AptLynxMCP server
Finlab Ai
io.github.koreal6803/finlab-ai
Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools
Quantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples.
Working at last checkAbout 598 tokens per request once connected6 tools
https://mcp.finlab.finance/mcp
At a glance
- Type
- MCP server
- Publisher
- Not verified
- Status
- Working at last check
- Tools
- 6
- Token cost
- About 598 tokens per request
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
- Last checked
- 26 Oct 2026, 08:29 UTC
Connect it to your agent
Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.
Claude Code
claude mcp add --transport http finlab-ai https://mcp.finlab.finance/mcp
Claude Desktop
Settings → Connectors → Add custom connector, and paste the URL.
Codex (config.toml)
[mcp_servers.finlab-ai] url = "https://mcp.finlab.finance/mcp"
Gemini CLI
{"mcpServers":{"finlab-ai":{"httpUrl":"https://mcp.finlab.finance/mcp"}}}
Cursor
{"mcpServers":{"finlab-ai":{"url":"https://mcp.finlab.finance/mcp"}}}
VS Code
{"servers":{"finlab-ai":{"type":"http","url":"https://mcp.finlab.finance/mcp"}}}
Antigravity
agy mcp add finlab-ai https://mcp.finlab.finance/mcp
ChatGPT
Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.
OpenAI API (Responses tools)
{"type":"mcp","server_label":"finlab-ai","server_url":"https://mcp.finlab.finance/mcp","require_approval":"always"}
Grok (xAI API tools)
{"type":"mcp","server_label":"finlab-ai","server_url":"https://mcp.finlab.finance/mcp"}
Tools
get_data_catalog~67 tokens
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」。get_finlab_docs~134 tokens
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。get_stock_evidence~149 tokens
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。get_strategy~103 tokens
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。how_to_start~74 tokens
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」。list_strategies~71 tokens
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。
Browse
Related MCP servers
- AlgoMaker — quantitative trading strategy factory
Mine, validate and paper-trade quantitative trading strategies. The engine runs on your machine. - OpenQFR
Search machine-readable quantitative strategy failure evidence before repeating failed research. - BotSpot: AI Trading, Backtests and Bots
AI agents backtest, paper trade and live trade via your broker. Free to connect; OAuth. - Autotrade — Autonomous Trading Agents
Deploy autonomous LLM trading agents and drive them over MCP. - Brighter
Browse, backtest and write rule-based portfolios of tokenized US stocks. - dMoERA Creator
Build, backtest, and deploy crypto trading strategies via MCP with 7-stage validation. - Agent Einstein — Crypto & Market Intelligence
AI price forecasts, whale flows, market sentiment and prediction signals. 18 tools free, no account. - EmidLabs Backtest
Run crypto trading strategy backtests through EmidLabs's Backtesting API.
Badge for your README
[](https://aptlynx.net/servers/io.github.koreal6803/finlab-ai)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents