Connect Finlab AI and your agent gets 6 tools, among them get_data_catalog, get_finlab_docs, get_stock_evidence. It answers at https://mcp.finlab.finance/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 22 October 2026, succeeded.
Quantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
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」。 |
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。 Inputs: doc |
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。 Inputs: symbol, market |
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。 Inputs: slug |
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」。 |
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。 |
Every block below points at https://mcp.finlab.finance/mcp. Pick your client and copy.
claude mcp add --transport http finlab-ai https://mcp.finlab.finance/mcp
{
"mcpServers": {
"finlab-ai": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.finlab.finance/mcp"]
}
}
}{
"mcpServers": {
"finlab-ai": {
"url": "https://mcp.finlab.finance/mcp"
}
}
}{
"servers": {
"finlab-ai": {
"type": "http",
"url": "https://mcp.finlab.finance/mcp"
}
}
}{
"context_servers": {
"finlab-ai": {
"url": "https://mcp.finlab.finance/mcp"
}
}
}{
"mcpServers": {
"finlab-ai": {
"serverUrl": "https://mcp.finlab.finance/mcp"
}
}
}{
"mcpServers": {
"finlab-ai": {
"url": "https://mcp.finlab.finance/mcp"
}
}
}name: Finlab AI
version: 0.0.1
schema: v1
mcpServers:
- name: Finlab AI
type: streamable-http
url: https://mcp.finlab.finance/mcp{
"mcpServers": {
"finlab-ai": {
"httpUrl": "https://mcp.finlab.finance/mcp"
}
}
}{
"mcpServers": {
"finlab-ai": {
"type": "http",
"url": "https://mcp.finlab.finance/mcp"
}
}
}{
"mcpServers": {
"finlab-ai": {
"url": "https://mcp.finlab.finance/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.finlab.finance%2Fmcp&type=streamable_http&id=finlab-ai&name=Finlab%20AI
It answered our last check on 22 October 2026 in 361 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
6, as returned by the server's own tools/list on 15 September 2026: get_data_catalog, get_finlab_docs, get_stock_evidence, get_strategy, how_to_start, list_strategies.
It answered our last check on 22 October 2026 in 361 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.finlab.finance/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.koreal6803. Endpoint host: mcp.finlab.finance. ARD identifier: urn:air:io.github.koreal6803:mcp:finlab-ai.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.