mcpbeat Sign in

Finlab AI MCP Server

by koreal6803 Your server? Claim it
answering

Finlab AI is answering right now. Last checked 4 min ago. It exposes 6 tools. Last commit 14 Aug 2026.

Quantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples.

Uptime history 47 days of history · worst day 0%
47 days agonow
50.0%
Uptime 24h
92 of 184 checks
6
Tools
read from the server
950 ms
Response time
average over 24h
413
Stars
last commit 14 Aug 2026

Finlab AI does not always answer

Over the last week it answered 50.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 4 min ago.

run in your terminal
claude mcp add finlab-ai --transport http https://mcp.finlab.finance/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "finlab-ai": {
      "url": "https://mcp.finlab.finance/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.finlab-ai]
url = "https://mcp.finlab.finance/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "finlab-ai": {
      "url": "https://mcp.finlab.finance/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "finlab-ai": {
      "url": "https://mcp.finlab.finance/mcp"
    }
  }
}

This server publishes 1 more address. The block above uses the one we reach during checks; the full list is under Endpoints below, and the author may intend a particular one for your client.

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

data
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」。
finlab
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。
how
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」。
stock
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。
strategies
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。
strategy
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。

Endpoints

URLTransportStateLatencyChecked
https://finlab-ai.koreal6803.workers.dev/mcp streamable-http answering 62 ms 6 min ago
https://mcp.finlab.finance/mcp streamable-http answering 770 ms 4 min ago

Alternatives to Finlab AI

same job, measured the same way
StratEvo
by neuzhou

Quantitative trading: quotes, backtesting, screening, and genetic algorithm strategy evolution.

68 installs/wk local only
CPZAI
by cpz-lab-mcp

Build, backtest, and deploy quantitative trading strategies from your AI agent.

answering
Quanttogo MCP
by michaeljiangmingfeng-debug

Quantitative trading strategies, market indices, and live performance data

75 installs/wk local only
Papers With Backtest
by paperswithbacktest

Search 5,000+ trading papers with verified backtests, strategies, datasets, and courses.

answering
Trading
by lona

AI-powered trading strategy development: backtesting, market data, and portfolio analysis

answering
dMoERA Creator
by cachecarti

Build, backtest, and deploy crypto trading strategies via MCP with 7-stage validation.

44 tools answering
TextToQuant Backtesting and Quant Research
by texttoquant

Backtest plain-English trading strategies on real market data: graded results, honesty flags.

answering
Sentinel
by clarencyu-boop

Crypto trading backtesting, bot deployment, AI strategy, and account management for Sentinel Bot.

36 installs/wk local only

Finlab AI — questions

Answers built from our own checks of this server.

What can Finlab AI do?
It exposes 6 tools, read directly from the server on our last check. Among them: get_data_catalog, get_finlab_docs, get_stock_evidence, get_strategy, how_to_start, list_strategies. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Finlab AI working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 184 checks got a reply (50.0%), average response time 950 ms. The bar chart above shows every period we have measured.
How do I connect Finlab AI?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Finlab AI need an API key?
No. Finlab AI completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Finlab AI?
It answers our handshake in 950 ms on average, which is faster than 10% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is Finlab AI open source?
We cannot say either way: 413 stars on GitHub and 2 open issues, but we could not determine the licence, and without one the code is not open source by default.