An MCP server for Dataroma to access superinvestor holdings and trades
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"dataroma-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# 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 The recommended way to run this server is using `uvx` (which acts like `npx` for Python). This allows you to run it directly from PyPI without manually installing dependencies or cloning the repository. ```bash uvx dataroma-mcp ``` ## Configuration ### Claude Desktop Add this to your `claude_desktop_config.json`: ```json { "mcpServers": { "dataroma-mcp": { "command": "uvx", "args": ["dataroma-mcp"] } } } ``` ### Cursor / Windsurf / Cline 1. Open your AI settings/MCP configuration. 2. Add a new MCP serv…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.