MCP Stock Details Server

You have an MCP Stock Details Server that provides a focused, extensible MCP interface for Korean stock market data and analysis. It integrates data collection, caching, and a layered set of analytical tools to help you fetch company information, financials, valuation metrics, ESG and technical indicators, shareholder context, and market comparisons from a configurable MCP server you run locally or in your environment.

How to use

Install and run the MCP Stock Details Server, then connect your MCP client to perform stock analysis tasks. You can request company overviews, pull financial statements, compute ratios and valuations, analyze ESG and technical indicators, review shareholder structures, compare peers, and fetch analyst consensus data. Use the client to call the available tools by name and pass the required parameters like company code and analysis options. The server handles data retrieval, caching, and structured responses to support your workflows.

How to install

Prerequisites: Python 3.8 or higher. Redis is optional but recommended for enhanced caching.

# Clone the repository
git clone https://github.com/yourusername/mcp-stock-details.git
cd mcp-stock-details

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Set up environment variables
cp .env.example .env
# Edit .env with your DART API key and other settings

Configuration and startup notes

Set the DART API key and optional environment values to control caching and logging behavior. The server is started with the Python runtime, and you can supply a development configuration if needed.

# Required environment variable
DART_API_KEY=your_dart_api_key_here

# Optional
REDIS_URL=redis://localhost:6379/0
LOG_LEVEL=INFO
CACHE_TTL=3600

Running the server and basic usage

Start the MCP server using the Python module entry point. You can run with default settings or specify a development configuration file.

# Start the MCP server
python -m src.server

# Or run with a specific configuration file
python -m src.server --config config/development.json

Connecting from Claude Desktop (example client setup)

Add the MCP stock_details server to your Claude Desktop configuration so you can call tools directly from the client.

{
  "mcpServers": {
    "stock-details": {
      "command": "python",
      "args": ["-m", "src.server"],
      "cwd": "/path/to/mcp-stock-details",
      "env": {
        "DART_API_KEY": "your_api_key"
      }
    }
  }
}

Example usage via client calls

From your MCP client, call the available tools by name and provide the required parameters, such as the company code and analysis options.

Available tools

get_company_overview

Fetches comprehensive information about a company, including key identifiers, sector, and overview details.

get_financial_statements

Retrieves income statement, balance sheet, and cash flow data for the specified company.

get_financial_ratios

Returns 50+ financial ratios with optional industry benchmarks.

get_valuation_metrics

Provides valuation outputs such as DCF, multiples, and related measures.

get_esg_info

Returns Environmental, Social, Governance metrics and summaries.

get_technical_indicators

Provides technical analysis indicators like RSI, MACD, Bollinger Bands, and moving averages.

get_shareholder_info

Presents shareholder structure and governance related metrics.

get_business_segments

Analyzes performance by business segment.

get_peer_comparison

Benchmarks against industry peers and benchmarking metrics.

get_analyst_consensus

Gathers analyst consensus, target prices, and investment opinions.