{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_mfe7hfcaxq33","handle":"dataroma-mcp","url":"https://wellknown.network/agents/dataroma-mcp","links":{"self":"https://wellknown.network/agents/dataroma-mcp/record.json","html":"https://wellknown.network/agents/dataroma-mcp","markdown":"https://wellknown.network/agents/dataroma-mcp/record.md","api":"https://wellknown.network/api/v1/agents/dataroma-mcp","status":"https://wellknown.network/api/v1/agents/dataroma-mcp/status","claim":"https://wellknown.network/agents/dataroma-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/dataroma-mcp/claim.json","badge":"https://wellknown.network/agents/dataroma-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/dataroma-mcp/history","tools":"https://wellknown.network/api/v1/agents/dataroma-mcp/tools"},"ard":{"identifier":"urn:air::server:dataroma-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"dataroma-mcp","summary":"An MCP server for Dataroma to access superinvestor holdings and trades","description":"# Universal Dataroma MCP Server \n \nA 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**. \n \n## Features \n- **One-Shot Homepage Scraper**: Extracts all 10+ market lists and the manager directory in a single request for maximum efficiency. \n- **Aggressive 24h Caching**: Uses an in-memory cache with disk persistence (dataroma_cache.json) to provide instant responses and avoid rate limits. \n- **Enriched Portfolio Data**: 13F holdings automatically include recent insider transaction (Form 4) summaries. \n- **Full Market Intelligence**: Direct access to Big Bets, 52-Week Lows, Most Owned Stocks, and Real-time Activity. \n \n## Available Tools \n- get_investor_holdings(manager_id): Get full 13F holdings for a specific manager (e.g., 'BRK' for Buffett). \n- get_realtime_insider_trades(symbol): Get the 10 most recent insider transactions for a stock ticker. \n- get_market_intelligence(list_type): Access Latest Insider Buys, Most Owned, Big Bets, Q1/Q2 Buying Trends, High Conviction Lows, and Insider Concentration. \n- list_superinvestors(): Full directory of all 80+ tracked superinvestors and their IDs. \n- invalidate_cache(key): Manually clear specific keys or the entire cache to force a fresh scrape. \n \n## Installation \nThe 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. \n \n```bash \nuvx dataroma-mcp \n``` \n \n## Configuration \n \n### Claude Desktop \nAdd this to your `claude_desktop_config.json`: \n```json \n{ \n  \"mcpServers\": { \n    \"dataroma-mcp\": { \n      \"command\": \"uvx\", \n      \"args\": [\"dataroma-mcp\"] \n    } \n  } \n} \n``` \n \n### Cursor / Windsurf / Cline \n1. Open your AI settings/MCP configuration. \n2. Add a new MCP serv…","publisher":null,"homepage":"https://github.com/kmukul123/dataroma-mcp","repository":"https://github.com/kmukul123/dataroma-mcp","version":"0.1.16","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:dataroma-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.825,"provenance":"derived"},{"slug":"finance.markets","name":"Markets & Trading","confidence":0.814,"provenance":"derived"}],"categories":["dev","finance"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"dataroma-mcp","registry":"pypi","observedAt":"2026-11-09T03:24:21.918Z","publishedAt":"2026-09-09T08:39:27.498543Z","latestVersion":"0.1.16"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"dataroma-mcp","url":"https://pypi.org/project/dataroma-mcp/","firstSeenAt":"2026-09-09T13:21:35.307Z","fetchedAt":"2026-11-09T03:22:49.649Z","normalizedAt":"2026-11-09T03:22:49.649Z"}]},"firstSeenAt":"2026-09-09T13:21:35.307Z","updatedAt":"2026-11-09T03:24:21.918Z"}