Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

fAlpha

REMOTE · AGENT.FALPHA.AI

Explainable model signals, drivers, news sentiment, SEC filings and macro data for US stocks.

Available components

+3 this week 82 Trust /100

Last scanned (17 hours ago)

Scores higher than 81% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Finance and Payments

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security74
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability76
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 4110 tokens (~228/item across 18 items; 17 tools + 1 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management80
  • Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
  • Supports UI / widget rendering.Pass
What we tested

Checks we ran (14)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol
  • Capabilities

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://agent.falpha.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=falpha.ai CN=Amazon RSA 2048 M01,O=Amazon,C=US 29 Sept 2026 14 Apr 2027 RSA 2048 SHA256-RSA 51f4d3baebbd5a5cf67bedb6293e100
SANs: falpha.ai, *.agent.falpha.ai, *.app.falpha.ai, *.falpha.ai
CN=Amazon RSA 2048 M01,O=Amazon,C=US (CA) CN=Amazon Root CA 1,O=Amazon,C=US 23 Aug 2022 23 Aug 2030 RSA 2048 SHA256-RSA 77312380b9d6688a33b1ed9bf9ccda68e0e0f
CN=Amazon Root CA 1,O=Amazon,C=US (CA) CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US 25 May 2015 31 Dec 2037 RSA 2048 SHA256-RSA 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of agent.falpha.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
falpha.ai. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agent.falpha.ai/mcp Verified 200
http (plaintext) http://agent.falpha.ai/mcp HTTPS enforced 301 https://agent.falpha.ai:443/mcp
MCP tools · 17 exposed · ~2,829 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
falpha_analyst_desk ~113

[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 fAlpha model. Covered universe only. Requires a connected fAlpha account.

NameTypeReqDescription
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_filings_scout ~157

[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.

NameTypeReqDescription
forms––SEC form types to return, e.g. ['10-K','8-K']. Defaults to 10-K, 10-Q and 8-K.
limitinteger–How many filings to return, up to 20.
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_filings_scout_facts ~144

[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 date. The filing is the source of record. Requires a connected fAlpha account; not included in the free trial.

NameTypeReqDescription
max_metricsinteger–How many of the six reported figures to return.
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_fundamentals_desk ~130

[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 trial.

NameTypeReqDescription
include_ratiosboolean–Include the TTM ratio snapshot alongside the company profile.
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_glossary ~84

[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.

NameTypeReqDescription
namestringyesThe term to define, e.g. EI, drivers, Sharpe, term structure.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_macro_desk ~140

[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 is returned. Requires a connected fAlpha account; not included in the free trial.

NameTypeReqDescription
series_id––One FRED series: DFF, CPIAUCSL, UNRATE, T10Y2Y or DGS10. Without it, the full bundle is returned.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_open_in_web ~60

[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.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_screener_desk ~279

[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 value are listed by ticker and the result says how many share it (`tied_at_top`). For questions like 'which tech names lean long'. Available on fAlpha Professional, Premium and Enterprise plans.

NameTypeReqDescription
directionstring–Restrict results to one side of the signal.
horizonstring–Holding period the reading is for, in trading days: hp5d (5), hp15d (15), hp2m (42, about two calendar months).
min_sharpe––Minimum realized Sharpe ratio a name needs to be included.
rank_bystring–Ranking measure: ei (the equity indicator, signed) or sharpe (the signal's realized Sharpe ratio).
regimestring–Market backdrop the model conditions on: neutral (no market view), bull or bear.
sector––GICS sector name, e.g. 'Information Technology'. Without it, every sector is included.
top_kinteger–How many names to return. Capped at 25.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_screener_desk_coverage ~156

[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.

NameTypeReqDescription
index––Index membership to filter the listing by, e.g. 'S&P 500'.
pageinteger–Page number when listing the universe.
page_sizeinteger–Rows per page when listing the universe, 1 to 100.
sector––GICS sector name to filter the listing by.
ticker––US-listed equity symbol to check. Without it, the covered universe is listed page by page.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_sentiment_desk ~140

[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 moved. Available without an account.

NameTypeReqDescription
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.
window_daysinteger–Window in days, 5 to 180. The score is the newest daily reading inside it.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_sentiment_desk_trend ~146

[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 questions about the trajectory rather than the latest score. Available without an account.

NameTypeReqDescription
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.
window_daysinteger–Window in days, 5 to 180. The score is the newest daily reading inside it.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_signal_desk_card ~233

[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 driver carrying the reading for the requested horizon and regime, the direction and EI at all three horizons for that regime (`horizons`), and the date the signal is for. The card view's Horizon and Regime controls switch the reading in place. For questions like 'what does the model say about NVDA'. Available without an account.

NameTypeReqDescription
horizonstring–Holding period the reading is for, in trading days: hp5d (5), hp15d (15), hp2m (42, about two calendar months).
regimestring–Market backdrop the model conditions on: neutral (no market view), bull or bear.
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_signal_desk_compare ~227

[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 ranks more than two names. Available without an account.

NameTypeReqDescription
horizonstring–Holding period the reading is for, in trading days: hp5d (5), hp15d (15), hp2m (42, about two calendar months).
regimestring–Market backdrop the model conditions on: neutral (no market view), bull or bear.
ticker_astringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.
ticker_bstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_signal_desk_curve ~205

[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 summary legs, each marked `mixed` when its points lean both ways. Carries no drivers; those are on the signal card. Past curves are stored daily from about May 2024, and the result carries the snapshot date served. Available on fAlpha Professional, Premium and Enterprise plans.

NameTypeReqDescription
as_of_date––Date, YYYY-MM-DD. Without it, the latest reading is returned.
regimestring–Market backdrop the model conditions on: neutral (no market view), bull or bear.
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_signal_desk_flips ~190

[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 fAlpha account.

NameTypeReqDescription
horizonstring–Holding period the reading is for, in trading days: hp5d (5), hp15d (15), hp2m (42, about two calendar months).
lookback_daysinteger–How far back to look for direction flips, in days.
regimestring–Market backdrop the model conditions on: neutral (no market view), bull or bear.
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_signal_desk_history ~196

[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 account.

NameTypeReqDescription
as_of_datestringyesDate, YYYY-MM-DD, on or before today. The signal stored for that date is returned.
horizonstring–Holding period the reading is for, in trading days: hp5d (5), hp15d (15), hp2m (42, about two calendar months).
regimestring–Market backdrop the model conditions on: neutral (no market view), bull or bear.
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.

Structured output declared, but exposes no named fields.

No examples provided.

falpha_signal_desk_performance ~229

[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 like 'was the model right on TSLA this quarter'. Requires a connected fAlpha account.

NameTypeReqDescription
benchmarkstring–Index the excess return is measured against.
frmstringyesStart of the range, YYYY-MM-DD.
horizonstring–Holding period the reading is for, in trading days: hp5d (5), hp15d (15), hp2m (42, about two calendar months).
regimestring–Market backdrop the model conditions on: neutral (no market view), bull or bear.
tickerstringyesUS-listed equity symbol in fAlpha's covered universe, e.g. NVDA. falpha_screener_desk_coverage reports whether a symbol is covered.
tostringyesEnd of the range, YYYY-MM-DD.

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the fAlpha MCP server?

fAlpha is a hosted endpoint at https://agent.falpha.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · agent.falpha.ai

# add to Claude Code
claude mcp add --transport http ai-falpha-mcp 'https://agent.falpha.ai/mcp'
Common questions

What is the fAlpha MCP server?

fAlpha is an MCP server listed in the public MCP registry as ai.falpha/mcp. Explainable model signals, drivers, news sentiment, SEC filings and macro data for US stocks. This page covers its hosted endpoint (https://agent.falpha.ai/mcp).

Is the fAlpha MCP server safe to use?

fAlpha scores 82 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the fAlpha MCP server expose?

fAlpha exposes 17 tools: falpha_signal_desk_card, falpha_signal_desk_compare, falpha_signal_desk_history, falpha_signal_desk_performance, falpha_signal_desk_flips, and 12 more. Their descriptions and schemas cost roughly 2,829 tokens of context every time the server is loaded.

Does the fAlpha MCP server require authentication?

No. We connected to fAlpha without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the fAlpha MCP server still maintained?

fAlpha is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the fAlpha MCP server?

VerifyMCP ran 14 checks on fAlpha, covering TLS certificate, Authorization, HTTPS, HSTS header and 10 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.