Discover the Best AI Tools

Python client and MCP server for retrieving Asian company financial reports or selected sections as Markdown from the DataSinking service; an API key is required and document quotas depend on the service plan.

Independent MCP server built on sec-edgar-toolkit for company filings, financial statements and insider transaction disclosures, returning filing links; it requires a configured SEC request identity and includes no HTTP authentication.

Self-hosted MCP server for stock analysis, screening and portfolio tracking using yfinance, with optional backtesting and model-assisted research extras; research requires separate model and search-service access.

Development-stage MCP adapter for the Interactive Brokers Web API, using Docker services for a Client Portal Gateway and MCP routing; it requires an authenticated brokerage session and can expose trading operations.

Local MCP server and CLI connecting assistants to OKX market data, account and trading operations, with read-only and module-filtering options; trading functions use exchange credentials and can place real orders.

Experimental command-line client with a built-in MCP server for Kraken market data, account operations and paper or live trading; authenticated live commands can execute real financial transactions.

MCP interface to Alpaca market data, accounts and order operations, requiring account API credentials; paper trading is the default, while explicitly configured live mode can execute real trades.

MCP connector for tennis scores, players and fixtures, with additional odds, statistics and model estimates depending on the data-service plan; an API key is required.

Independent MCP server for searching and retrieving FRED economic time-series data using a FRED API key; it is not affiliated with the Federal Reserve.

MCP adapter for the Financial Modeling Prep API, with dynamically loaded or preselected financial toolsets and hosted or self-hosted operation; it requires an FMP access token.

Alpha Vantage MCP server exposing financial-data and technical-indicator functions to assistants, available through a remote connection or local process and requiring an Alpha Vantage API key.

MCP server built on akshare-one for Chinese stock history, quotes, news and financial statements, with source and adjustment options and stdio or Streamable HTTP transport.

MCP server exposing Yahoo Finance stock history, company information, financial statements, options and news to compatible assistants, with local Python setup.

Experimental MCP interface to the Massive.com financial-data API, combining endpoint search, API calls and SQL over in-memory result tables; it requires a Massive.com API key.

Python MCP server and integration examples for TickDB market quotes, candles, order books and trades; self-hosting the connector still requires access credentials for the separate TickDB data service.

Locally runnable MCP financial-data server routing requests across providers such as Tushare, Qveris and Binance, with source attribution and provider credentials; its public hosted service is currently suspended.

Python library for retrieving and parsing SEC EDGAR filings into structured objects and tables, with XBRL, financial statements and MCP integration; requests require a configured email identity.

Independent MCP server for market data, technical indicators, screening and backtesting, with self-hosted and paid hosted options; it is not a TradingView product and optional news features require a provider key.

Claude Code research framework combining four analyst perspectives, reports and deterministic tools; its walk-forward backtester evaluates a rule-based approximation, not the agents’ qualitative decisions.

Web and Python tool for source-linked funding and liquidity briefs, optional snapshot comparisons and evidence-gap tracking; it can prepare material for an AI assistant but does not itself call a model or place orders.

Claude research skill with Python helpers for parameter-region pooling, effective sample size, selection bias and position sizing; it reviews backtest evidence without guaranteeing future returns.

Claude Code research skill with Python tools for SEC EDGAR and market data, producing stock summaries, scores and comparisons; the repository exposes a partial methodology, while full reports are a separate service.

Research engine using generative order models to simulate financial markets, with examples for market statistics, forecasting and market impact; setup requires model assets and a Docker/CUDA environment.

Educational terminal application for defining model-assisted funds and backtesting their strategies, using financial-data and model API keys; its documented current workflow does not execute trades.