Skip to main content
Glama
ambideXtrous9

StockMcp

🧠 Stock Analysis using MCP Local LLM (Ollama Qwen3) with LangChain

This project demonstrates how to build a fully local AI assistant that provides detailed stock analysis using:

  • MCP (Model Context Protocol): Enables structured tool usage by the language model.

  • Ollama: A tool for running large language models locally.(Qwen3)

  • LangChain: A framework for developing applications powered by language models and run as MCP Client

  • BeautifulSoup: For web scraping financial data from Screener.in.

šŸ“¦ Features

šŸ” Company Details: Retrieve company name, current price, market cap, PE ratio, ROE, ROCE, and more.

šŸ“ˆ Profit Analysis: Extract quarterly and yearly net profit data.

šŸ‘„ Shareholding Patterns: Analyze holdings by promoters, DIIs, FIIs, and the public.

šŸ”§ Tool Integration: Seamless integration with MCP tools for enhanced functionality.

Related MCP server: sfinance-mcp-server

āš™ļø Configuration

MCP Server Setup

The MCP server is defined in mcp_config.json.

{
  "mcpServers": {
    "stock": {
      "command": "python",
      "args": ["StockMcp.py"],
      "transport": "stdio"
    }
  }
}


Give me the company details of CREDITACC.NS

šŸ› ļø Project Structure

ā”œā”€ā”€ StockMcp.py         # MCP server with tool definitions
ā”œā”€ā”€ requirements.txt    # Python dependencies
ā”œā”€ā”€ README.md           # Project documentation

šŸ“š Resources

MCP Github

Ollama Documentation

LangChain MCP Documentation

BeautifulSoup Documentation

Related MCP Connectors

Related MCP Servers

  • F
    license
    B
    quality
    Not graded
    maintenance
    Enables LLMs to retrieve, analyze, and visualize stock prices and financial report data for quantitative trading research and investment analysis. Provides real-time and historical stock data, financial statement analysis, key metric calculations, and trading signal visualization.
    13
    -
  • A
    license
    A
    quality
    D
    maintenance
    Provides financial data for Indian listed companies from screener.in, enabling users to search companies and fetch financial statements, ratios, and peer comparisons.
    2
    28 npm
    1
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Enables RAG-based querying of local stock company data using a local LLM and vector database, providing tools to ask questions, search raw chunks, and list documents.
    -