Provides 11 tools for stock research, including search, market history, financial statements, announcements, and data quality checks, with a local-first architecture using DuckDB and Parquet.
A local, fully vectorized computational engine for stock market analysis that enables AI to perform factor calculation, strategy backtesting, IC analysis, and GPU-based multi-dimensional visualization using local DuckDB data.
Local-first backtesting engine with built-in overfitting detection (PBO, deflated Sharpe, bootstrap CI, walk-forward) and a native MCP server for AI agents to validate trading strategies.
Read-only SQL MCP server for quantitative finance data (DuckDB) with stock quotes, financials, and historical K-lines, enabling cross-database JOIN queries.
Enables querying, modifying, and managing Parquet files with CRUD operations, semantic search, audit logging, and rollback capabilities for structured data storage.