Stock Sentinel

sdzhuang/stock-sentinel-mcp

Daily US stock market attack/defense signals from a data-driven 4-dimension macro framework: AI supply-demand (model usage + cloud capex + semiconductor output, the cash-flow chain), monetary (FOMC decision direction), fiscal (real federal outlays), and administrative policy (EPU + oil shock). 4 tiers: attack / watch / reduce / defense, with recession locks, attack-admission vetoes (yield curve, credit spread, real rates) and a public 26-year backtest + tamper-evident daily track record. For research reference only — not investment advice.

Website ↗

Watch this dependency Share evidence report

Uptime

100.0%

5 direct probes · 30d

Response

642ms

last probe

Tools

callable

Resources

readable

Prompts

available

Primary URL

https://stocksentinel-production-55ed.up.railway.app/mcp

Score: 100/100

Handshake verified by our own probe.

pass Answers the MCP handshake 50/50

The handshake and the list calls succeeded on the primary URL.

pass Lists tools, resources or prompts 30/30

8 tools, 0 resources, 0 prompts returned.

pass 3 or more catalogue items 10/10

8 items in total; 3 or more earns these points.

pass Describes itself 10/10

545 characters; more than 30 earns these points.

Tools · 8

get_current_signal

获取美股当前进攻/防守信号。返回四档最终信号（attack进攻/neutral观望/reduce减仓观望/defense全面防守）、四个维度（AI供需/货币/财政/行政）各自的宽松/中性/收紧状态、以及全部参考指标（联邦基金利率、萨姆规则、联邦支出、WTI油价、EPU不确定性指数、美债收益率曲线、AI模型调用量等）。更新节奏：每日美东21:00生成完整快照；FOMC决议（美东14:00）与08:3…

get_signal_history

获取信号历史存档（公开可验证的 track record）：每日的最终档位与四维状态，按日期倒序。可用于回看信号在近期市场事件中的表现。

get_ai_chain

获取AI产业链资金流向状态：六个环节（AI大模型→云厂商→AI芯片→存储/光模块→设备封装→电力）按30天相对SPY强弱的排名、当前市场隐含的卡点环节、以及泡沫监测三指标（模型调用量趋势/云厂商资本开支/半导体产出同比，按现金流向排序）。

get_stock_percentile

查询个股或ETF：当前价格在历史区间中的百分位（≥80%高位/≤20%低位）、真实市盈率P/E与市销率P/S（SEC EDGAR财报口径）。支持指数别名：US10Y(10年美债收益率)、VIX、SPX、NDX。

get_backtest_summary

获取信号系统的历史回测核心结论：26年月度重放，覆盖6场危机（2000互联网泡沫/2008金融危机/2020新冠/2022加息熊/2025关税战/2026美伊战争）的捕获情况与8段大规模上涨期的捕获率，以及"仅全面防守离场"策略与买入持有的全期对比（年化/最大回撤）。

get_daily_report

获取AI生成的每日信号解读（中英双语）：今日档位、由哪些维度和数据驱动、距离进攻/防守的条件差距。

get_research_note

获取 AI 产业链公司（MSFT/GOOGL/AMZN/META/NVDA/AMD/AVGO/TSM）某财季的结构化研究笔记：关键数字（XBRL，本季/上季/去年同期/环比/同比）、要点、对照管理层指引（是否达成由程序计算）、变化、风险点、未披露项。每条陈述附出处（XBRL 字段或 SEC 原文链接+字符区间+逐字引文）；未通过程序核对的陈述标 needs_review。quarter 用财年口径…

ask_company

就一家 AI 产业链公司（MSFT/GOOGL/AMZN/META/NVDA/AMD/AVGO/TSM）提问，答案只依据其 SEC 申报原文与 XBRL 数据，每句附出处；程序逐句核对，核对不通过的句子不返回（unverified 计数）。不回答买卖建议、目标价或股价预测类问题。需要 API key（free 每日 5 次）。仅供研究参考，不构成投资建议。

How to use

Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://stocksentinel-production-55ed.up.railway.app/mcp

Cursor or Cline: add to your MCP config:

{
  "mcpServers": {
    "stock_sentinel": {
      "url": "https://stocksentinel-production-55ed.up.railway.app/mcp",
      "transport": "http"
    }
  }
}

Tools · 8

How to use

Cookies on Agenstry