Metadata-Version: 2.4
Name: dataroma-mcp
Version: 0.1.0
Summary: An MCP server for Dataroma to access superinvestor holdings and trades
Author-email: Your Name <your.email@example.com>
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: mcp
Requires-Dist: beautifulsoup4
Requires-Dist: requests

﻿# Universal Dataroma MCP Server

A high-performance Model Context Protocol (MCP) server for extracting superinvestor portfolios and financial intelligence from Dataroma.com. This server is compatible with any MCP-enabled AI client, including **Claude Desktop**, **Cursor**, **Cline**, and **ZeroClaw**.

## Features
- **One-Shot Homepage Scraper**: Extracts all 10+ market lists and the manager directory in a single request for maximum efficiency.
- **Aggressive 24h Caching**: Uses an in-memory cache with disk persistence (dataroma_cache.json) to provide instant responses and avoid rate limits.
- **Enriched Portfolio Data**: 13F holdings automatically include recent insider transaction (Form 4) summaries.
- **Full Market Intelligence**: Direct access to Big Bets, 52-Week Lows, Most Owned Stocks, and Real-time Activity.

## Available Tools
- get_investor_holdings(manager_id): Get full 13F holdings for a specific manager (e.g., 'BRK' for Buffett).
- get_realtime_insider_trades(symbol): Get the 10 most recent insider transactions for a stock ticker.
- get_market_intelligence(list_type): Access Latest Insider Buys, Most Owned, Big Bets, Q1/Q2 Buying Trends, High Conviction Lows, and Insider Concentration.
- list_superinvestors(): Full directory of all 80+ tracked superinvestors and their IDs.
- invalidate_cache(key): Manually clear specific keys or the entire cache to force a fresh scrape.

## Installation
Ensure you have Python 3.10+ installed, then install the dependencies:
`ash
pip install mcp beautifulsoup4 requests
`

## Configuration

### Claude Desktop
Add this to your claude_desktop_config.json:
`json
{
  "mcpServers": {
    "dataroma": {
      "command": "python",
      "args": ["D:\\SRC\\dataroma-mcp\\dataroma_mcp.py"]
    }
  }
}
`

### Cursor / Windsurf / Cline
1. Open your AI settings/MCP configuration.
2. Add a new MCP server.
3. Type: command
4. Configuration:
   - Command: python
   - Arguments: D:\SRC\dataroma-mcp\dataroma_mcp.py

### ZeroClaw
Add to your config.toml:
`	oml
[[mcp.servers]]
name = "Dataroma"
transport = "stdio"
command = "python.exe"
args = ["D:\\SRC\\dataroma-mcp\\dataroma_mcp.py"]
`

## Credits
Data sourced from [Dataroma.com](https://www.dataroma.com). This project is for educational and research purposes only.
