About Stocksense
Stocksense is an MCP server for AI agents researching public companies through SEC filings and financial data. It combines filings, fundamentals, insider trades, and price history without requiring API keys.
Key features
- 01SEC filing search and full text
- 02Quotes and historical prices
- 03Financial statements and key ratios
- 04Insider trades and earnings history
- 05Company research and comparisons
- 06Dividends, events, and technical indicators
Use cases
- 01Review a company’s SEC filings
- 02Compare financial metrics across tickers
- 03Track insider trades and dividend history
- 04Prepare a research brief from market data
MCP support
Exposes financial-data tools to MCP clients, including filing search, company analysis, quotes, and price history. Integrates with Claude Desktop through its MCP server configuration.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEStockSense
An MCP (Model Context Protocol) server that gives AI agents access to financial data — SEC EDGAR filings, market fundamentals, insider trades, and price history. No API keys needed.
Quick Start
1. Install
pip install stocksense
2. Add to Claude Desktop
Add to your Claude Desktop config:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"stocksense": {
"command": "stocksense"
}
}
}
3. Restart Claude Desktop
Quit and reopen Claude Desktop. You should see the hammer icon with 13 tools available.
Available Tools
| Tool | Description |
|---|---|
price_history | Get historical OHLCV price data for any ticker |
quote | Get current price, market cap, P/E, 52-week range |
search_filings | Search SEC EDGAR filings (10-K, 10-Q, 8-K) |
get_filing | Get full text of a specific SEC filing |
insider_trades | Get recent insider buys/sells from Form 4 filings |
financials | Get income statement, balance sheet, cash flow, and key ratios |
analyze_company | Comprehensive research brief aggregating all data sources |
compare_companies | Compare key metrics across multiple companies side-by-side |
earnings | Quarterly earnings history with EPS estimates vs actuals |
company_profile | Company profile: sector, industry, and business description |
dividends | Dividend history and current yield |
key_events | Upcoming earnings dates, ex-dividend date, and estimates |
technicals | Technical indicators: SMA, EMA, RSI, MACD, and performance |
Example queries
- "What's AAPL's price history for the last month?"
- "Get me a quote for MSFT"
- "Show me TSLA's weekly prices over the past year"
- "Show me Apple's recent 10-K filings"
- "What insider trades happened at Tesla recently?"
- "Show me Apple's financial statements"
- "Give me a research brief on Tesla"
- "Compare AAPL, MSFT, and GOOGL"
- "Show me Apple's earnings history"
- "What sector is NVIDIA in?"
- "Show me AAPL's dividend history"
- "When is Microsoft's next earnings date?"
- "What are Tesla's technical indicators?"
Data Sources
- yfinance — price data, quotes, financial statements, analyst consensus
- SEC EDGAR — free, unlimited filings and insider trades (no API key needed)
Requirements
- Python 3.11+
- No API keys needed — uses free public data sources
Development
# Clone and install for development
git clone https://github.com/mikejj-creation/stocksense.git
cd stocksense
pip install -e ".[dev]"
# Run tests
pytest
# Run linter
ruff check src/ tests/
Disclaimer
StockSense uses free public data from Yahoo Finance and SEC EDGAR. Users are responsible for complying with each provider's terms of service. This tool is for informational purposes only — not financial advice.
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.