広告掲載
MCP.so
ログイン
P

penDART MCP - Korean corporate disclosure data for AI agents

@SongHyojun0228

リポジトリ

基本情報

カテゴリ

データと分析

トランスポート

stdio

作者

SongHyojun0228

投稿者

효준 송

penDART MCP - Korean corporate disclosure data for AI agents について

### Server Name

penDART MCP - Korean corporate disclosure data for AI agents の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "opendart": {
      "command": "npx",
      "args": [
        "-y",
        "opendart-mcp"
      ],
      "env": {
        "DART_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

penDART MCP - Korean corporate disclosure data for AI agents のツール

5

Search for a Korean company and get basic corporate info (한국 기업 검색 및 기본 정보 조회). Input can be a company name (삼성전자), stock code (005930), or DART corp code (00126380).

Search DART disclosure filings (공시 보고서 검색). Can search by company or browse all recent filings. Returns filing title, date, and DART link.

Get key financial data for a Korean company (기업 주요 재무 데이터 조회). Returns revenue, operating profit, net income, total assets/liabilities/equity with year-over-year change rates.

Compare financial data across multiple Korean companies (다중 회사 재무 비교). Shows revenue, operating profit, and net income side by side.

Get full financial statements with all account items (전체 재무제표 상세 조회). Returns every line item of BS, IS, CIS, CF, or SCE.

概要

What is penDART MCP - Korean corporate disclosure data for AI agents?

penDART MCP connects AI agents (Claude Desktop, Cursor, etc.) to Korea’s DART (Electronic Disclosure System) official corporate filings. It lets you ask natural‑language questions like “Show me Samsung Electronics’ financial statements” and get real answers from public Korean financial data.

How to use penDART MCP - Korean corporate disclosure data for AI agents?

Add the server to your AI client’s MCP configuration (e.g., claude_desktop_config.json). Run with npx opendart-mcp and set the DART_API_KEY environment variable. A free API key is obtained from opendart.fss.or.kr. Corporate codes are downloaded automatically on first start.

Key features of penDART MCP - Korean corporate disclosure data for AI agents

  • Search Korean companies by name, stock code, or DART corp code.
  • Search disclosure filings with date/type filters.
  • Get key financials: revenue, operating profit, net income, assets, liabilities.
  • Compare financials across multiple companies side by side.
  • Retrieve full financial statements (balance sheet, income statement, cash flow, etc.).

Use cases of penDART MCP - Korean corporate disclosure data for AI agents

  • Ask your AI for a company’s basic information and stock code.
  • Query recent disclosure filings for a specific company.
  • Request annual or quarterly financial summaries (e.g., revenue, net income).
  • Compare financial performance of competing Korean companies.
  • Retrieve detailed financial statements for in‑house analysis.

よくある質問

1

How do I get a DART API key?

Sign up at [opendart.fss.or.kr](https://opendart.fss.or.kr), log in, and apply for an API key. It is issued instantly and free of charge.

2

Is the API key free? Are there usage limits?

Yes, it is free. The DART OpenAPI allows up to 10,000 requests per day.

3

Do I need to manually download the corporate code data?

No. The server automatically downloads the corporate code database on first run. You can manually update it later with `npm run update-corp-codes` if needed.

4

Which AI clients are supported?

Claude Desktop and Cursor are explicitly supported. Any MCP‑compatible client (including MCP Inspector for debugging) can be used.

5

What is the project structure?

The server entry point is `src/index.ts`. Tools are organized in `src/tools/` (disclosure and financial) and utilities in `src/utils/` (DART API client, corp‑code conversion, formatting helpers).

コメント

「データと分析」の他のコンテンツ

TikTok MCP Server

HasData

Hosted TikTok MCP server for AI agents: read public profiles, account videos, comments and replies, or search videos and creators. Structured JSON for creator research and content analysis.

3

Contextflo

Vivek Sah

Contextflo is a governed context layer that lets your whole team ask questions of your real data through the AI they already use. Connect BigQuery, Snowflake, Postgres, Redshift, Databricks, ClickHouse, or upload a CSV,

AgentGrown

Brady Heinrich

AgentGrown gives your coding agent your site's own Google Search Console and GA4 data. Sign in with Google at agentgrown.com and connect your sites. We sync Search Console and GA4 every day, so your agent can query click

Batru

Batru

Real, calibrated win-rate predictions, pick recommendations, counters, synergy and tier lists for Dota 2, Deadlock and Marvel Rivals, from production models trained on ~20M matches. Free hosted endpoint (Streamable HTTP)

Context.dev

Yahia Bakour

Context.dev is the web-data infrastructure for AI products and agents, one API that turns the web into clean, structured, LLM-ready data. MCP available at https://mcp.context.dev.

広告掲載