Skip to main content

Financial Market Intelligence MCP Server — stock quotes, technical analysis, crypto data, and portfolio insights for AI agents

Project description

PyPI version License: MIT Python 3.11+ Glama MCP Server

FinanceKit MCP

Financial Market Intelligence for AI Agents — real-time stock quotes, technical analysis, crypto data, and portfolio insights via the Model Context Protocol (MCP).

FinanceKit is an MCP server that gives Claude Code, Cursor, Windsurf, and any AI agent instant access to financial market data. No API keys required for stocks and crypto.

Use Cases

Here are concrete examples of what you can ask your AI agent once FinanceKit is installed:

  • "Run full technical analysis on TSLA and tell me if it's a buy" — Get RSI, MACD, Bollinger Bands, ADX, Stochastic, and pattern detection with a plain-English signal summary
  • "Compare AAPL vs MSFT vs GOOGL performance over the last 6 months" — Side-by-side returns, volatility, Sharpe ratio, and max drawdown
  • "Analyze my portfolio: AAPL:50, NVDA:20, MSFT:30, AMZN:10" — Total value, sector allocation, concentration risk, and diversification score
  • "What are the trending cryptocurrencies right now? Any worth watching?" — Top trending coins from CoinGecko with price data and momentum
  • "Give me a market overview — how are the major indices doing?" — S&P 500, NASDAQ, Dow, VIX, and market sentiment in one call
  • "Is Bitcoin overbought? Show me RSI and Bollinger Band analysis" — Full technical analysis works on crypto too, not just stocks

Why FinanceKit?

Feature FinanceKit MCP Yahoo Finance API Alpha Vantage TradingView
Works with Claude Code / Cursor Yes No No No
No API key needed Yes Yes No (free tier) No
Technical analysis built-in 10+ indicators Raw data only Limited Manual
Crypto + stocks in one tool Yes Stocks only Separate APIs Manual
Portfolio analysis Yes No No No
MCP native (stdio + HTTP) Yes REST only REST only Web only
Free Yes Yes Rate limited Paid

Tools (12)

Stocks

Tool Description
stock_quote Current price, change, volume, P/E, market cap
company_info Sector, financials, valuation metrics, description
multi_quote Batch quotes for up to 10 tickers at once

Crypto

Tool Description
crypto_price Price, market cap, 1h/24h/7d changes, ATH data
crypto_trending Top 10 trending coins on CoinGecko
crypto_search Find coins by name or symbol
crypto_top_coins Top N coins ranked by market cap

Technical Analysis

Tool Description
technical_analysis Full analysis: RSI, MACD, Bollinger Bands, SMA/EMA, ADX, Stochastic, ATR, OBV + pattern detection (Golden Cross, Death Cross, overbought/oversold) with plain-English signal summary
price_history Historical OHLCV data with summary statistics

Market Overview

Tool Description
market_overview Major indices (S&P 500, NASDAQ, Dow), VIX, market sentiment

Portfolio & Comparison

Tool Description
compare_assets Side-by-side returns, volatility, Sharpe ratio, drawdown
portfolio_analysis Total value, allocation weights, sector breakdown, concentration risk

Installation

Claude Code (recommended)

claude mcp add financekit -- uvx --from financekit-mcp financekit

Claude Desktop / Cursor / Windsurf

Add to your MCP configuration (claude_desktop_config.json, .cursor/mcp.json, etc.):

{
  "mcpServers": {
    "financekit": {
      "command": "uvx",
      "args": ["--from", "financekit-mcp", "financekit"]
    }
  }
}

Install via Smithery

npx -y @smithery/cli install @vdalhambra/financekit --client claude

Install via MCPize (hosted, no local install)

{
  "mcpServers": {
    "financekit": {
      "url": "https://financekit-mcp.mcpize.run/mcp"
    }
  }
}

From PyPI

pip install financekit-mcp
financekit

From source

git clone https://github.com/vdalhambra/financekit-mcp.git
cd financekit-mcp
uv sync
uv run financekit

Data Sources

  • Stocks: Yahoo Finance (via yfinance) — free, no API key
  • Crypto: CoinGecko API (free tier, 10K calls/month)
  • Technical Indicators: Calculated locally using the ta library (RSI, MACD, Bollinger Bands, ADX, Stochastic, ATR, OBV)

All data is cached to minimize API calls: quotes (60s), historical data (1h), crypto (2min), company info (24h).

Examples

Technical Analysis Output

Symbol: AAPL
Current Price: 260.48
Indicators:
  RSI(14): 55.65 — neutral
  MACD: histogram positive — bullish momentum
  Bollinger Bands: price within bands — normal
  SMA(50): 260.84
  ADX: 18.3 — weak/no trend
Patterns:
  Golden Cross: false
  Overbought: false

Portfolio Analysis Output

Total Value: $45,230.50
Positions: 3
Concentration Risk: MODERATE
Sector Breakdown:
  Technology: 85.2%
  Communication Services: 14.8%

Compatible AI Agents

FinanceKit works with any AI agent or IDE that supports the Model Context Protocol:

  • Claude Code (CLI) — claude mcp add
  • Claude Desktopclaude_desktop_config.json
  • Cursor.cursor/mcp.json
  • Windsurf — MCP settings
  • Copilot — MCP configuration
  • Any MCP client — stdio or HTTP transport

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

financekit_mcp-1.1.0.tar.gz (113.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

financekit_mcp-1.1.0-py3-none-any.whl (21.3 kB view details)

Uploaded Python 3

File details

Details for the file financekit_mcp-1.1.0.tar.gz.

File metadata

  • Download URL: financekit_mcp-1.1.0.tar.gz
  • Upload date:
  • Size: 113.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for financekit_mcp-1.1.0.tar.gz
Algorithm Hash digest
SHA256 01e1c8ea1d2db4465f814e84c3a0b57de451dc7121fdcfbae0849c20440cee69
MD5 1d8c035448a6074adb96ec97204ebd1a
BLAKE2b-256 2efc72465da5333aeea77cd11dcbfa3ef3616d3e70933797800857c6a89cb65a

See more details on using hashes here.

File details

Details for the file financekit_mcp-1.1.0-py3-none-any.whl.

File metadata

  • Download URL: financekit_mcp-1.1.0-py3-none-any.whl
  • Upload date:
  • Size: 21.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for financekit_mcp-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 abe308b964e8b6e2ac35c267b1ae74d47f55f19b6cdb05965657ef62e8361343
MD5 db49ba80816cce3035cd806822f8e1e2
BLAKE2b-256 6d8ede5c5b0212d9d2f39626923ffbf1aafe54507c18f48903f5c51ca88a1b56

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page