Quantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples.
finlab-ai MCP Server (io.github.koreal6803/finlab-ai)
FinLab AI is a quantitative trading toolkit. It includes 900+ data columns, backtesting, and 60+ strategy examples. It also provides an official hosted, read-only Model Context Protocol (MCP) server over streamable HTTP, intended to be used without installing the toolkit locally.
🛠️ Key Features
Hosted, read-only MCP server
Streamable HTTP transport
Quantitative trading toolkit with 900+ data columns
Backtesting
60+ strategy examples
🚀 Use Cases
Query or use trading data from the 900+ data columns
Run or reference backtesting workflows
Explore strategy examples (60+)
⚡ Developer Benefits
No install required for the MCP server (hosted access)
HTTP-based integration via MCP
⚠️ Limitations
Server is read-only
MCP server is accessed via hosted streamable HTTP (no local install described)
FinLab AI is an official product of FinLab. FinLab official website: https://finlab.finance
Backtest Taiwan and U.S. stocks from Claude Code, Codex or Gemini CLI: your AI gets real market data and the FinLab backtest engine, with no scraping or backtest code of your own.
用 Claude Code、Codex 回測台股:AI 直接讀還原股價、月營收、財報、三大法人資料,用 FinLab 回測引擎驗證策略。
This installs the skill for Claude Code, Codex, Cursor and other tools that read Agent Skills, for every project on this machine. Already have the finlab package (2.3.9+)? python -m finlab skill install does the same without Node.js. Or use your tool's own plugin command:
codex plugin marketplace add koreal6803/finlab-ai, then codex plugin add finlab-plugin@finlab-ai
Cursor
Customize > From GitHub Repository > koreal6803/finlab-ai
Then ask your AI: "Backtest a Taiwan stock strategy that buys the strongest monthly revenue growth." The first run asks you to sign in to FinLab once in your browser, which creates a free account with a 7-day full trial, no credit card needed.
What it does on your machine
The skill is documentation: it has no hooks and no bundled programs. It tells your AI tool to install the finlab Python package with uv, sign in with python -m finlab login, which opens your browser, and download market data from FinLab. Strategy code runs on your machine, and nothing is uploaded unless you ask for it. It also documents broker order APIs, and tells your AI to show you a preview and wait for your confirmation before placing any real order.
MCP Server
A hosted, read-only MCP server (streamable HTTP) is available — no install required:
bash
claude mcp add --transport http finlab https://mcp.finlab.finance/mcp
Tools: list_strategies, get_strategy (with Python code), get_stock_evidence, get_data_catalog, get_finlab_docs (this skill's docs, always in sync with main), how_to_start. Listed on the MCP Registry as io.github.koreal6803/finlab-ai (see server.json). The old finlab-ai.koreal6803.workers.dev endpoint is retired.
Documentation
Document
Content
Data Reference
900+ columns across 80+ tables
Backtesting Reference
sim() API, resampling, metrics
Factor Examples
60+ complete strategy examples
Best Practices
Patterns, anti-patterns, tips
ML Reference
Feature engineering, labels
Learn more
Quant trading guide (量化交易): what quantitative trading is, a Taiwan-stock strategy backtester, and a platform comparison.
Program trading guide (程式交易): how program trading works, three backtest-verified Taiwan-stock strategies, and an auto-trading walkthrough.
Stock selection guide (股票選股): factor-based stock picking with real backtests, from single factors to multi-factor composites.
Strategy research blog: backtest-verified Taiwan-stock strategy reports (CAGR, Sharpe, max drawdown).