Indian Stock Analysis MCP Server

What is Indian Stock Analysis MCP Server?

A Model Context Protocol (MCP) server that integrates with MongoDB, the Alpha Vantage API, and a knowledge graph to provide portfolio recommendations and market insights exclusively for the Indian stock market (NSE/BSE). It enables Claude to access your Indian stock portfolio holdings, analyze performance, and give personalised recommendations directly from the Claude Desktop app.

How to use Indian Stock Analysis MCP Server?

Install prerequisites (Python 3.9+, MongoDB on localhost:27017, Alpha Vantage free API key, Claude Desktop), clone the repository, install dependencies, configure the .env file, then run python server.py. Configure Claude Desktop by editing claude_desktop_config.json (located in ~/Library/Application Support/Claude/ on macOS or %APPDATA%\Claude\ on Windows) to point to the server script. After restarting Claude, start a new conversation and ask about your portfolio.

Key features of Indian Stock Analysis MCP Server

• Exclusive Indian market focus (NSE and BSE listed stocks)
• Direct MongoDB access without an API layer
• Knowledge graph integration for persistent analysis data
• Automatic rate handling for Alpha Vantage free tier
• Modular architecture with environment configuration
• Segmented portfolio analysis to prevent timeouts

Use cases of Indian Stock Analysis MCP Server

• Get a summary of your Indian stock portfolio holdings
• Analyze portfolio segments one at a time for large portfolios
• Request market trends and stock recommendations for NSE/BSE
• Ask about specific stocks like Reliance or TCS
• Identify which sectors are most represented in your portfolio

FAQ from Indian Stock Analysis MCP Server

What are the prerequisites to run this server?

Python 3.9+, a running MongoDB instance on localhost:27017 with a stock_data database, an Alpha Vantage API key (free tier), and the Claude Desktop app.

Where does my stock data live?

All stock data is stored locally in your MongoDB instance on stock_data database. The server queries this database directly; no external cloud storage is used.

What are the Alpha Vantage API limits?

The free tier allows 5 requests per minute and 500 requests per day. The server automatically respects these limits and queues requests accordingly.

How do I handle large portfolios (20+ stocks)?

Use the segmented approach: first run get_portfolio_summary to see an overview, then analyze segments one at a time with portfolio_analysis using the segment parameter. Default segment size is 5 stocks, adjustable via segment_size.

Why aren't the MCP tools appearing in Claude Desktop?

Check that the server key in claude_desktop_config.json uses hyphens, the MCP_SERVER_NAME environment variable matches, paths are absolute, and you start a new conversation after making changes. Also enable developer mode in Claude's settings.