication. Put it behind a gateway that handles auth before exposing it.

Env var

Default

Purpose

DART_API_KEY

(required)

OpenDART key

DART_MCP_CACHE_DIR

~/.cache/dart_mcp

Company list cache (about 100k entities, refreshed weekly)

DART_MCP_LOG_LEVEL

INFO

Logs go to stderr

DART_MCP_HOST / DART_MCP_PORT

127.0.0.1 / 8000

HTTP bind address

How it works

  • Company resolution: DART's full company list (about 100k entities, with English names where registered) is cached locally and matched by ticker, English name or Korean name. Legal-form suffixes like "Co., Ltd." and "(주)" are ignored.

  • Glossary (glossary.py): hand-curated mappings for 80+ filing types, financial accounts, ownership relationships and governance terms. Accounts outside the glossary fall back to their IFRS XBRL tag (ifrs-full_ProfitLossAttributableToOwnersOfParent becomes "Profit loss attributable to owners of parent").

  • Diagnostics (analysis.py): rules that classify filings into categories such as distress, control change, dilution and exchange scrutiny. On top of that are red-flag rules for Korean market patterns, like serial CB issuance, conversion-price refixing and frequent amendments. Every rule is plain code with unit tests, and none of it is a black box.

  • Production details: retries with backoff, a TTL cache, a concurrency limit, DART status codes turned into clear errors, EUC-KR fallback, and paging for large filings.

Limitations

  • Structured financials (XBRL) start in FY2015. Some financial firms and unlisted companies don't file XBRL, so read their reports with get_filing_text.

  • Insider "changes" include grants, option exercises and inheritance, not only open-market trades.

  • Red flags are heuristics to start an investigation, not investment advice.

  • The glossary covers common terms. Unknown terms come back with *_en: null, and the LLM translates them from the Korean, which is always included.

Development

uv sync
uv run pytest            # offline: DART is mocked
uv run ruff check src tests && uv run ruff format --check src tests

Contributions are welcome, especially new glossary terms and red-flag rules. See CLAUDE.md for the architecture and conventions.

License

MIT. Free to use, modify and redistribute, including commercially, as long as the copyright notice is kept. DART data belongs to the Financial Supervisory Service (금융감독원); follow OpenDART's terms of use. Nothing here is investment advice.

Available Tools

10 tools
get_company_profileA

Company overview: English/Korean name, CEO, market, industry code, address, website, fiscal year-end.

company accepts a ticker (005930), corp_code, or name.

Inputs: company (required). Returns: object

get_dividendsB

Dividend data from a periodic report: DPS, payout ratio, yield, total paid (배당에 관한 사항).

Labels are Korean (e.g. 주당 현금배당금(원) = cash dividend per share in won, 현금배당성향(%) = payout ratio, 현금배당수익률(%) = dividend yield).

Inputs: year (required), company (required), period. Returns: object

get_filing_textA

Read the original text of a filing (Korean) by its 14-digit rcept_no.

Returns a table of contents with character offsets; page through long filings with offset. Pass search (a Korean keyword such as 매출, 배당, 최대주주, 소송) to get matching snippets instead of a page. Tables are flattened to ' | '-separated rows. Translate the returned text as needed and cite url.

Inputs: rcept_no (required), offset, search, max_chars. Returns: object

get_financial_statementsA

Financial statements from XBRL filings, with English account labels.

  • year: fiscal year (2015+). period: annual, half (H1), q1, q3. For Q4/full-year use annual.

  • consolidated: True = consolidated (CFS); falls back to separate (OFS) if the company files no consolidated statements.

  • detail: summary = key accounts (revenue, operating profit, net income, assets, liabilities, equity); full = every line of BS, IS, CIS, CF, SCE. Amounts are integers in KRW (won). 'current' is the reported period; for quarterly income statements 'current' is the 3-month quarter and 'current_year_to_date' is cumulative.

Inputs: year (required), company (required), detail, period, +1 more. Returns: object

get_insider_tradesB

Executive and major-shareholder ownership reports (임원ㆍ주요주주 소유보고).

Korea's equivalent of SEC Form 4: holdings and changes by directors, officers, and 10%+ holders. Newest first.

Inputs: company (required), limit. Returns: object

get_largest_shareholdersB

Largest shareholder and related parties as of a periodic report (최대주주 현황).

Reveals chaebol control structure: founding family, affiliates, foundations, and their stakes at the start and end of the period.

Inputs: year (required), company (required), period. Returns: object

get_major_shareholder_changesA

5% block-holding reports (대량보유상황보고): who crossed or changed a 5%+ stake.

Korea's equivalent of SEC Schedule 13D/13G. Shows filer, shares held, ownership %, change vs. prior report, and stated reason. Newest first. Key activist/M&A signal.

Inputs: company (required), limit. Returns: object

get_recent_filingsA

List DART filings, newest first, with English titles where known.

  • company: ticker / corp_code / name. Omit to see the whole market (DART limits market-wide searches to a 3-month window).

  • filing_type: periodic (annual/quarterly reports), major_event (M&A, capital raises, litigation), issuance, ownership (5% block / insider), other, audit, fund, abs, exchange (preliminary earnings, KRX inquiries), ftc.

  • start_date / end_date (YYYY-MM-DD) override days. Use get_filing_text with a returned rcept_no to read the filing body.

Inputs: days, page, limit, company, +4 more. Returns: object

search_companyA

Find Korean companies on DART by English name, Korean name, KRX ticker, or corp_code.

Use this first when unsure which entity a name refers to (e.g. "Hyundai" matches dozens of group companies). Listed companies rank first.

Inputs: query (required), limit, listed_only. Returns: result

translate_termsA

Look up Korean disclosure, accounting, and governance terms in a curated glossary.

More reliable than generic translation for DART jargon (e.g. 유상증자, 최대주주, 전환사채, 공정공시, 기재정정). Returns null for unknown terms. No API call needed.

Inputs: terms (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 10 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes, and the ownership trio (5% block changes, insider Form 4-style reports, largest-shareholder snapshots) is differentiated via descriptions referencing different DART report types. There is still mild potential for confusion between get_insider_trades (10%+ holders) and get_major_shareholder_changes (5% blocks), since both concern large holders.

    Naming Consistency4/5

    Eight of ten tools follow a clean verb_noun pattern (get_recent_filings, get_financial_statements, get_dividends, etc.). search_company and translate_terms are sensible verb-first deviations, though they slightly break the otherwise uniform get_ prefix convention.

    Tool Count5/5

    Ten tools is well-scoped for a DART filings server: one discovery tool, one profile, one glossary helper, and seven focused data-retrieval tools. Each tool earns its place without redundancy.

    Completeness4/5

    Coverage of the core lifecycle is strong: entity search, profile, filing listing and full-text retrieval, XBRL financials, ownership/largest-shareholder data, and dividends. Minor gaps remain (e.g., no dedicated capital-raise/event summary or notes to financial statements), but agents can work around these via get_filing_text.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to access Korean corporate disclosure data from DART, allowing natural language queries about companies, financial statements, and disclosures.
      54 npm
      2
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables LLM agents to access Korean stock market data including DART disclosures, financial statements, and KOSPI/KOSDAQ prices, with an English-first interface designed for non-Korean speaking analysts.
      6
      35 PyPI
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI-powered analysis of Korean stock market data and corporate disclosures using official DART and KRX APIs.
      190 npm
      ISC
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides AI assistants with real-time access to Korean listed companies' disclosures, financial statements, and corporate information via the DART API.
      4
      MIT