FlashAlpha MCP server
Commit Nov 9, 2026Connect AI assistants to real-time and historical options market analytics including gamma exposure, dealer positioning, and volatility surfaces.
Also known as FlashAlpha-lab/flashalpha-mcp, flashalpha-mcp
- Stars
- 1
- Tools
- 84
- Downloads, 30 days
- —
- Latest version
- 1.6.3
- Last commit
- Nov 9, 2026
- License
- MIT
What is FlashAlpha MCP?
FlashAlpha connects AI assistants to real-time and historical options market analytics including gamma exposure, dealer positioning, and volatility surfaces. It exposes 84 tools, such as get_stock_quote, get_tickers, get_symbols.
Summary generated from the project's README
About FlashAlpha MCP server
FlashAlpha provides a remote MCP server that connects AI assistants to live and historical options market analytics. It offers over 70 tools covering complex metrics such as gamma exposure, dealer positioning, volatility surfaces, and 0DTE intraday flow. Developers can use this to equip clients like Claude Desktop, Cursor, or Windsurf with deep market intelligence, including Black-Scholes greeks and actionable strategy signals.
The server supports two primary authentication methods depending on the client setup. Self-hosted clients use an apiKey passed as a tool parameter, while remote hosts like Perplexity or ChatGPT use OAuth 2.1 with PKCE. To help users focus on specific trading styles, the server provides persona-scoped endpoints for specialized toolsets such as Gamma Exposure, Premium Selling, or Volatility Relative Value. It also includes a historical replay feature that allows for backtesting with minute-resolution data dating back to April 2018.
What you can do with it
- 1Analyze intraday 0DTE flowAsk your AI assistant to examine real-time 0DTE intraday heatmaps and hedge flow for specific symbols.
- 2Evaluate options selling riskDetermine if it is a safe day to sell options on major ETFs using the sell-window signal.
- 3Backtest historical volatility strategiesUse historical replay to test options strategies against market data from several years ago.
- 4Screen for earnings volatilityIdentify upcoming earnings events and analyze expected moves or IV crush potential.
Written from the project's README. Every use case is checked against a quote from it.
How to install FlashAlpha MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall FlashAlpha MCP in Claude Code
$ claude mcp add --transport http flashalpha-mcp https://lab.flashalpha.com/mcpInstall FlashAlpha MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"flashalpha-mcp": {
"url": "https://lab.flashalpha.com/mcp"
}
}
}Install FlashAlpha MCP in VS Code
.vscode/mcp.json
{
"servers": {
"flashalpha-mcp": {
"type": "http",
"url": "https://lab.flashalpha.com/mcp"
}
}
}Install FlashAlpha MCP in VS Code CLI
$ code --add-mcp '{"name":"flashalpha-mcp","type":"http","url":"https://lab.flashalpha.com/mcp"}'Install FlashAlpha MCP in Codex
$ codex mcp add flashalpha-mcp --url https://lab.flashalpha.com/mcpInstall FlashAlpha MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.flashalpha-mcp] url = "https://lab.flashalpha.com/mcp"
Install FlashAlpha MCP in Gemini CLI
$ gemini mcp add -s user --transport http flashalpha-mcp https://lab.flashalpha.com/mcpInstall FlashAlpha MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"flashalpha-mcp": {
"url": "https://lab.flashalpha.com/mcp",
"type": "http"
}
}
}FlashAlpha MCP tools 84
Detected from the READMEget_stock_quoteget_tickersget_symbolsget_option_chainget_option_quoteget_accountget_gexget_dexget_vexget_chexget_levelsget_exposure_summary
Show all 84 toolsShow fewer tools
get_exposure_sheetget_term_structureget_exposure_basketget_oi_diffget_narrativeget_max_painget_zero_dteget_surfaceget_svi_paramsget_volatilityget_advanced_volatilityget_expected_moveget_skew_termget_spot_vol_correlationget_realized_volget_volatility_forecastget_liquidityget_dispersionget_vix_stateget_universeget_vrpget_vrp_historyget_stock_summarycalculate_greekssolve_ivcalculate_kellyget_flow_liveget_flow_summaryget_flow_levelsget_flow_signalsget_flow_pin_riskget_flow_dealer_riskget_dealer_premiumget_option_flowget_stock_flowget_flow_scanget_zero_dte_flowflow_anomalyexpiry_positioningzero_dtedealer_regimevol_carryyield_enhancementsurface_anomalyskewterm_structuretail_pricingsell_windowget_earningsget_earnings_calendarget_earnings_screenerpost_structure_pnlpost_structure_greekspost_screenerget_screener_fieldsget_historical_gexget_historical_dexget_historical_vexget_historical_chexget_historical_levelsget_historical_exposure_summaryget_historical_narrativeget_historical_zero_dteget_historical_max_painget_historical_volatilityget_historical_advanced_volatilityget_historical_vrpget_historical_surfaceget_historical_stock_quoteget_historical_option_quoteget_historical_stock_summaryget_historical_coverage
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachableflashalpha-lab/flashalpha-mcp is public and reachablegithub.com/flashalpha-lab/flashalpha-mcp ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-09github.com/flashalpha-lab/flashalpha-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model84 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 819 msPass
README
View on GitHubFlashAlpha MCP Server — Real-Time Options Analytics for AI Assistants
Connect Claude, ChatGPT, Cursor, Windsurf, or any MCP-compatible AI assistant to live options market data. 70+ tools covering gamma exposure (GEX), delta/vanna/charm exposure, max pain, key dealer-positioning levels, IV surfaces (SVI parameters), VRP analytics + history, expected move, volatility skew & term structure, spot-vol correlation, dispersion / index-vs-component vol arbitrage, liquidity scoring, VIX macro state, the tradeable universe, exposure sheet / term-structure / multi-symbol basket / open-interest diff, Black-Scholes greeks, Kelly sizing, real-time options & stock order flow (sweeps, blocks, dealer premium), 0DTE intraday flow (snapshot, time series, hedge flow, heatmap, strike flow), 10 actionable options-strategy signals (flow-anomaly, expiry-positioning, 0DTE, dealer-regime, vol-carry, yield-enhancement, surface-anomaly, skew, term-structure, tail-pricing), a full earnings analytics suite (calendar, expected move, history, IV crush, VRP, dealer positioning, strategies, screener), multi-leg structure P&L + greeks calculators, a multi-factor options screener with field taxonomy, plus minute-resolution historical replay back to April 2018 for backtesting.
What is this repo
Documentation, setup snippets, and server.json metadata for the FlashAlpha remote MCP server. The server itself runs at https://lab.flashalpha.com/mcp (and /mcp-oauth for OAuth-authenticated clients) — its source is not open. Use this repo as a reference for how to wire FlashAlpha into your AI client of choice.
Server URLs
Two endpoints, identical tool catalog, different authentication:
| Endpoint | Auth | When to use |
|---|---|---|
https://lab.flashalpha.com/mcp |
apiKey tool parameter |
Self-hosted clients: Claude Desktop, Claude Code CLI, Cursor, Windsurf, VS Code Copilot |
https://lab.flashalpha.com/mcp-oauth |
OAuth 2.1 + PKCE + DCR (RFC 7591) | Claude Connector Directory, ChatGPT Apps, Perplexity custom connectors, any host that requires OAuth-authenticated remote MCP |
- Transport: Streamable HTTP
- Protocol version: MCP 2025-06-18
- OAuth discovery:
https://lab.flashalpha.com/.well-known/oauth-protected-resource(RFC 9728) - Authorization server:
https://flashalpha.com/oauth
Persona-scoped endpoints
Each base endpoint also has nine persona variants that expose a curated subset of the catalog for a specific trading style. Same auth model — /mcp/<persona> takes the apiKey parameter, /mcp-oauth/<persona> uses OAuth. Point your client at a persona URL instead of the base URL to load just that toolset.
| Persona | API-key URL | OAuth URL |
|---|---|---|
| 🧲 Gamma Exposure | https://lab.flashalpha.com/mcp/gex |
https://lab.flashalpha.com/mcp-oauth/gex |
| 🎯 Directional | https://lab.flashalpha.com/mcp/directional |
https://lab.flashalpha.com/mcp-oauth/directional |
| 💵 Premium Seller | https://lab.flashalpha.com/mcp/premium |
https://lab.flashalpha.com/mcp-oauth/premium |
| ⚖️ Spreads & Condors | https://lab.flashalpha.com/mcp/spreads |
https://lab.flashalpha.com/mcp-oauth/spreads |
| ⚡ 0DTE | https://lab.flashalpha.com/mcp/0dte |
https://lab.flashalpha.com/mcp-oauth/0dte |
| 📈 Dealer-Positioning Swing | https://lab.flashalpha.com/mcp/swing |
https://lab.flashalpha.com/mcp-oauth/swing |
| 🌊 Volatility / Relative Value | https://lab.flashalpha.com/mcp/volarb |
https://lab.flashalpha.com/mcp-oauth/volarb |
| 💻 Quant / Systematic | https://lab.flashalpha.com/mcp/quant |
https://lab.flashalpha.com/mcp-oauth/quant |
| 📅 Earnings | https://lab.flashalpha.com/mcp/earnings |
https://lab.flashalpha.com/mcp-oauth/earnings |
Quick Setup (self-hosted clients → /mcp + apiKey)
Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"flashalpha": {
"type": "http",
"url": "https://lab.flashalpha.com/mcp"
}
}
}
Claude Code CLI
claude mcp add flashalpha --transport http https://lab.flashalpha.com/mcp
claude mcp list
Cursor
Settings → MCP → Add server:
{
"flashalpha": {
"transport": "http",
"url": "https://lab.flashalpha.com/mcp"
}
}
VS Code (Copilot / Continue)
.vscode/mcp.json or user settings:
{
"servers": {
"flashalpha": {
"type": "http",
"url": "https://lab.flashalpha.com/mcp"
}
}
}
Windsurf
Cascade settings → MCP Servers:
{
"flashalpha": {
"transport": "http",
"url": "https://lab.flashalpha.com/mcp"
}
}
Perplexity (Pro/Max/Enterprise)
Settings → Connectors → + Custom connector → Remote
- URL:
https://lab.flashalpha.com/mcp-oauth - Auth: OAuth (walks the consent flow at
flashalpha.com/oauth/login)
Authentication
/mcp (apiKey)
Every tool call takes apiKey as a string parameter. Get a free key at flashalpha.com.
apiKey: "fa_your_key_here"
Key passes per-call rather than in a header so it works uniformly across all MCP clients without transport-level configuration.
/mcp-oauth (Bearer)
OAuth 2.1 + PKCE + Dynamic Client Registration (RFC 7591). The client registers itself, walks the authorization-code + PKCE flow, and presents a Bearer JWT on each request. No apiKey parameter needed — the server resolves the user's account from the OAuth identity and forwards the API key internally for upstream /v1/* calls. Same per-user tier gating and rate limits apply as the apiKey flow.
Discovery + endpoints:
| RFC 9728 protected-resource metadata | https://lab.flashalpha.com/.well-known/oauth-protected-resource |
| OIDC discovery | https://flashalpha.com/oauth/.well-known/openid-configuration |
| JWKS | https://flashalpha.com/oauth/.well-known/jwks |
| Dynamic Client Registration | POST https://flashalpha.com/oauth/register |
| Authorization endpoint | https://flashalpha.com/oauth/authorize |
| Token endpoint | https://flashalpha.com/oauth/token |
| Scope | flashalpha.mcp |
sell-window: should you sell options today?
Option sellers get wiped out on a few bad days. sell-window tells you which days to stay out, and on the days it says sell, it hands you the trades: which expiry, which strikes and how to exit. Every session, for SPY, QQQ and IWM. More than 5 million backtests led to this one endpoint.
On MCP, call get_strategy with signal set to sell_window and symbol set to SPY, QQQ or IWM. Ask your assistant:
- "Should I sell options on SPY today?"
- "Which strikes does sell-window pick for QQQ this week?"
- "Is today a skip day for IWM 0DTE?"
| Backtest, 2018 to 2026 | Following sell-window | Selling the same trades every day |
|---|---|---|
| Max drawdown at the same trade size | $255k | $959k |
| Worst month at the same trade size | -$171k | -$307k |
| Sharpe ratio | 0.76 | 0.61 |
| Total P&L at the same max drawdown | $3.55M | $2.32M |
| Worst day at the same max drawdown | -$258k | -$385k |
Cut the risk or earn more. Keep your trade size and the deepest drawdown falls 73%. Or size up about 3.8 times, until the deepest drawdown matches, and you earn 53% more. These are two separate choices, not one result.
Plans: Live answers need Basic or higher through November 2026, and Growth or higher from December 1, 2026. Backtesting any past session needs Alpha or higher.
Read more: API docs | trading guide | every backtested trade | sell-window in depth | plans | live forward test on Discord
Backtest on SPY, QQQ and IWM, January 2018 to October 2026, at halfway fills and $1 per contract. At one contract set per signal, following it made $945,541 on 20,883 trades; selling every day made $2,321,150 on 56,975. At 3.76 times the contracts, both fell $958,924 at their deepest, and the worst month was -$642,135 against -$307,241. Past results do not guarantee future returns, and short options can lose more than the premium collected. The skip call applies to new trades, so it cannot protect open positions from a sudden shock. This is data, not investment advice.
Data provenance: data_as_of
Every tool result carries the API's response envelope: data_as_of, reporting when each
upstream feed last delivered to the node that answered, and endpoint_version identifying
the deployment that produced it.
| Field | Feed | Expected cadence |
|---|---|---|
node |
Which node answered | Nodes hydrate independently |
equity_feed |
Equity and ETF spot quotes | seconds, during market hours |
equity_options_feed |
Equity and ETF option quotes | seconds, during market hours |
index_feed |
Index spot (SPX, RUT, VIX and the other index roots) | seconds, during market hours |
index_options_feed |
Index option quotes | seconds, during market hours |
futures_feed |
Futures prices | seconds, during the futures session |
futures_options_feed |
Futures option quotes | seconds, during the futures session |
flow_feed |
Classified options and stock trade tape | seconds, during market hours |
oi_feed |
Settled open interest | daily, dated to the prior 16:00 ET close |
macro_feed |
VIX, VVIX, SKEW, MOVE, SPX, Fear & Greed | minutes; reports its OLDEST component |
This matters more for an MCP client than for a normal SDK caller: a model reading a tool result has no other way to tell a current figure from a stale one, and will otherwise present both with equal confidence.
How to read it
- Check the feeds the tool depends on. A GEX call on an equity is answered from
equity_feed,equity_options_feedandoi_feed.futures_feedbeingnullin that result says nothing about the answer. - Compare against the cadence, not the clock.
oi_feedat the previous session's close is correct: settled open interest is published once per session, so on a Monday the newest figure that exists is Friday's. An options feed an hour behind during the regular session is not correct. nullmeans "not seen on this node", not "broken". A node that has never been asked for a futures symbol has never opened that feed.- Spot and options are separate on purpose. They arrive over different pipes and can fail independently, so an index chain can be current while the index level behind it is not.
- It evidences feed activity, not per-contract freshness. An illiquid strike may not have quoted for hours while its feed is healthy.
data_as_ofis notas_of.as_ofis response-generation time or the newest contract in the payload, depending on the endpoint.data_as_ofdescribes the feeds behind it.
Historical replay tools carry a second object, archive_as_of, in the same shape: the
vintage of the archive rows actually replayed for the timestamp requested. Their
every feed in data_as_of is null, because a replay node reads the archive and consumes no live
feed.
Full reference: https://flashalpha.com/docs/lab-api-overview#response-envelope and the methodology whitepaper at https://flashalpha.com/methodology#freshness-reporting.
Tool Catalog (70+ tools)
Tool names below are the exact strings sent via tools/call — snake_case, not the PascalCase C# method names. Copy verbatim.
Live tools
Market Data (6)
| Tool | Description |
|---|---|
get_stock_quote |
Real-time stock quote (bid, ask, mid, last) |
get_tickers |
List/search available tickers |
get_symbols |
Full list of supported underlying symbols |
get_option_chain |
Available expirations + strikes metadata |
get_option_quote |
Live option quote: bid, ask, mid, IV, greeks, OI, volume (expiry, strike, type) |
get_account |
Plan, daily quota, usage today, remaining calls |
Exposure Analytics (13)
| Tool | Description |
|---|---|
get_gex |
Gamma exposure (GEX) by strike — call/put walls, gamma flip (expiration, min_oi) |
get_dex |
Delta exposure (DEX) by strike — net dealer delta (expiration) |
get_vex |
Vanna exposure (VEX) by strike — dealer hedging response to vol moves (expiration) |
get_chex |
Charm exposure (CHEX) by strike — time-decay-driven flows (expiration) |
get_levels |
Gamma flip, call/put walls, max pain, highest OI strike, 0DTE magnet |
get_exposure_summary |
Net GEX/DEX/VEX/CHEX, regime, hedging estimates, top strikes, 0DTE breakdown |
get_exposure_sheet |
Per-strike greeks exposure sheet (GEX/DEX/VEX/CHEX side by side) with expiration, min_oi filters |
get_term_structure |
Exposure term structure — net GEX/DEX/VEX/CHEX bucketed by expiry/DTE |
get_exposure_basket |
Aggregate dealer exposure across a multi-symbol basket (symbols required, optional weights) |
get_oi_diff |
Day-over-day open-interest change by strike — top OI builders/unwinds (topN) |
get_narrative |
Verbal analysis: regime, levels, dealer positioning, implications |
get_max_pain |
Max pain strike, pain curve, put/call OI ratio, dealer alignment, pin probability (expiration) |
get_zero_dte |
0DTE analytics: intraday gamma, time-decay acceleration, pin risk, hedging pressure (expiry, strike_range) |
Volatility & Pricing (19)
| Tool | Description |
|---|---|
get_surface |
Live 50×50 implied-volatility surface grid over (tenor, log-moneyness) |
get_svi_params |
SVI (stochastic-volatility-inspired) calibrated surface parameters per tenor (Alpha) |
get_volatility |
ATM IV, realized vol (5/10/20/30d), VRP, 25-δ skew, term structure, GEX-by-DTE |
get_advanced_volatility |
SVI parameters, forward prices, variance surface, arbitrage flags, vanna/charm/volga surfaces, variance-swap fair values (Alpha) |
get_expected_move |
Straddle-implied expected move (1σ) by expiry — bands, % move, breakevens (expiry) |
get_skew_term |
Volatility skew across strikes and term structure across expiries in one call |
get_spot_vol_correlation |
Realized spot-vol correlation / leverage effect for the underlying |
get_realized_vol |
Realized-vol estimators (close-to-close, Parkinson, Garman-Klass, Rogers-Satchell, Yang-Zhang) at 10/20/30-day windows (Alpha) |
get_volatility_forecast |
Volatility forecasts: EWMA, HAR-RV, GARCH with multi-horizon term structure (dist = student_t default, gaussian) (Alpha) |
get_liquidity |
Options-chain liquidity score: spreads, depth, volume/OI quality |
get_dispersion |
Index-vs-component dispersion / correlation vol-arbitrage (index, symbols required, weights, horizon_days) (Alpha) |
get_vix_state |
VIX macro state: level, term structure, percentile, contango/backwardation regime |
get_universe |
Tradeable universe ranked by liquidity/coverage (sort, limit) |
get_vrp |
Volatility risk premium dashboard: IV vs RV, percentiles, regime, strategy scores (date) |
get_vrp_history |
Historical VRP time series for charting + backtesting (days) |
get_stock_summary |
One-call combined summary: price, IV, VRP, skew, term, exposure, macro context |
calculate_greeks |
Black-Scholes greeks (Δ, Γ, Θ, ν, ρ, vanna, charm, speed, zomma, color) |
solve_iv |
Solve implied volatility from market price (BSM inversion) |
calculate_kelly |
Kelly criterion optimal sizing for an option trade |
Order Flow — Options & Stocks (real-time, simulation-aware)
| Tool | Description |
|---|---|
get_flow_live |
Headline live flow bundle in one call: effective OI state, live levels, live GEX/DEX totals, pin-risk score, dealer-risk summary. view='gex' returns the full simulation-aware live GEX surface, view='dex' live DEX, view='oi' the raw OI simulator state |
get_flow_summary |
Net signed options premium, call/put flow, sweep vs block breakdown (expiry) |
get_flow_levels |
Flow-derived support/resistance and dealer hedging levels (expiry) |
get_flow_signals |
Scored actionable flow signals — intent, structure, conviction (minScore, intent, structure, windowMinutes, limit, expiry) |
get_flow_pin_risk |
Real-time pin-risk estimate from live flow + positioning (expiry) |
get_flow_dealer_risk |
Live dealer gamma/delta risk from intraday flow (expiry) |
get_dealer_premium |
Dealer-side options premium attribution (sold/bought) over a window (windowMinutes, expiry) |
get_option_flow |
Raw recent option prints, blocks, sweeps, cumulative & history (minSize, minutes, limit, expiry) |
get_stock_flow |
Raw recent stock prints, blocks, bars, cumulative & history (resolution, minSize, minutes, limit) |
get_flow_scan |
Cross-symbol flow leaderboards & outliers (n, limit, minTrades, windowMinutes) |
0DTE Intraday Flow
| Tool | Description |
|---|---|
get_zero_dte_flow |
0DTE flow snapshot: live exposure + net flow direction by strike, plus intraday series, hedge flow, heatmap, and strike-flow views (bar, minutes, side, metric, mode) |
Strategy Signals (11 signals via get_strategy)
One tool, parameterized by signal, returning the uniform strategy-decision envelope (decision, score, confidence, regime, best_structures[], metrics, risk_flags[], why[], avoid_if[], data_quality).
signal value |
Description |
|---|---|
flow_anomaly |
Directional options-flow imbalance → matching short vertical spread (expiry) |
expiry_positioning |
Dealer expiry positioning → iron-condor / butterfly candidates (expiry, minOpenInterest, wingWidth) |
zero_dte |
0DTE intraday setup → defined-risk spreads (expiry, minOpenInterest, wingWidth) |
dealer_regime |
Gamma regime read (long/short gamma) → directional bias (expiry) |
vol_carry |
Vol carry / theta harvest → short-premium structures (targetShortDelta, maxWidth, minCredit, ...) |
yield_enhancement |
Covered-call / cash-secured-put yield (targetDelta, structure, excludeEarningsBeforeExpiry, ...) |
surface_anomaly |
IV-surface mispricing / arbitrage candidates (expiry) |
skew |
Skew steepness/richness → risk-reversal / ratio ideas (expiry) |
term_structure |
Calendar / diagonal opportunities from term-structure shape |
tail_pricing |
Tail-risk richness → cheap-convexity / hedge candidates (expiry) |
sell_window |
Should you sell options today? Sell, skip or unavailable per listed expiry for SPY, QQQ and IWM, with the trades to place on a sell. Its own response shape, not the envelope |
Earnings Analytics
| Tool | Description |
|---|---|
get_earnings |
Per-symbol earnings analytics: expected move, history, IV crush, VRP, dealer positioning, and strategies (parameterized) |
get_earnings_calendar |
Upcoming earnings calendar with expected moves (days, symbols, importance) |
get_earnings_screener |
Rank earnings names by IV-crush edge / VRP / expected move (sort, limit, days, min_importance) |
Structures (multi-leg, pure-math)
| Tool | Description |
|---|---|
post_structure_pnl |
Multi-leg structure P&L curve across an underlying range (legs[], minUnderlying, maxUnderlying, points) |
post_structure_greeks |
Aggregate greeks for a multi-leg structure (legs[] with expiry+impliedVol, spot, today, rate, dividendYield) |
Screener
| Tool | Description |
|---|---|
post_screener |
Multi-factor options screener: universe, filters, formulas, sort, select, limit, offset |
get_screener_fields |
Screener field taxonomy — every filterable/selectable field and type |
Futures (CME)
FlashAlpha serves the full options-analytics stack for CME futures across six complexes - equity index (ES=F, NQ=F, RTY=F, YM=F, MES=F, MNQ=F), metals (GC=F gold, SI=F silver), energy (CL=F crude oil, NG=F natural gas), the Treasury curve (ZT=F, ZF=F, ZN=F, TN=F, ZB=F, UB=F), grains (ZC=F corn, ZS=F soybeans, ZW=F wheat) and crypto (BTC=F bitcoin). Options-on-futures are priced with Black-76 (forward-priced) and each root carries its own CME contract multiplier, so notionals and dollar gamma are in real dollars. Note the quote conventions: Treasuries are quoted in points of par and grains in cents, so their multipliers are the contract size divided by 100. Everything that works for an equity works for futures: gamma exposure (GEX), DEX, VEX, CHEX, key levels, max pain, the IV surface, exposure summary, narrative, and live flow.
Call any live tool with the futures symbol — e.g. get_gex with symbol: "ES=F" returns gamma exposure for the E-mini S&P 500 future:
{ "symbol": "ES=F" }
Use the =F suffix - bare ES/NQ are equities, not futures. In raw REST paths URL-encode the = as %3D (e.g. GET /v1/exposure/gex/GC%3DF); SDK methods take the plain string "GC=F". Futures symbols require the Growth plan or higher. Historical replay for futures is coming; live analytics are available now.
Historical replay tools (17, Alpha tier)
All historical tools take a required at=YYYY-MM-DDTHH:mm:ss parameter (ET wall-clock) and replay the matching live analytic at any minute since 2017-01-03. Response shapes are identical to the live counterparts — backtesting code that parses live responses works on historical with a tool-name swap.
| Tool | Mirrors |
|---|---|
get_historical_gex |
get_gex |
get_historical_dex |
get_dex |
get_historical_vex |
get_vex |
get_historical_chex |
get_chex |
get_historical_levels |
get_levels |
get_historical_exposure_summary |
get_exposure_summary |
get_historical_narrative |
get_narrative |
get_historical_zero_dte |
get_zero_dte |
get_historical_max_pain |
get_max_pain |
get_historical_volatility |
get_volatility |
get_historical_advanced_volatility |
get_advanced_volatility |
get_historical_vrp |
get_vrp |
get_historical_surface |
get_surface |
get_historical_stock_quote |
get_stock_quote |
get_historical_option_quote |
get_option_quote |
get_historical_stock_summary |
get_stock_summary |
get_historical_coverage |
List symbols backfilled with coverage windows and gaps — call first to check whether (symbol, date range) is queryable |
Note: The multi-factor options screener is now exposed as the post_screener MCP tool (with get_screener_fields for the field taxonomy), in addition to POST /v1/screener. The historical replay tools cover analytics only; for raw historical tick data use the historical REST endpoints directly.
FlashAlpha MCP questions
How do I add FlashAlpha MCP to Claude Code?
Run claude mcp add --transport http flashalpha-mcp https://lab.flashalpha.com/mcp in your terminal. Add --scope user to make it available in every project.
How do I add FlashAlpha MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does FlashAlpha MCP provide?
It exposes 84 tools, including get_stock_quote, get_tickers, get_symbols, get_option_chain, get_option_quote.
What kind of options analytics does FlashAlpha provide?
It provides over 70 tools covering gamma exposure (GEX), delta/vanna/charm exposure, max pain, dealer positioning, IV surfaces, VRP analytics, and 0DTE intraday flow.
How can I authenticate with the FlashAlpha MCP server?
You can use an apiKey passed as a tool parameter for self-hosted clients like Claude Desktop, or use OAuth 2.1 with PKCE for remote clients like ChatGPT Apps.
Does FlashAlpha offer historical data for backtesting?
Yes, it provides minute-resolution historical replay dating back to April 2018.
Can I filter tools by specific trading styles?
Yes, the server offers persona-scoped endpoints for styles such as Gamma Exposure, Directional, Premium Seller, 0DTE, and Quant/Systematic.