What do I get with Agent Access?

Your AI gets the full GammaRips pool every trading night: roughly 40 to 50 calls with deep books, one per bullish name among the 100 most liquid US stocks, each with its thesis, technicals, catalyst, and contract detail. It also gets fresh liquidity checks, earnings dates, the exit lab (how often past pool contracts hit each profit level and each stop, plus a score for any target and stop you choose), contract replay, regime context, and the methodology playbooks. That is 9 tools, $29/mo after a 30-day free trial. Everything human-readable on gammarips.com stays free.

What does a trade plan look like?

Ask your AI for a trade and it comes back with 1 to 3 candidates from the pool that pass the liquidity and earnings checks. Each one has the contract, why it passed, an entry (about 10:00 ET, a limit order near the mid), a target and a stop set from the exit lab history, the maximum loss, and a size that keeps that loss inside your risk budget. If nothing passes, you get a reasoned no-trade with the check that failed. You decide, and you place the order in your own brokerage. GammaRips never places trades.

Which AIs work with this?

Claude (Claude Code, Claude Desktop, and claude.ai), ChatGPT, Cursor, and Codex, plus Gemini CLI, Grok, and any other client that speaks MCP (Model Context Protocol). Claude Code, Codex, Cursor, and Gemini CLI send your API key in a header. A chat client that cannot send a header, such as ChatGPT, claude.ai, or Grok, adds https://mcp.gammarips.com/pro and signs in instead. Both routes reach the same 9 tools. The install section on this page has the exact steps for each client.

What does the free trial include?

Full Agent Access for 30 days: every pro tool, the full pool, the exit lab, and trade plans in your AI from minute one. Card on file, no charge during the trial. Cancel before day 30 and you pay nothing. After that it is $29/mo, the founding price, which the first 100 subscribers keep for as long as they stay subscribed.

Why don't you just tell me what to buy?

Your AI builds a plan for your account and your risk: your size, your stop, your budget. Shared picks get crowded. When every subscriber piles into the same contract, the fills get worse for all of them. A plan your AI builds from the data is yours alone. That is why GammaRips has no pick endpoint.

Where's the track record?

On the scorecard. Claude Code trades the GammaRips pool with real money in an agent account: 11 of 14 trades closed at a profit, +$2,263 net realized, every trade counted (entries Sep 14 to Oct 2, 2026). The pool history is public too. Of 793 pool contracts that have expired (scan dates Aug 24 to Oct 1, 2026), 73.0% hit +20%, 54.6% hit +50%, and 37.1% hit +100% before expiration. Within 3 trading days, 36.3% hit +50% (N=1,574). Both update daily. Past results: real-money trades and historical pool data. Educational only. Not investment advice.

How is the pool curated?

Every trading night the engine ranks about 3,500 optionable US stocks by liquidity. A name must trade 3M+ shares that session and carry 25 or more listed strikes, then the top 100 by combined chain dollar volume and share volume go through. The engine keeps the bullish names and chooses one out-of-the-money call in each on contract liquidity. That gives a pool of roughly 40 to 50 contracts, each with its flow data, technicals, news context, and contract detail. Every field is point-in-time, so nothing your AI sees contains information that was not knowable at scan time. Earnings dates are not screened out of the pool, so your AI checks each candidate's earnings date before it plans a trade.

Is this financial advice?

No. GammaRips is a data vendor. We publish market data, methodology, and research. We never see your account, never manage money, and never make personalized recommendations, and the MCP has no 'what should I buy' endpoint. The plan your AI builds is your own analysis of GammaRips data, and you decide. For personalized investment advice, work with a licensed advisor.

Do I need the harness?

No. Any MCP client can call the tools directly, and your AI can build a trade plan in Claude, ChatGPT, Cursor, or Codex as is. The harness is a free, open-source repo for traders who want a daily loop: a morning screen, a journal, and an after-the-close review. Clone it from github.com/DevDizzle/gammarips-harness. Its screen uses the pro tools, so it runs on Agent Access.

Can't I just scrape the free site?

The website shows the pool and the daily reports free, and it always will. Agent Access is a different thing: structured point-in-time data built for your AI, the outcome history and exit lab that never render on a web page, liquidity checks, contract replay, regime context, and the methodology playbooks. You could rebuild part of that from a scrape. It would cost you far more than $29/mo of your own time.

What happens if I cancel?

Your AI's MCP access ends with your billing cycle. No retention tricks. Everything human-readable stays free: the daily pool, reports, scorecard, methodology, blog, and Lab. Come back whenever your AI needs the data again.

Evan Parra (founder, ML engineer, data architect) built the engine. The nightly pipeline (scan, enrichment, reports, and outcome labels) runs on its own, and every run is logged to BigQuery. The Lab publishes the experiments run on the engine's own data. Read more on the About page.

What happened to the WhatsApp pick subscription?

Retired. It pushed one shared pick to every subscriber, and a shared pick puts everyone into the same contract. Agent Access gives your AI the whole pool and the exit lab instead, so it builds a plan for your account. If you had an active subscription, email evan@gammarips.com and we'll make it right.

What is agentic trading?

Trading with an AI agent as your analyst. Your AI (Claude, ChatGPT, Cursor, Codex, or one you build) pulls real data, reasons over it, and builds a trade plan. You keep the judgment and place the trade, or skip it. An agent is only as good as the data it can reach. GammaRips is that data for options: a nightly pool of liquid contracts and the history to plan the exit, served over MCP.

Options data for your AI agent

Better option contracts.A real trade plan, in the AI you already use.

Every trading night, your AI gets fresh calls with deep books from the 100 most liquid US stocks, and the history to set the target and the stop. It builds the plan with you. You decide.

11 of 14

real-money trades closed at a profit, +$2,263 net

Claude Code trading the GammaRips pool. Every trade, entries Sep 14 to Oct 2, 2026.

54.6%

of pool contracts hit +50% before expiration, more than half. About 3 in 4 hit +20%.

N=793 expired pool contracts, scan dates Aug 24 to Oct 1, 2026.

the open interest: median 4,667 per contract vs 906 before the liquidity rule

N=1,680 pool contracts Aug 24 to Oct 14, 2026 vs N=3,501 over the 60 scan days before the rule.

Add to Claude Add to ChatGPT Add to Cursor Add to Codex

Start your 30-day free trial

Then $29/mo, the founding price. Cancel anytime. The website stays free.

Past results: real-money trades and historical pool data. Educational only. Not investment advice.

How it works

Three steps from install to a trade plan you can act on.

1
Install GammaRips in your AI
Add it to Claude, ChatGPT, Cursor, or Codex in about a minute. Start the 30-day free trial, then sign in or paste your key, and every pro tool turns on.
2
Ask for a trade plan
Your AI reads last night's pool, checks fresh liquidity and the earnings date for each candidate, and sets the target and the stop from the exit lab: how often past pool contracts hit each level.
3
You decide, and place it
You get 1 to 3 candidates, each with entry, target, stop, maximum loss, and a size that fits your risk. Or a reasoned no-trade. You place the order in your own brokerage.

your AI + gammarips

you ▸ build me a trade plan for today. Max risk $300.

get_market_calendar_status()get_regime_context()get_pool(view="enriched")get_signal(view="earnings")get_liquidity()query_outcomes(view="harvest")

AI ▸ The market is open and the regime rail passes. Two names in last night's pool clear the liquidity and earnings checks. Plan for candidate A: limit near the $4.50 mid at about 10:00 ET. Target +50% ($6.75), set from the exit lab history. Stop −30% ($3.15). Size: 2 contracts, maximum loss $270, inside your $300 budget. Want the plan for candidate B too, or will you place this one?

Illustrative session. Not live data, not a recommendation.

Using Gemini CLI, Grok, or another MCP client? Install steps for every client.

Look at the record.

Real-money trades, the history of every pool contract, and the contracts themselves. Each number shows its sample size and its window.

Live record

Claude Code, trading the GammaRips pool with real money

11 of 14

trades closed at a profit

+$2,263

net realized

10 of 14

closed at the agent's pre-set target

+24.5%

median trade, on premium

BE +31%NVDA +33%TSLA −28%NVDA +25%NVDA +23%NVDA +20%NVDA −31%INTC +27%NVDA +27%SPCX +25%NVDA +8%SPCX +24%INTC +30%NVDA −37%

Every trade, wins and losses: N=14, entries Sep 14 to Oct 2, 2026. Realized fills from the broker.

The exit lab

How far pool contracts ran before expiration

Hit +20%73.0%

Hit +50%54.6%

Hit +100%37.1%

Fast moves too: within 3 trading days, 59.5% hit +20% and 36.3% hit +50%. Contracts swing both ways, so the exit plan decides the result. Your AI sets the target and the stop from this history.

N=793 expired pool contracts, scan dates Aug 24 to Oct 1, 2026. 3 trading days: N=1,574, scan dates Aug 24 to Oct 9, 2026. A hit is a touch of the level, not profit kept.

Better contracts

Deeper books since the liquidity rule

	Now	Before
Median open interest	4,667	906
Median session volume	1,086	232
Open interest, thinnest 10%	1,635	29
No fill at 10:00 ET (study)	6.1%	40.5%

Now: N=1,680 pool contracts Aug 24 to Oct 14, 2026. Before: N=3,501 over the 60 scan days before the rule. No-fill figures come from a 60-session study ending Aug 14, 2026.

See every trade on the scorecard

Past results: real-money trades and historical pool data. Educational only. Not investment advice.

Thursday, October 15, 2026

The Earnings Beat Realignment

24contracts in the pool

24bullish names, one call each

A sample of the pool

See every name, free →

A few names from the latest pool, in no order. Every name is free to read on this site. Your AI gets the full pool, with liquidity checks and the exit lab, on Agent Access. Nothing here is a recommendation.

BULL

SKYD

SKYD BULL $8C Oct 23 '26. The institutional flow shows significant accumulation concentrated at the $8 strike expiring next week, indicating a highly aggressive bet on a fast tactical recovery following a structural 22% drop. This collapse was driven by the mechanical ex-distribution separating 470.7 million warrants from the common Class B stock. Risk factor: The stock faces heavy technical resistance and negative sentiment stemming from broader balance-sheet concerns and its post-merger leverage profile.

BULL

GME

GME BULL $28C Oct 23 '26. The institutional flow shows aggressive positioning targeting the short-term strike just out-of-the-money, fueled by ongoing insider buying filings from CEO Ryan Cohen that have propelled the stock back toward its annual highs. Risk factor: The stock is hovering in heavily overbought territory with its Daily RSI pushing above 74, leaving the contract highly sensitive to rapid profit-taking or mean-reversion pullbacks.

BULL

CSCO

CSCO BULL $120C Nov 20 '26. Institutional flow is showing heavy accumulation in the out-of-the-money $120 calls, representing an aggressive positioning for a recovery beyond near-term resistance levels following a temporary pullback driven by gateway security vulnerabilities. While the recent technical correction has broken short-term moving averages, the massive size of this premium reflects strong conviction in Cisco's dominant enterprise market share and robust multi-year AI hardware demand. Risk factor: Continued enterprise risk-off rotation or further escalation of product vulnerability issues could delay the anticipated rebound and pressure near-term margins.

BULL

WMT

WMT BULL $120C Nov 20 '26. The substantial call premium concentration at the $120 strike reflects robust institutional backing following Deutsche Bank's upgrade to Buy and a significant price target lift to $136. This flow aligns with a broader macroeconomic rotation toward defensive consumer staples as inflation dynamics favor Walmart's everyday-low-price model and expanding e-commerce capabilities. Risk factor: Potential margin pressure from elevated valuation levels or high transport and labor investment costs could temper the pace of the upward trajectory.

BULL

RBLX

RBLX BULL $55C Nov 20 '26. The institutional flow shows significant premium concentration in out-of-the-money call options, indicating long-volatility positioning ahead of the late-October earnings print. Risk factor: The primary source of uncertainty remains the underlying struggle with booking growth deceleration and regulatory headwind concerns surrounding minor safety initiatives.

Built for contracts you can actually trade

The engine runs this rule every trading night, at 23:00 ET.

about 3,500 optionable US stockstraded 3M+ shares that sessionchain carries 25+ listed strikestop 100 by combined liquidity rankbullish names onlyone out-of-the-money call eacha pool of roughly 40 to 50

Liquidity decides membership. The engine ranks the most liquid names, keeps the bullish ones, and chooses one call in each on contract liquidity: deep open interest and real session volume. Your AI plans trades it can enter and exit near the quote. If we ranked the most liquid contracts instead, you would get SPY and QQQ every day.

Each contract arrives with its flow data, technicals, catalyst, and news context, all point-in-time. Earnings dates are not screened out of the pool, so your AI checks each candidate's earnings date before it plans a trade.

Read the full methodology See how the engine works

Install steps for every AI

Pick your client. Start the 30-day free trial of Agent Access ($29/mo after), then paste your key, or add the pro endpoint and sign in if your client cannot send one. Every tab reaches the same 9 tools. Want to look first? The free tier needs no card and no key.

Free

no card, no key

One command. No card, no key, no signup.

Add the server, then ask Claude for a morning brief.

claude mcp add --transport http gammarips https://mcp.gammarips.com/mcp

Pro, $29/mo

All paid tools, with your key

All paid tools, and the harness loop. Add the same server with your key.

Mint your key on the account page after the trial starts. Paste it with no spaces and no newline.

claude mcp add --transport http gammarips https://mcp.gammarips.com/mcp \
  --header "Authorization: Bearer YOUR_API_KEY"

2
Or skip the key and sign in. Add the /pro endpoint, then run /mcp inside Claude Code and authenticate.
```
claude mcp add --transport http gammarips https://mcp.gammarips.com/pro
```
3
Or clone the harness: its .mcp.json reads GAMMARIPS_MCP_KEY from your shell.

Start your 30-day free trial, get your key

See all 9 MCP tools →

The Python SDK connects the same way. Steps are on the developer docs.

From the Blog

How the engine builds the pool: methodology, research, and plain-English explainers.

View all →

Give your AI better contracts and a real trade plan.

Install GammaRips in the AI you already use, then start your free trial. Ask for a plan before the next open.

Add to Claude Add to ChatGPT Add to Cursor Add to Codex

Start your 30-day free trial

Then $29/mo, the founding price. Cancel anytime. The website stays free.

Better option contracts.A real trade plan, in the AI you already use.

How it works

Install GammaRips in your AI

Ask for a trade plan

You decide, and place it

Look at the record.

Claude Code, trading the GammaRips pool with real money

How far pool contracts ran before expiration

Deeper books since the liquidity rule

The Earnings Beat Realignment

A sample of the pool

Built for contracts you can actually trade

Install steps for every AI

Free

Pro, $29/mo

From the Blog

How to Read Options Volume vs Open Interest

How to Build an MCP Server for Options Trading

Options Block Trade vs Sweep: How to Spot Institutional Flow

Frequently Asked Questions

Give your AI better contracts and a real trade plan.

One email a week. Catch up in five minutes.

Better option contracts.A real trade plan, in the AI you already use.

How it works

Install GammaRips in your AI

Ask for a trade plan

You decide, and place it

Look at the record.

Claude Code, trading the GammaRips pool with real money

How far pool contracts ran before expiration

Deeper books since the liquidity rule

The Earnings Beat Realignment

A sample of the pool

Built for contracts you can actually trade

Install steps for every AI

Free

Pro, $29/mo

From the Blog

How to Read Options Volume vs Open Interest

How to Build an MCP Server for Options Trading

Options Block Trade vs Sweep: How to Spot Institutional Flow

Frequently Asked Questions

What do I get with Agent Access?

What does a trade plan look like?

Which AIs work with this?

What does the free trial include?

Why don't you just tell me what to buy?

Where's the track record?

How is the pool curated?

Is this financial advice?

Do I need the harness?

Can't I just scrape the free site?

What happens if I cancel?

Who runs this?

What happened to the WhatsApp pick subscription?

What is agentic trading?

Give your AI better contracts and a real trade plan.

One email a week. Catch up in five minutes.