Awesome MCPFinance & Trading

xbtlin/ai-berkshire

⭐ 16323 Python added to this list on 2026-07-06 repository created 2026-04-07

AI Berkshire is an advanced investment research framework designed to revolutionize the way value investing is approached in the era of artificial intelligence. It integrates the robust capabilities of large language models such as Claude Code and Codex to mimic and apply the investment philosophies of renowned value investors, including Warren Buffett, Charlie Munger, Duan Yongping, and Li Lu. The system orchestrates multiple AI agents that conduct parallel research, enabling a comprehensive and multi-faceted analysis of investment opportunities. Unlike traditional AI interactions that might yield generic 'on the one hand, on the other hand' analyses, AI Berkshire is engineered to provide actionable conclusions, including explicit 'pass/fail/gray area' recommendations with specific price ranges. A core innovation is its adversarial analysis mechanism, wherein different AI agents, each embodying a master investor's perspective, confront and challenge each other's findings. This process generates realistic conflicts and deeper insights, mitigating confirmation bias and providing a more robust decision-making basis. The framework is also built with strong anti-scam mechanisms, including rigorous data validation, Monte Carlo simulations for failure scenarios, and a 'quick veto' checklist for immediate rejection based on critical red flags. It further emphasizes financial data accuracy by using precise decimal calculations and cross-validation from independent sources, ensuring reliability. The entire research workflow is designed for reproducibility, guaranteeing consistent output structure and depth for comparative analysis over time or across different companies, making it an invaluable tool for professional investment research.

https://github.com/xbtlin/ai-berkshire

aiai-agentanthropicberkshire-hathawaycharlie-mungerclaudeclaude-codefinancial-analysisfintechfundamental-analysisinvestmentinvestment-researchllmmcpportfolio-managementstock-analysisstock-marketvalue-investingwarren-buffettmulti-agentadversarial-analysis

Also in Finance & Trading

HKUDS/Vibe-Trading

Vibe-Trading is an AI-powered personal trading agent designed to assist with algorithmic trading, backtesting, and quantitative finance, leveraging large language models and multi-agent systems.

financial-datasets/mcp-server

An MCP server that enables AI assistants to access comprehensive stock market and cryptocurrency data from Financial Datasets via the Model Context Protocol interface.

stripe/agent-toolkit

The Stripe Agent Toolkit is a library that integrates Stripe's API into various agent frameworks and the Model Context Protocol (MCP) to enable seamless payment and billing automation in intelligent agent workflows.

sendaifun/solana-agent-kit

Solana Agent Kit is an open-source toolkit that enables AI agents to autonomously perform a wide range of actions on Solana blockchain protocols, integrating AI models with decentralized finance, NFTs, and cross-chain operations.

whchien/ai-trader

AI-Trader is a professional backtesting framework for algorithmic trading with multi-market support and integrated Model Context Protocol (MCP) server enabling AI assistant interaction.

goat-sdk/goat

GOAT is a comprehensive agentic finance toolkit enabling AI agents to autonomously perform financial activities using blockchain, cryptocurrencies, wallets, and supports the Model Context Protocol (MCP) along with other agent frameworks.

alpacahq/alpaca-mcp-server

Alpaca MCP Server is an MCP server implementation that enables large language models to interact with Alpaca's trading API using natural language for stock, options, and crypto trading, portfolio management, and real-time market data access.

ariadng/metatrader-mcp-server

MetaTrader MCP Server seamlessly connects AI assistants like Claude and ChatGPT to the MetaTrader 5 trading platform, enabling natural language trading and automated financial operations.