QuantGeeks GEX

Option chain with GEX

quantgeeks_get_option_chain

Read-onlyIdempotent

Requires a QuantGeeks plan; not available without signing in (the call asks the user to sign in) or with a free account (the call says it needs a plan). The option chain for ONE expiration, compact: by default the 15 strikes on each side of spot, one row per strike with gex (QuantGeeks GEX, flow-based, the house value) first, gex_oi (open-interest GEX, for comparison) second, then call and put (bid, ask, iv, delta, open interest). The reply opens with the expiration (same-day or days out). Give center (a strike) or from_strike and to_strike to look away from spot, strikes (up to 40) to widen, time (HH:MM ET), expiration. A quote carries quote_age_s/stale when old and below_intrinsic when its bid is under intrinsic value: caveat or skip those. gex and gex_oi are readable strings such as +$2.0M or −$10.0M (quote them as written). For the GEX ladder alone, use quantgeeks_get_gex_ladder.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "symbol": "<symbol>"
    },
    "name": "quantgeeks_get_option_chain"
  }
}

Input Schema

Name	Required	Description
`date`	No	Session date, YYYY-MM-DD (US Eastern). Default: the newest session with stored data for the symbol (an overnight session dated today counts).
`time`	No	Time of day HH:MM US Eastern. Default: the latest available minute.
`range`	No	Alias of strikes.
`center`	No	Center the window on this strike instead of spot (e.g. 6550).
`symbol`	Yes	Ticker, e.g. SPX (maps to its 0DTE option root SPXW), SPY, QQQ, VIX.
`strikes`	No	Strikes on each side of spot (default 15, at most 40).
`to_strike`	No	Highest strike of a range to show.
`expiration`	No	Option expiration YYYY-MM-DD. Default: the session expiration.
`from_strike`	No	Lowest strike of a range to show (with to_strike).

Output Schema

Name	Required	Description	Default
`dte`	No
`date`	Yes
`rows`	Yes
`spot`	Yes
`as_of`	Yes
`units`	Yes
`access`	Yes
`notice`	Yes
`source`	Yes
`symbol`	Yes
`account`	No
`oi_asof`	No
`preview`	Yes
`gex_note`	No
`pro_plan`	No
`gex_as_of`	No
`truncated`	No
`expiration`	Yes
`window_note`	No
`coverage_note`	No
`truncated_more`	No
`expiration_kind`	No
`expiration_note`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 15, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare read-only/idempotent/non-destructive/openWorld=false; the description adds the real behavioral payload beyond them — gated by plan and sign-in, the default 15-strike window, the exact row layout, the reply opening with the expiration, and the `quote_age_s`/`stale`/`below_intrinsic` caveats. It also tells the agent that `gex`/`gex_oi` come back as readable strings like +$2.0M and should be quoted as written, which no annotation covers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The content is dense and mostly earns its place, but the opening availability sentence is padded with a redundant parenthetical ('not available without signing in (the call asks the user to sign in)...') and the core purpose is deferred behind it. The second sentence is a long run-on that packs the row layout, windowing controls, and parameters into one block, making it harder to scan than it needs to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a plan-gated, 9-parameter read tool with an output schema, nothing an agent needs is missing: auth prerequisites, default window width, window-repositioning parameters, string formatting of GEX values, data-quality caveats, and sibling routing are all covered. The breadth of the description matches the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3: every parameter is already documented in the schema. The description adds some interpretive value — `center` takes a strike, `strikes` widens the window to 40, `time` is HH:MM ET — but that mostly restates the schema rather than extending it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: the option chain for ONE expiration, compact, one row per strike with `gex` first then `gex_oi`, then call/put bid, ask, iv, delta, open interest. It explicitly separates itself from `quantgeeks_get_gex_ladder` ('For the GEX ladder alone, use...'), so an agent can pick the right tool without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use and when-not-to-use guidance: plan/sign-in prerequisites up front, 'Give `center` or `from_strike`/`to_strike` to look away from spot', '`strikes` (up to 40) to widen', and a named alternative for the GEX ladder. It also tells the agent to caveat or skip quotes flagged `stale`/`below_intrinsic`, which is actionable guidance rather than description filler.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All QuantGeeks GEX tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?