Pykrx

Provides up-to-date Korean stock market data via an MCP server built on pykrx, enabling natural-language queries for stock, index, ETF, and investor data.

python

0

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "sharebook-kr-pykrx-mcp": {
      "command": "uvx",
      "args": [
        "pykrx-mcp"
      ]
    }
  }
}

You can access a wide range of Korean stock market data through an MCP server built around the pykrx library. This server exposes information on market data, prices, fundamental metrics, investor activity, and short selling in natural language, enabling you to query ChatGPT, Claude, or other AI agents with ease.

How to use

To use the pykrx MCP server, connect your MCP client to the provided server endpoint and start asking questions in everyday language. You can request single-item lookups, market-wide summaries, or investory-specific analyses, and the AI agent will fetch the corresponding data from the server and present it in a concise, human-friendly form.

How to install

Prerequisites you need before installation:

Node.js is required for MCP tooling and runtime
npm or npx helps install and run MCP modules

Step-by-step installation and setup you can follow exactly as shown here:

# 1) Quick install via MCP Registry (recommended)
npx @modelcontextprotocol/inspector install pykrx-mcp

# 2) Manual installation - configure Claude Desktop to use this MCP server
# Claude Desktop settings file (example for macOS/Linux)
~/Library/Application Support/Claude/claude_desktop_config.json

# Claude Desktop settings file (example for Windows)
%APPDATA%\Claude\claude_desktop_config.json

Additional configuration and startup

The following configuration snippet shows how to declare the MCP server for local runtime. This config is used by Claude Desktop to connect to the pykrx MCP server.

{
  "mcpServers": {
    "pykrx": {
      "command": "uvx",
      "args": ["pykrx-mcp"]
    }
  }
}

Available tools

get_market_ticker_list

Returns the list of stock tickers by market (e.g., KOSPI, KOSDAQ, KOSDEX) with their codes.

get_market_ticker_name

Resolves a stock ticker code to its corresponding company name.

get_stock_ohlcv

Fetches OHLCV data for a specific stock, including open, high, low, close, and volume.

get_market_ohlcv_by_date

Gets the OHLCV data for all stocks on a specified date.

get_market_price_change

Provides price changes over a defined period for all stocks.

get_market_cap_by_date

Returns market capitalization for a given stock on a specific date.

get_market_fundamental_by_date

Retrieves fundamental indicators like PER, PBR, EPS, DIV, BPS, and DPS for a date.

get_market_trading_value_by_date

Shows trading value by date for investor activity per stock.

get_market_trading_volume_by_investor

Provides trading volume broken down by investor type.

get_market_trading_value_by_investor

Shows trading value by investor type for each stock.

get_market_net_purchases_of_equities

Lists top securities by net purchases from different investor groups.

get_index_ticker_list

Lists index tickers available in the market.

get_index_ticker_name

Resolves an index ticker to its index name.

get_index_ohlcv

Fetches OHLCV data for indices.

get_shorting_status_by_date

Short selling status per stock on a given date.

get_shorting_volume_by_ticker

Short selling volume across all stocks.

get_shorting_balance_top50

Top 50 stocks by shorting balance.

get_shorting_volume_top50

Top 50 stocks by shorting volume.

get_exhaustion_rates_of_foreign_investment

Foreign ownership exhaustion rates and limits.

get_etf_ticker_list

Lists ETF tickers available in the market.

get_etf_ohlcv_by_date

Fetches OHLCV data for ETFs on a specific date.