MCP.so
登录

fAlpha MCP Server已验证已精选

@fAlpha.ai, Inc.

基本信息

分类

金融与商务

许可证

MIT

认证方式

oauth

作者

fAlpha.ai, Inc.

提交者

Uttkarsh Singh

关于 fAlpha MCP Server

面向 AI 智能体的只读美股研究:fAlpha 对某只股票的模型信号及其背后的驱动因素、信号历史与翻转、新闻情绪、分析师覆盖、SEC 文件、FRED 宏观数据和基本面。每条结果

fAlpha MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "falpha": {
      "type": "http",
      "url": "https://agent.falpha.ai/mcp"
    }
  }
}

fAlpha MCP Server 工具

17

The model's current reading on one ticker: the equity indicator (EI, signed: positive leans long, negative leans short), the signal's risk-adjusted track record, and the driver carrying the reading, with the date the signal is for.

Two tickers side by side on the current signal, with which of the two carries the stronger reading.

The signal and its drivers as they stood on a past date, read point-in-time: only data available on that date is used.

How a ticker performed over a date range and how the signal would have performed if followed, measured against a benchmark.

The dates the signal changed direction (long to short or back) over a lookback window, the drivers at each change, and the current direction.

The model's term structure for a ticker: the equity indicator's direction from one day out to six months, the curve's shape (strengthening, weakening or flipping) and whether the sign changes across horizons.

Ranks fAlpha's covered universe (about 5,000 US equities) by the current signal, either the equity indicator or the signal's realized Sharpe ratio, filtered by direction, sector or a minimum Sharpe ratio.

Whether a ticker is in fAlpha's covered universe, with its sector and latest signal date, or a page through the universe.

fAlpha's daily news sentiment score for a ticker, with the articles it was computed from and the date of the reading.

How news sentiment has moved over a window: the current reading, the change since the window opened, the direction, the high/low band and the daily series.

Sell-side coverage for a ticker: recent price-target calls with source links, an accuracy-weighted consensus lean, and each analyst's historical hit rate, including their accuracy when agreeing and when disagreeing with the fAlpha model.

The fAlpha definition of a term the desks return: EI (equity indicator), VICE, drivers, Sharpe, Sortino, percent_positive_pnl, signal flip, term structure.

Recent SEC filings for a ticker from SEC EDGAR (10-K, 10-Q and 8-K by default), newest first, each with its filing date and document URL.

Reported fundamentals from SEC XBRL filings: revenue, net income, diluted EPS, total assets, total liabilities and stockholders' equity, for the latest reported quarters and fiscal years, each with its period end and filing date.

The US macro backdrop from FRED: the fed funds rate (DFF), CPI (CPIAUCSL), unemployment (UNRATE), the 10y-2y spread (T10Y2Y) and the 10-year yield (DGS10).

Company profile and trailing-twelve-month ratios from FMP: sector, market cap, P/E, margins, debt/equity.

Links to the fAlpha website and the user's account page, where plan, usage and billing are shown.

概览

What is fAlpha?

fAlpha is a hosted MCP server that gives AI assistants read-only US equity research: fAlpha's model signal for a stock and the drivers behind it, plus the public data around it. Every result says which source produced it and the date the data is for. The signal is model output, not investment advice, and the server never places orders.

How to connect

  • Endpoint: https://agent.falpha.ai/mcp (Streamable HTTP)
  • Auth: OAuth 2.1 with your fAlpha account, or a personal access token (Authorization: Bearer falpha_pat_…)
  • No-card trial token: https://falpha.ai/mcp/trial
  • Claude: Customize → Connectors → + → paste the endpoint → approve on falpha.ai
  • ChatGPT: Settings → Security and login → Developer mode on → Plugins → + → paste the endpoint
  • Claude Code: claude mcp add --transport http falpha https://agent.falpha.ai/mcp, then /mcp to sign in
  • Cursor, VS Code and more: https://falpha.ai/mcp

Tools

  • Signal: current card, compare two tickers, history on a past date, performance, flips, term structure
  • Screener: screen the covered universe, coverage check
  • News sentiment and its trend
  • Analyst coverage and price targets
  • SEC filings and XBRL company facts
  • FRED macro backdrop
  • Company profile and ratios
  • Glossary of fAlpha terms, and a link to open the view on falpha.ai

Use cases

  • "What does the model say about NVDA, and what's driving it?"
  • "Compare the signals on AAPL and MSFT."
  • "When did the signal on TSLA last flip, and what changed?"
  • "Screen semiconductors with a positive signal and improving sentiment."
  • "Summarize the latest 10-Q for AMD alongside its signal."

Data sources

fAlpha's own model signal and news sentiment; Financial Modeling Prep (prices, analyst targets, fundamentals); SEC EDGAR (filings, XBRL); FRED (macro).

常见问题

1

Is it free?

There is a no-card trial token at https://falpha.ai/mcp/trial. Ongoing use needs a fAlpha account.

2

Does it trade?

No. All tools are read-only and nothing places orders.

3

Is this investment advice?

No. The signal is model output.

4

Where is the code?

The server is hosted. https://github.com/techbammoney/falpha-agent-kit (MIT) holds the Claude plugin, recipes and example prompts.

评论

金融与商务 分类下的更多 MCP 服务器