Is the Koreal6803 Finlab Ai MCP server down?

mcp-registry/io.github.koreal6803/finlab-ai · v1.0.0

As of 2026-10-22 10:34 UTC, the Koreal6803 Finlab Ai MCP server is up with a Glimind reliability score of 91/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 7 minutes.

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

claude mcp add --transport http koreal6803-finlab-ai-mcp-server https://mcp.finlab.finance/mcp

{
  "mcpServers": {
    "koreal6803-finlab-ai-mcp-server": {
      "type": "http",
      "url": "https://mcp.finlab.finance/mcp"
    }
  }
}

Third-party server, listed as discovered. Review its source before installing.

Agent-readiness: B (84/100)

What to fix (3)

Auto-fix: 6 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fio.github.koreal6803%2Ffinlab-ai/fixes

{
  "name": "get_data_catalog",
  "description": "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」。",
  "inputSchema": {
    "type": "object",
    "$schema": "http://json-schema.org/draft-07/schema#",
    "properties": {}
  },
  "annotations": {
    "readOnlyHint": true
  },
  "title": "FinLab 資料庫目錄摘要"
}

{
  "name": "get_finlab_docs",
  "description": "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。",
  "inputSchema": {
    "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
  },
  "annotations": {
    "readOnlyHint": true
  },
  "title": "FinLab Skill 開發文件"
}

{
  "name": "get_stock_evidence",
  "description": "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。",
  "inputSchema": {
    "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
  },
  "annotations": {
    "readOnlyHint": true
  },
  "title": "查個股數據實證"
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/io.github.koreal6803/finlab-ai"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/io.github.koreal6803/finlab-ai"}) over MCP.

Passed

• Every tool has a well-formed, typed input schema.
• Every tool and parameter is described.
• No tool-poisoning patterns (hidden characters, instruction overrides, concealment, secret access, tool shadowing).
• Compact tool list (~581 tokens).
• Tool names are unique and portable across clients.
• Speaks MCP 2025-06-18.
• 99.95% uptime over 30 days.
• No breaking contract changes in 30 days.

Largest tool definitions

• get_stock_evidence ~145 tokens
• get_finlab_docs ~130 tokens
• get_strategy ~100 tokens
• how_to_start ~72 tokens
• list_strategies ~69 tokens

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live. Embed the readiness badge:

[![MCP agent-readiness](https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.koreal6803%2Ffinlab-ai.svg)](https://glimind.com/server/mcp-registry%2Fio.github.koreal6803%2Ffinlab-ai?ref=badge)

<a href="https://glimind.com/server/mcp-registry%2Fio.github.koreal6803%2Ffinlab-ai?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.koreal6803%2Ffinlab-ai.svg" alt="MCP agent-readiness"></a>

.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fio.github.koreal6803%2Ffinlab-ai.svg
   :target: https://glimind.com/server/mcp-registry%2Fio.github.koreal6803%2Ffinlab-ai?ref=badge
   :alt: MCP agent-readiness

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:b60daab669846b10…, first seen 2026-10-17, included at leaf 247 of 45,439. Version history · verify what your client received.

Tools (6)

• get_data_catalog
• get_finlab_docs
• get_stock_evidence
• get_strategy
• how_to_start
• list_strategies

Compare: most reliable data servers · most reliable knowledge servers

claude mcp add --transport http glimind https://glimind.com/mcp

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp"
    }
  }
}

FAQ

Is the Koreal6803 Finlab Ai MCP server down right now?

As of 2026-10-22 10:34 UTC, the Koreal6803 Finlab Ai MCP server is up with a Glimind reliability score of 91/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks. It had 3 outages in 90 days, with a median recovery of 7 minutes.

How many tools does Koreal6803 Finlab Ai MCP server provide?

Koreal6803 Finlab Ai MCP server advertises 6 tools, including get_data_catalog, get_finlab_docs, get_stock_evidence, get_strategy, how_to_start.

How do I install Koreal6803 Finlab Ai MCP server?

Point your MCP client at this streamable-http endpoint: https://mcp.finlab.finance/mcp

Is the Koreal6803 Finlab Ai MCP server safe to connect to an AI agent?

Glimind scanned all 6 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of Koreal6803 Finlab Ai MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.