fAlpha is an MCP server with 17 tools an agent can call, among them falpha_analyst_desk, falpha_filings_scout, falpha_filings_scout_facts. It answers at https://agent.falpha.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 27 September 2026; the last check, on 12 November 2026, succeeded.
Explainable model signals, drivers, news sentiment, SEC filings and macro data for US stocks.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
falpha_analyst_desk | [Analyst Desk] 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 f Inputs: ticker |
falpha_filings_scout | [Filings Scout] 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. Requires a connected fAlpha account; not included in the free trial. Inputs: ticker, forms, limit |
falpha_filings_scout_facts | [Filings Scout] 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 Inputs: ticker, max_metrics |
falpha_fundamentals_desk | [Fundamentals Desk] Company profile and trailing-twelve-month ratios from FMP: sector, market cap, P/E, margins, debt/equity. Third-party reference data, not fAlpha model output. Requires a connected fAlpha account; not included in the free Inputs: ticker, include_ratios |
falpha_glossary | [Glossary] The fAlpha definition of a term the desks return: EI (equity indicator), drivers, Sharpe, Sortino, percent_positive_pnl, signal flip, term structure. Not metered. Available without an account. Inputs: name |
falpha_macro_desk | [Macro Desk] 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). One series returns its recent history; with no series the full bundle i Inputs: series_id |
falpha_open_in_web | [Your Record] Links to the fAlpha website and the user's account page, where plan, usage and billing are shown. For questions about the user's fAlpha plan, usage, billing or account. Not metered. Available without an account. |
falpha_screener_desk | [Screener Desk] Ranks fAlpha's covered universe (5k+ 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. Names that share the top va Inputs: horizon, regime, rank_by, direction, min_sharpe, sector |
falpha_screener_desk_coverage | [Screener Desk] Whether a ticker is in fAlpha's covered universe, with its sector and latest signal date, or a page through the universe. The other desks return no data for tickers outside it. Available without an account. Inputs: ticker, sector, index, page, page_size |
falpha_sentiment_desk | [Sentiment Desk] fAlpha's daily news sentiment score for a ticker, with the articles it was computed from and the date of the reading. For questions like 'what is the news saying about AMZN'; falpha_sentiment_desk_trend covers how it has mo Inputs: ticker, window_days |
falpha_sentiment_desk_trend | [Sentiment Desk] How news sentiment has moved over a window: the current reading (the newest scored day, with its date and article count), the change since the window opened, the direction, the high/low band and the daily series. For questi Inputs: ticker, window_days |
falpha_signal_desk_card | [Signal Desk] fAlpha's current model reading on one ticker, computed by quantitative models from numerical market data (no language model sets the number): the equity indicator (EI, signed: positive leans long, negative leans short) and the Inputs: ticker, horizon, regime |
falpha_signal_desk_compare | [Signal Desk] Two tickers side by side on the current signal, with which of the two carries the stronger reading (`stronger`; EI magnitudes within 0.05 of each other are `comparable`). For questions like 'AAPL or MSFT'; falpha_screener_desk Inputs: ticker_a, ticker_b, horizon, regime |
falpha_signal_desk_curve | [Signal Desk] 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), whether the sign changes across horizons, and near/mid/long su Inputs: ticker, regime, as_of_date |
falpha_signal_desk_flips | [Signal Desk] The dates the signal changed direction (long to short or back) over a lookback window, the drivers at each change, and the current direction. For questions like 'when did the model turn bearish on TSLA'. Requires a connected f Inputs: ticker, horizon, regime, lookback_days |
falpha_signal_desk_history | [Signal Desk] The signal and its drivers stored for a past date (the newest reading on or before it). For questions like 'what did the model say in June'; falpha_signal_desk_performance covers a date range. Requires a connected fAlpha accou Inputs: ticker, as_of_date, horizon, regime |
falpha_signal_desk_performance | [Signal Desk] How a ticker moved over a date range against a benchmark, and the excess return taken in the direction of the signal on the range's first day. One reading held over one window: a realized outcome, not a forecast. For questions Inputs: ticker, frm, to, horizon, regime, benchmark |
Every block below points at https://agent.falpha.ai/mcp. Pick your client and copy.
claude mcp add --transport http falpha https://agent.falpha.ai/mcp
{
"mcpServers": {
"falpha": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://agent.falpha.ai/mcp"]
}
}
}{
"mcpServers": {
"falpha": {
"url": "https://agent.falpha.ai/mcp"
}
}
}{
"servers": {
"falpha": {
"type": "http",
"url": "https://agent.falpha.ai/mcp"
}
}
}{
"context_servers": {
"falpha": {
"url": "https://agent.falpha.ai/mcp"
}
}
}{
"mcpServers": {
"falpha": {
"serverUrl": "https://agent.falpha.ai/mcp"
}
}
}{
"mcpServers": {
"falpha": {
"url": "https://agent.falpha.ai/mcp"
}
}
}name: fAlpha
version: 0.0.1
schema: v1
mcpServers:
- name: fAlpha
type: streamable-http
url: https://agent.falpha.ai/mcp{
"mcpServers": {
"falpha": {
"httpUrl": "https://agent.falpha.ai/mcp"
}
}
}{
"mcpServers": {
"falpha": {
"type": "http",
"url": "https://agent.falpha.ai/mcp"
}
}
}{
"mcpServers": {
"falpha": {
"url": "https://agent.falpha.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fagent.falpha.ai%2Fmcp&type=streamable_http&id=falpha&name=fAlpha
It answered our last check on 12 November 2026 in 388 ms. Over 4 checks since 27 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by falpha.ai and served from agent.falpha.ai, the vendor's own domain: https://agent.falpha.ai/mcp.
17, as returned by the server's own tools/list on 16 November 2026: falpha_analyst_desk, falpha_filings_scout, falpha_filings_scout_facts, falpha_fundamentals_desk, falpha_glossary, falpha_macro_desk, falpha_open_in_web, falpha_screener_desk, and 9 more.
It answered our last check on 12 November 2026 in 388 ms. Over 4 checks since 27 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agent.falpha.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.falpha. Endpoint host: agent.falpha.ai. ARD identifier: urn:air:ai.falpha:mcp:mcp.
First indexed 27 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.