io.github.koreal6803/finlab-ai

Official6 toolsLive

by koreal6803

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)

Captured live from the server via tools/list.

list_strategies

列出 FinLab 公開策略庫中的台股量化策略，含每一檔策略的真實回測績效摘要（CAGR、Sharpe、最大回撤）與基準比較。想看完整策略內容與 Python 程式碼時，請接著呼叫 get_strategy。

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_strategy

取得 FinLab 策略庫中單一策略的完整快照：策略說明、真實回測績效與基準比較、以及可直接執行的 finlab Python 程式碼。slug 可先用 list_strategies 查詢。

Parameters1

slug

string

required

策略代號（slug），例如由 list_strategies 取得

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "策略代號（slug），例如由 list_strategies 取得"
    }
  },
  "required": [
    "slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_stock_evidence

查詢台股個股的每日更新數據實證：基本面體質定位（獲利、估值、籌碼因子百分位）、目前正在觸發的量化訊號與其歷史前瞻報酬統計、估值位階等。例如 symbol="2330" 查台積電。資料來自 FinLab 每日以 finlab 套件計算的真實數據。

Parameters2

symbol	string	required	台股股票代號字串，例如 "2330"（台積電）、"0050"、"00631L"。保留前導零，不要轉成數字。
market	string	optional	市場，預設 "tw" 台股；"us" 為美股（覆蓋率較低）。

Raw schema

{
  "type": "object",
  "properties": {
    "symbol": {
      "type": "string",
      "description": "台股股票代號字串，例如 \"2330\"（台積電）、\"0050\"、\"00631L\"。保留前導零，不要轉成數字。"
    },
    "market": {
      "type": "string",
      "enum": [
        "tw",
        "us"
      ],
      "description": "市場，預設 \"tw\" 台股；\"us\" 為美股（覆蓋率較低）。"
    }
  },
  "required": [
    "symbol"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_data_catalog

取得 FinLab 量化資料庫的目錄摘要：涵蓋台股與美股的分類數、欄位數、資料列數、年份範圍，以及代表性資料集（股價、月營收、財務指標等）。適合回答「FinLab 有哪些資料」。

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_finlab_docs

取得 FinLab Skill 的開發文件（與 GitHub koreal6803/finlab-ai main 分支同步，skill 更新後自動生效）：不帶參數回傳 SKILL.md 主文件與參考文件清單；帶 doc 參數回傳指定參考文件全文。涵蓋 900+ 資料欄位、sim() 回測 API、60+ 策略範例、因子分析與機器學習等，撰寫 finlab Python 程式前建議先查閱。

Parameters1

doc

string

optional

參考文件檔名，例如 "dataframe-reference.md"。省略時回傳 SKILL.md 與文件清單。

Raw schema

{
  "type": "object",
  "properties": {
    "doc": {
      "type": "string",
      "description": "參考文件檔名，例如 \"dataframe-reference.md\"。省略時回傳 SKILL.md 與文件清單。"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

how_to_start

取得 FinLab 快速上手指南：如何用 AI 輔助流程（Claude cowork / Codex）在自己電腦安裝 FinLab 並跑第一個台股策略真實回測，以及免費線上體驗入口。適合回答「怎麼開始用 FinLab」「怎麼回測台股」。

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md2 KBView on GitHub

FinLab AI

Let AI discover your next alpha.

FinLab AI is an official product of FinLab. FinLab official website: https://finlab.finance

Demo

Installation

bash

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:

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).
Website: finlab.finance

Install

Tools (6)

list_strategiesget_strategyget_stock_evidenceget_data_catalogget_finlab_docshow_to_start

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.finlab.finance/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "finlab-ai": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.finlab.finance/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

finlab-ai MCP Server (io.github.koreal6803/finlab-ai)

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

list_strategies

get_strategy

get_stock_evidence

get_data_catalog

get_finlab_docs

how_to_start

FinLab AI

Installation

MCP Server

Documentation

Learn more

Install

Remote endpoint

Related servers