io.github.koreal6803/finlab-ai MCP Server
io.github.koreal6803/finlab-ai
Quantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples for AI-driven alpha discovery.
What this kind of tool is for
- Query, inspect, or seed a database without writing a one-off script.
- Let your agent look up schema details before it writes migration code.
- Move a small dataset between tools without leaving the terminal.
How to compare servers like this
- Engine match:
- Confirm it speaks your exact database and version, not just the family.
- Access scope:
- Read-only connections are the safe default — start there before granting writes.
- Safety rails:
- Check whether destructive statements need an explicit confirmation before they run.
- Maintenance signal:
- Database drivers change; a recently updated tool is less likely to break mid-query.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.koreal6803/finlab-ai MCP server?
FinLab AI is a quantitative trading toolkit that provides access to 900+ financial data columns, backtesting capabilities, and 60+ pre-built strategy examples. It enables AI agents to discover trading strategies, analyze stock evidence, and explore factor-based approaches for Taiwan stock markets.
FinLab AI gives you a complete quantitative trading environment accessible via MCP. Query financial data across 80+ tables, backtest strategies with the sim() API, explore 60+ example strategies with Python code, and leverage factor engineering for stock selection. It's designed for researchers and traders building data-driven trading systems.
How to install io.github.koreal6803/finlab-ai
Copy-paste configuration for popular MCP clients.
{
"mcpServers": {
"finlab-ai": {
"url": "https://mcp.finlab.finance/mcp"
}
}
}Tools & capabilities
Tools this server exposes to the agent.
list_strategies— List available pre-built strategy examplesget_strategy— Retrieve a specific strategy with its Python codeget_stock_evidence— Get evidence and analysis for stock selectionget_data_catalog— Browse the 900+ available data columns across 80+ tablesget_finlab_docs— Access FinLab AI documentation, always in sync with the main repositoryhow_to_start— Get guidance on getting started with FinLab AI
Use cases
- Backtest quantitative trading strategies on Taiwan stock data using the sim() API
- Discover factor-based stock selection signals from 900+ financial data columns
- Explore and adapt 60+ pre-built strategy examples with Python code
- Analyze stock evidence and multi-factor composites for portfolio construction
- Research strategy performance metrics (CAGR, Sharpe ratio, max drawdown) on historical data
io.github.koreal6803/finlab-ai MCP server FAQ
FinLab AI is a quantitative trading toolkit that provides access to 900+ financial data columns, backtesting capabilities, and 60+ strategy examples. It helps AI agents discover trading strategies and analyze stock markets, primarily focused on Taiwan stocks.
You can use the automated installer: `curl -sSf https://ai.finlab.finance/install.sh | sh`. Alternatively, use the hosted MCP server without installation: `claude mcp add --transport http finlab https://mcp.finlab.finance/mcp`
The README does not specify pricing details. The hosted MCP server is available as a read-only service, but you should check finlab.finance for current pricing and terms.
FinLab AI provides 900+ data columns across 80+ tables, including stock prices, factors, and fundamental data. The get_data_catalog tool lets you browse all available data.
Yes. FinLab AI includes a backtesting API (sim()) with support for resampling and metrics like CAGR, Sharpe ratio, and max drawdown. You can test your own strategies or adapt from 60+ examples.
The hosted MCP server is read-only and available at https://mcp.finlab.finance/mcp. No authentication details are mentioned in the README.
README (reference)
Source of truth, from the repository.
FinLab AI
Let AI discover your next alpha.
FinLab AI is an official product of FinLab. FinLab official website: https://finlab.finance
<br> <img src="assets/demo.gif" alt="Demo" width="600"> </div>Installation
curl -sSf https://ai.finlab.finance/install.sh | sh
Auto-detects your CLI (Claude Code / Codex / Gemini), installs uv if needed, and sets up the skill.
MCP Server
A hosted, read-only MCP server (streamable HTTP) is available — no install required:
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).
- Website: finlab.finance
Related MCP servers
CryptoData MCP Server - Real-time crypto market data, DeFi analytics, and on-chain intelligence...
Purchaser-gated MCP for Vault, HMRC TRS, 95/5 equity, and Companies House PSC.
View repository →
io.github.kozmos-tech/contactapi
An open-source API for collecting and managing contacts and signups.

io.github.kozmos-tech/inhalt
An open-source headless CMS for managing content models and entries.

Talkthrough
Convert recordings and video URLs into searchable transcripts, keyframes, OCR, and wall-clock timestamps for AI-assisted bug reports and incident analysis.


