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.
Awesome MCP › Finance & Trading
stefanoamorelli/sec-edgar-mcp
sec-edgar-mcp is a Model Context Protocol server that connects AI assistants to the United States SEC EDGAR filing system. It is built on the edgartools library and focuses on returning exact numeric values rather than approximations, and every response includes the underlying SEC filing URL so answers can be verified against the source document. The tool surface is grouped into four areas. Company tools resolve a CIK, return company information and return company facts. Filing tools retrieve 10-K, 10-Q and 8-K documents and extract individual sections from them. Financial tools return balance sheets, income statements and cash flow statements parsed from XBRL data. Insider trading tools return Form 3, 4 and 5 transactions. The quickest way to run it is the published Docker image, invoked from an MCP client configuration with docker run -i and a SEC_EDGAR_USER_AGENT environment variable carrying a name and email address as the SEC requires; the -i flag is needed for JSON-RPC over stdio. Installation is also available from PyPI, conda and uv, and the project documentation covers those paths. Besides stdio, the server can run over streamable HTTP for platforms such as Dify, started with a --transport streamable-http flag and a port; the README warns that this mode ships no authentication and should only be used on private networks. Quality is tracked with a Promptfoo-based evaluation suite under the evals directory, run through npm, and wired into a GitHub Actions workflow. The project requires Python 3.11 or newer, is archived on Zenodo with a DOI and a citation file for research use, and is licensed under AGPL-3.0 with commercial licensing offered separately. It is not affiliated with the SEC.
https://github.com/stefanoamorelli/sec-edgar-mcp
Also in Finance & Trading
xbtlin/ai-berkshire
AI Berkshire is an investment research framework leveraging AI agents powered by Claude Code and Codex to apply the methodologies of legendary value investors like Buffett and Munger, aiming to red...
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.