finlab-ai MCP server
io.github.koreal6803/finlab-aikoreal6803streamable-httpv1.1.0Scanned
Quantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples.
6 tools: 1 change things and 5 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the finlab-ai MCP server can do
The finlab-ai MCP server is published by the GitHub account koreal6803. It has 6 tools. It can create or change data (1 tool: how_to_start), but cannot delete data. 5 tools only read.
1 tool reads private data (get_finlab_docs).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 1.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
6 tools
Changes things 1Claude Code: ask
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」。No findings
Why it is in this group
- The name "how_to_start" says "start": a word for a change.
Description, as the server wrote it 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」。
Only reads 5Show 5 read-only tools
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」。No findings
Why it is in this group
- The name "get_data_catalog" says "get": a word for reading.
Description, as the server wrote it 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 P…Reads private dataNo findings
Why it is in this group
- The name "get_finlab_docs" says "get": a word for reading.
What it can reach
- private-dataThe name "get_finlab_docs" says "get" and "doc": it reads documents.
- private-dataThe description's first sentence says "doc": it reads documents.
Description, as the server wrote it 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。No findings
Why it is in this group
- The name "get_stock_evidence" says "get": a word for reading.
Description, as the server wrote it 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。No findings
Why it is in this group
- The name "get_strategy" says "get": a word for reading.
Description, as the server wrote it 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。
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。No findings
Why it is in this group
- The name "list_strategies" says "list": a word for reading.
Description, as the server wrote it 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。
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:07 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 1
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.finlab.finance/mcp: tools/list returned 6 tools to an anonymous client, including how_to_start (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http finlab-ai https://mcp.finlab.finance/mcpclaude mcp add --transport http finlab-ai https://mcp.finlab.finance/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__finlab-ai__list_strategies",
"mcp__finlab-ai__get_strategy",
"mcp__finlab-ai__get_stock_evidence",
"mcp__finlab-ai__get_data_catalog",
"mcp__finlab-ai__get_finlab_docs"
],
"ask": [
"mcp__finlab-ai__how_to_start"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as finlab-ai. Review it before you use it.
Capability tags behind 1 rule
- mcp__finlab-ai__get_finlab_docs private-data
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.koreal6803/finlab-ai/verify?hash=f7feefac76e974cc30410ad4dd2e46d708b0f0e8b0a570984d0dd78d094f9c26" | jq -e '.changed == false'Pinned hash f7feefac76e9, from Nov 20, 2026, 00:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.koreal6803/finlab-ai/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.koreal6803/finlab-ai)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:37 UTC.
finlab-ai MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the finlab-ai MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the finlab-ai MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the finlab-ai MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the finlab-ai MCP server have?
- 6 tools: 1 write, 5 read. how_to_start, list_strategies, get_strategy, get_stock_evidence, get_data_catalog and get_finlab_docs.
Does the finlab-ai MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the finlab-ai MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the finlab-ai MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.