MCP Server: QRep Portfolio Profiling

What It Does

A comprehensive portfolio analysis platform that combines FastAPI endpoints, Model Context Protocol (MCP) integration, and a streamlined web interface:

Fast portfolio performance analysis using QuantStats-Lumi (Lumiwealth fork of QuantStats with bug fixes)
Generates professional HTML reports with visualizations
Calculates key performance metrics:
- Sharpe and Sortino ratios
- Maximum Drawdown and Value at Risk
- Rolling statistics and correlations
- Return distribution analysis
Compares performance against benchmark

How to Use

Endpoints

Base URL: https://quantstats-h.tigzig.com/ MCP Endpoint: https://quantstats-h.tigzig.com/mcp API Endpoint: https://quantstats-h.tigzig.com/analyze

Feel free to try out these endpoints, subject to rate limits and server load.

Access Methods

Web Interface: visit / for the Flask frontend
Direct API: make HTTP GET requests to /analyze with required parameters:
- symbols - Yahoo Finance symbol to analyze (stock, ETF, metals, crypto - e.g. AAPL, BTC-USD, GLD, XAGUSD)
- benchmark - benchmark symbol (default: ^GSPC)
- start_date - analysis start date (YYYY-MM-DD)
- end_date - analysis end date (YYYY-MM-DD)
- risk_free_rate - optional risk-free rate percentage (default: 5.0)
MCP/LLM: connect to /mcp using any MCP-compatible client

How It Works

Data Collection

Historical price data fetched from Yahoo Finance API
Downloads both stock and benchmark data
Processes and aligns stock returns for consistent analysis

Portfolio Analysis

Creates comprehensive visual reports with quantstats-lumi

Integration Layer

FastAPI backend with efficient data processing
HTML report generation using quantstats-lumi
Enhanced with MCP for AI/LLM interactions

Endpoints

Three endpoint types:
- / - Flask-based web interface for interactive analysis
- /api/* - FastAPI endpoints for direct programmatic access
- /mcp - Model Context Protocol endpoint for AI/LLM integration
Enhanced with MCP capabilities using fastapi-mcp

How to Replicate

Clone the repository
Install dependencies: pip install -r requirements.txt

Configure environment variables:

IS_LOCAL_DEVELOPMENT=1  # Set to 0 for production
BASE_URL_FOR_REPORTS=https://your-domain.com/

Run the server: uvicorn main:app --host 0.0.0.0 --port 8000

Key Dependencies

MCP Server: Yahoo Finance (companion service)
FastAPI Server: ReportLab

Resources

MCP Server: QRep (Lumi)

Consolidated source code for FastAPI, MCP Server and Flask UI

MCP Server: Yahoo Finance

Companion Yahoo Finance data-pull MCP server

FastAPI Server: ReportLab

Markdown-to-PDF report generation server

API Docs: QRep Server

Interactive Swagger UI for the QRep FastAPI server

API Docs: Yahoo Finance

Interactive Swagger UI for the Yahoo Finance server

QuantStats-Lumi Package

Lumiwealth's fork of QuantStats with important bug fixes and improvements

FastAPI-MCP

Tadata's package to convert any FastAPI into an MCP server

Fine Print: This is for informational purposes only and should not be considered as investment advice. All metrics in this report are generated using the open-source QuantStats-Lumiwealth Version. While widely used for performance and risk analytics, some calculations may rely on assumptions (e.g., trading days, compounding methods) or be subject to version-specific behavior. Key metrics such as total return and CAGR have been manually reviewed for consistency, but users are encouraged to refer to the official documentation for full methodology. Results should be interpreted in light of the intended use case. Always validate outputs.