mcpField
K
koreastockcheck

koreastockcheck

Remote
koreastockcheck.comFinance0Updated 10w ago
RepositoryVisit website

About koreastockcheck

koreastockcheck is an MCP service for researching Korean listed companies through English-language access to DART regulatory filings. It provides ten years of filing history with links to original government documents, and does not offer investment advice.

Key features

  1. 01Search filings for Korean listed companies
  2. 02Review offerings and dilution events
  3. 03Check audits and exchange sanctions
  4. 04Track suspensions and delisting records
  5. 05Link claims to original filings

Use cases

  1. 01Review a company's financing and dilution history
  2. 02Trace filings before a trading suspension
  3. 03Check audit opinions and exchange sanctions

MCP support

This remote MCP service connects through Streamable HTTP to clients supporting remote servers with URL-embedded authentication. It exposes company filing history sourced from Korea's official DART system.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.koreastockcheck.com/mcp/{api_key}
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

KoreaStockCheck MCP Server

Background checks for Korean stocks — inside your AI assistant.

KoreaStockCheck is a remote MCP (Model Context Protocol) server that lets Claude and other MCP-capable AI assistants look up the public regulatory filing history of any company listed on the Korea Exchange (KOSPI / KOSDAQ) — in English.

Ask your assistant "What has Samsung Electronics actually filed?" or "Show me this KOSDAQ company's dilution history" and it answers from ten years of official filings, with every claim linked to the original government document.

What the data is

All data comes from DART (dart.fss.or.kr), the Korean government's official corporate disclosure system — the Korean equivalent of the SEC's EDGAR. The server covers all ~3,400 listed companies with ten years of filing history, updated every Korean business day:

  • Rights offerings, convertible bonds, bonds with warrants (dilution history)
  • Capital reductions and treasury-share actions
  • Audit opinions and auditor changes
  • Exchange sanctions, trading suspensions, delisting records
  • Embezzlement / breach-of-trust disclosures

What it is not: no buy/sell recommendations, no price targets, no forecasts, no investment advice. Facts from filings only — every response links to the source document. The risk scoring methodology is validated against official KRX delisting outcomes and published openly.

Connect to Claude

  1. Get your personal access key at koreastockcheck.com ($9/month, cancel anytime — key arrives by email).
  2. In Claude: Settings → Connectors → Add custom connector, and paste your personal server URL:
https://mcp.koreastockcheck.com/mcp/<your-key>
  1. Ask about any Korean stock by name or 6-digit ticker. Example prompts:
List 삼성전자 (005930)'s capital raises from the last five years.
Summarize the filing history of Celltrion.
Which filings preceded this company's trading suspension?

The server speaks streamable-HTTP MCP and works with any MCP client that supports remote servers with URL-embedded auth.

Fair use

Personal subscriptions include 300 checks per month (up to 30/day) across web reports and AI calls. Bulk extraction, redistribution, and building competing datasets are not permitted — see Terms. Need the dataset or a team license? [email protected]

Links

Facts from public DART filings. Not investment advice. © KoreaStockCheck

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.