data-mcp/
├── findata/                         Data library
│   ├── equity_prices.py             get_equity_prices()           yfinance wrapper
│   ├── sp500_composition.py         get_sp500_composition()       fja05680/sp500 (local git clone)
│   ├── fama_french.py               get_fama_french_factors()     Ken French Data Library
│   ├── fred.py                      get_fred_series()             FRED macroeconomic series
│   ├── cboe_volatility.py           get_cboe_volatility_indices() VIX / VVIX
│   ├── coingecko.py                 get_coingecko_ohlcv()         CoinGecko public API
│   ├── file_reader.py               get_file_data()               CSV / Parquet / Excel
│   └── bloomberg.py                 get_bloomberg_data()          blpapi (stub)
├── findata_mcp/
│   └── server.py                    Tool registry + MCP handlers
├── Dockerfile
├── docker-compose.yml
├── .github/workflows/docker.yml     GHCR build + push on every push to main
├── pyproject.toml
└── README.md

codex auth login    # opens browser → saves to ~/.codex/auth.json

curl -O https://raw.githubusercontent.com/lakshya-aga/data-mcp/main/docker-compose.yml
docker compose up -d

docker logs data-mcp-findata-mcp-1
# should show: findata-mcp starting on :8000

{
  "mcpServers": {
    "findata": {
      "url": "http://localhost:8000/sse"
    }
  }
}

import asyncio
from mcp.client.sse import sse_client
from mcp.client.session import ClientSession

async def main():
    async with sse_client("http://localhost:8000/sse") as (r, w):
        async with ClientSession(r, w) as s:
            await s.initialize()
            res = await s.call_tool("search_tools", {"query": "equity daily prices", "top_k": 3})
            print(res.content[0].text)

asyncio.run(main())

from agents.mcp import MCPServerSse
mcp = MCPServerSse(url="http://localhost:8000/sse")

res = await s.call_tool("search_tools", {"query": "fama french factors", "top_k": 2})

res = await s.call_tool("get_tool_doc", {"tool_name": "get_equity_prices"})

res = await s.call_tool("request_data_source", {
    "description": "get World Bank GDP per capita using the wbdata library"
})

from findata.equity_prices import get_equity_prices

df = get_equity_prices(
    tickers=["AAPL", "MSFT"],
    start_date="2024-01-01",
    end_date="2024-12-31",
    fields=["Close"],
    frequency="1d",         # 1d 5d 1wk 1mo 3mo
)

from findata.fama_french import get_fama_french_factors

df = get_fama_french_factors(factor_model="5", start_date="2010-01-01", end_date="2020-12-31")
# columns: Mkt-RF, SMB, HML, RMW, CMA, RF

from findata.fred import get_fred_series

df = get_fred_series(["CPIAUCSL", "UNRATE"], start_date="2015-01-01", end_date="2024-12-31")

from findata.coingecko import get_coingecko_ohlcv

df = get_coingecko_ohlcv("bitcoin", vs_currency="usd", days=90)
# columns: open, high, low, close, volume

from findata.cboe_volatility import get_cboe_volatility_indices

df = get_cboe_volatility_indices(symbols=["^VIX", "^VVIX"], start_date="2020-01-01", end_date="2024-12-31")

from findata.sp500_composition import get_sp500_composition

members = get_sp500_composition("2024-12-31")   # list[str], ~503 tickers

from findata.file_reader import get_file_data

df = get_file_data("data/prices.parquet", tickers=["AAPL"], start_date="2023-01-01", end_date="2023-12-31")

pytest tests/ -v