Skip to main content
Glama
celineycn

Quant Data MCP Server

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
QUANTDATA_API_KEYNoOptional Quant Data API key (starts with qd_). Without it an anonymous source gets one complete first-look response per UTC day. A free key, delivered by email with no account or card, gives the four market tools 10 shared successful calls per UTC day; paid access removes the daily limit.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
quantdata_request_free_api_keyA

Send a free qd_ API key to an email address. No account, card, payment or GUI is required. The key covers all four market-data tools, sharing 10 successful calls per UTC day. The raw key is delivered only to the inbox and is never returned in this tool result. Ask the user for the email address before calling. Set marketing_opt_in to true only when the email owner explicitly asks to receive occasional product updates; it defaults to false and is not required for the key. A true value stays pending until the recipient replies SUBSCRIBE to the key email.

quantdata_day_typeA

Day-type probabilities for the trading session in progress: a calibrated distribution over five classes (trending up, trending down, range, trending range, reversal) from a model trained on S&P 500 futures 5-minute bars. Answers 'what kind of day is this so far'. Descriptive statistics about how comparable past sessions resolved — not a forecast of today and not a recommendation. Check session_is_live before calling the read 'today', and check bars: fewer than 18 (90 minutes) means the distribution is provisional.

quantdata_weis_waveA

Weis Wave volume-price structure: price grouped into waves with volume summed per wave, plus which of five classical volume-price events have fired. Each event carries the win rate measured for it on sixteen years of S&P 500 futures data, including the two that came out REVERSED against the tradition. Answers 'is there volume behind this move'. Quote the measured reference numbers rather than the folklore. Needs real exchange volume: spot FX has none — use CME currency futures (6E=F) instead. Use session='full' to match the published reference-rate window, or the default 'rth' for a regular-session-only read.

quantdata_max_painA

Options max pain per expiration, computed from open interest alone: the strike at which option buyers lose the most in aggregate if the underlying settled there. Pure arithmetic — no pricing model, no volatility assumption, so anyone with the same chain gets the same number. Also returns put/call ratio and the heaviest call and put open-interest strikes. Returns every expiration inside 45 days rather than picking one, because the figure is per-expiration and the near- and far-dated values routinely disagree. US listed stocks and ETFs only: cash-settled index options (SPX, NDX, RUT, VIX) return an error — use SPY, QQQ, IWM. Open interest settles overnight, so this describes the prior session's positioning; report as_of and spot_date alongside the number.

quantdata_gammaA

Estimated dealer gamma exposure (GEX) for a US listed stock or ETF: net and gross GEX, the zero gamma (flip) level and the heaviest strikes. Unlike max pain this is a Black-Scholes ESTIMATE — zero rate, zero dividend, implied volatility solved from end-of-day quotes, and the convention that dealers are long every call and short every put. Keep that framing when reporting it. A null flip is not an error: check flip_status — 'no_sign_change_within_10pct' means net gamma keeps one sign across the whole traded range, which is a state worth reporting. US listed stocks and ETFs only, with a liquid chain: cash-settled index options (SPX, NDX, RUT, VIX) return an error — use SPY, QQQ, IWM instead. Reads the prior session's settled open interest and cannot update intraday whatever the clock says, so report as_of and spot_date with the number.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/celineycn/quantdata-plugin'

If you have feedback or need assistance with the MCP directory API, please join our Discord server