FinLab MCP
A hosted read-only MCP server for the FinLab Quant Research Platform, enabling AI agents to access quantitative trading tools, backtesting engines, and market data for U.S. and Taiwan stock research.
Endpoint and access
No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.
https://mcp.finlab.finance/mcpWhat its tools do
6 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.
Checks and signals
Each line is separate evidence, not a trust score.
- Passed Endpoint answered the live check ·
- Availability 1 of 1 checks passed in 30 days
What you can do with it
- Backtest Taiwan or U.S. stock strategies using AI agents
- Access quantitative trading data and Python SDK tools
- Generate strategy reports and performance metrics
Source and maintenance
- Maintenance checked
Protocol and capabilities
- Server
- FinLab 1.0.0
- MCP protocol negotiated in check
- 2025-06-18
- Tools
- 6 advertised
- Resources
- Not advertised
- Resource templates
- Not advertised
- Prompts
- Not advertised
{
"tools": {
"listChanged": true
}
}Server-provided instructions
Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.
Tools
6 advertised
list_strategies — 列出 FinLab 策略庫
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。
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}get_strategy — 取得單一策略完整內容
取得 FinLab 策略庫中單一策略的完整快照:策略說明、真實回測績效與基準比較、以及可直接執行的 finlab Python 程式碼。slug 可先用 list_strategies 查詢。
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "策略代號(slug),例如由 list_strategies 取得"
}
},
"additionalProperties": false
}get_stock_evidence — 查個股數據實證
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。
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"symbol"
],
"properties": {
"market": {
"enum": [
"tw",
"us"
],
"type": "string",
"description": "市場,預設 \"tw\" 台股;\"us\" 為美股(覆蓋率較低)。"
},
"symbol": {
"type": "string",
"description": "台股股票代號字串,例如 \"2330\"(台積電)、\"0050\"、\"00631L\"。保留前導零,不要轉成數字。"
}
},
"additionalProperties": false
}get_data_catalog — FinLab 資料庫目錄摘要
取得 FinLab 量化資料庫的目錄摘要:涵蓋台股與美股的分類數、欄位數、資料列數、年份範圍,以及代表性資料集(股價、月營收、財務指標等)。適合回答「FinLab 有哪些資料」。
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}get_finlab_docs — FinLab Skill 開發文件
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。
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"doc": {
"type": "string",
"description": "參考文件檔名,例如 \"dataframe-reference.md\"。省略時回傳 SKILL.md 與文件清單。"
}
},
"additionalProperties": false
}how_to_start — FinLab 快速上手
取得 FinLab 快速上手指南:如何用 AI 輔助流程(Claude cowork / Codex)在自己電腦安裝 FinLab 並跑第一個台股策略真實回測,以及免費線上體驗入口。適合回答「怎麼開始用 FinLab」「怎麼回測台股」。
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}Prompts
Not advertised
Resources
Not advertised
90-day uptime
A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.
- 2026-11-06: 1 of 1 checks answered
- 2026-11-07: 1 of 1 checks answered
30-day availability
Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.
- Successful checks
- 1 of 1 (100%)
- Average latency
- 1125 ms
- 95th percentile latency
- 1125 ms
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · probe · passed · 1125 ms · metadata changed · 6 tool(s)
Connect from your client
Each snippet registers the same endpoint; pick the client you use.
Claude Code
claude mcp add --transport http finlab-mcp https://mcp.finlab.finance/mcpCodex
codex mcp add finlab-mcp --url https://mcp.finlab.finance/mcpCursor
{
"mcpServers": {
"finlab-mcp": {
"url": "https://mcp.finlab.finance/mcp"
}
}
}Cline
{
"mcpServers": {
"finlab-mcp": {
"type": "streamableHttp",
"url": "https://mcp.finlab.finance/mcp",
"disabled": false
}
}
}VS Code
{
"servers": {
"finlab-mcp": {
"type": "http",
"url": "https://mcp.finlab.finance/mcp"
}
}
}Gemini CLI
gemini mcp add --transport http finlab-mcp https://mcp.finlab.finance/mcpClaude Desktop
https://mcp.finlab.finance/mcpWindsurf
{
"mcpServers": {
"finlab-mcp": {
"serverUrl": "https://mcp.finlab.finance/mcp"
}
}
}Let your agent find its tools
Find servers like FinLab MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.