The Leeway Context API connects Claude, ChatGPT, Cursor and other AI agents to current research on stocks, assets and markets. The first request funds the research for the community. Every later access to the same research costs only two cents.
Your assistant does not know what happened after its training ended. Ask it about a stock and it will still answer, in complete sentences and with great confidence, and it will sometimes be years out of date.
The Leeway Context MCP closes that gap. It gives your assistant the current state of a stock, a tradable asset or the wider market: what happened recently, what is moving the price, who the competitors are and which risks exist. You set up the connection once and then ask your questions as usual.
On the left the assistant answers from its training. It names Tim Cook as chief executive and sounds entirely certain. On the right the same assistant has fetched the context object for Apple and knows about the succession to John Ternus, the pressure from memory costs and the breach at a supplier.
How has the track record been of the apple leadership? Is the CEO good?
The track record of Apple’s leadership under CEO Tim Cook, who took over from Steve Jobs in August 2011, is widely considered one of the most successful in corporate history, though it comes with its own set of criticisms.
Whether Tim Cook is a "good" CEO depends on the metric you use to measure success. Here is a breakdown across several key areas:
If measured by financial success, Tim Cook is arguably one of the greatest CEOs of all time.
As of September 2026, Apple's leadership is in the midst of a historic transition, which makes evaluating its track record a tale of two eras: the highly successful but currently strained outgoing era of Tim Cook, and the brand-new tenure of incoming CEO John Ternus.
To answer whether the CEO is "good," we have to look at what Tim Cook is leaving behind and what John Ternus is inheriting this month.
Because John Ternus is taking over the CEO role this month, he doesn’t have a track record as chief executive yet, but his background tells us a lot about where Apple is heading.
Ternus previously served as Apple’s Senior Vice President of Hardware Engineering. His appointment suggests the board wants a leader who is deeply rooted in product development to speed up execution.
Tim Cook’s 15-year run as CEO is objectively one of the most financially successful in corporate history, though his final year has exposed significant structural vulnerabilities.
Financial Juggernaut: Cook transformed Apple into a cash-generating machine. Even in Q2 2026, Apple generated a massive 111.2 billion in revenue (up 17% year-over-year).
The Services Empire: Cook successfully diversified Apple away from just selling iPhones. The Services division (App Store, iCloud, Apple Music, etc.) recently hit a record 31 billion in a single quarter.
Shareholder Value: Cook has been exceptionally friendly to Wall Street, recently authorizing another 100 billion share repurchase program, bringing total buyback capacity to an unprecedented 164 billion.
The AI Blindspot: Cook's leadership team was caught off-guard by the generative AI boom. Repeated delays in the Siri AI rollout have led to internal and external questions about Apple's "execution velocity."
Supply Chain Vulnerabilities: Despite Cook's reputation as a supply chain mastermind, Apple is currently structurally dependent on external suppliers for memory. With AI data centers driving up global storage costs, Apple has been forced to raise prices on Macs and iPads by double-digit percentages—a drastic move it avoided even during the COVID-19 crisis.
Geopolitical and Security Headwinds: The company is currently in the awkward position of lobbying the Trump administration to buy DRAM from CXMT, a Chinese manufacturer on the Pentagon's restricted list. Furthermore, efforts to move manufacturing to India recently resulted in a massive data breach at supplier Tata Electronics, damaging Apple's privacy-first reputation.
The market and consumers will be watching closely. He is inheriting a company with a flawless balance sheet but severe operational fires. To be considered a "good" CEO, Ternus will need to:
Fix the AI Lag: Get the delayed Siri AI features out the door and prove Apple can compete with Microsoft, Google, and OpenAI.
Solve the Memory Crisis: Find a way to secure DRAM and storage without relying on restricted Chinese entities or passing massive price hikes onto consumers.
Restore Supply Chain Security: Clean up the fallout from the Tata Electronics breach and ensure the transition of manufacturing to India and Vietnam goes smoothly.
Was Tim Cook a good CEO? Yes, he was an absolute master of financial engineering, ecosystem expansion, and scale. He made Apple the most valuable company in the world.
Is the current leadership good? They are currently under immense pressure. The transition to John Ternus reflects a necessary pivot. Apple's leadership has the cash and the market power to weather the current AI and supply chain storms, but their reputation for flawless execution has taken a significant hit in 2026.
Your assistant requests a research object for a stock, asset or market. The result is stored once and can then serve many people instead of triggering the same research again and again.
It asks for a specific research type and instrument, such as recent developments for AAPL.NASDAQ or a five-year timeline.
For stock and asset objects, if no sufficiently fresh version exists, your request starts a new research run and carries the provider cost that actually arises. Public market routes are read-only and do not generate missing documents.
The public research object is stored under its research type and instrument. Other users can use the same stored version without funding another research run.
Every request served from the fresh cache costs two cents when the requested language version is already stored. A missing translation or rewrite can require provider work instead.
Only the generated public research object is shared. Your private question, prompt, portfolio, conversation and account details are neither stored in nor shared through the cache. The shared result contains research about the requested market object, not your personal instructions.
Ten people requesting the same research type, instrument and language can either trigger ten research runs or use one generation followed by nine cache reads.
For illustration, assume one research run costs €0.12 and that 10 requests arrive within the object's freshness window.
| Case | Calculation | Total |
|---|---|---|
| Everyone researches separately | 10 × €0.12 | €1.20 |
| Shared through Leeway | €0.12 for the first call, then 9 × €0.02 | €0.30 |
The example assumes that the requested version is already available after the first run. A real generation or missing translation is charged at the provider cost actually incurred; a cache read remains the fixed two-cent charge.
In this example, sharing saves €0.90, or 75 percent, across the ten requests.
The system does not require users to coordinate or contribute to a common fund. Each request is billed to the person making it, while the resulting public research becomes useful to the next caller.
When your request finds no sufficiently fresh requested version, you pay the actual generation or translation cost. You also make that research available to everyone else during the freshness window.
When another caller has already requested the same stored version, you pay only the two-cent cache read. You benefit from research that no longer needs to be generated or translated for your request.
The Context API supplies current research objects that an AI assistant can call when it needs financial information. Each object answers a defined research question and is available through MCP or REST.
Every request authenticates with your API token. Each object has a default maximum age; you or the AI can lower or raise that maximum, to get a newer piece or save money through more cache hits.
https://api.leeway.tech/api/v1/public/ai| Object | What it is | Default freshness | REST Endpoint | Sample |
|---|---|---|---|---|
| Equities | ||||
| What's New | A dated briefing on recent events at a company, with the context an AI assistant needs to explain what changed and why it matters. | 7 days | GET /research/equity/whatsnew/{ticker} | |
| Timeline | A five-year chronology of the events that shaped a company, so an AI assistant can explain how its position and investor view evolved. | 30 days | GET /research/equity/timeline/{ticker} | |
| Competitors | A structured view of the companies competing in the same market, including their roles, relative strengths and weaknesses. | 90 days | GET /research/equity/competitors/{ticker} | |
| Risks | The material risks facing a company, with context on how they could affect its business and stock. | 90 days | GET /research/equity/risks/{ticker} | |
| Price drivers | A structured view of the forces currently moving a stock’s price and the events or expectations behind them. | 30 days | GET /research/equity/price-drivers/{ticker} | |
| What's New: Industry | A briefing on recent events and shifts in the industry, providing context for the company’s market position. | 7 days | GET /research/equity/industry/{ticker} | |
| What's New: Sector | A briefing on recent events and shifts across the company’s wider sector, providing context for its outlook. | 7 days | GET /research/equity/sector/{ticker} | |
| Commodities and currencies | ||||
| What's New: Asset | A dated briefing on recent events affecting a commodity or currency pair, with context for its current price. | 1 day | GET /research/asset/whatsnew/{ticker} | |
| Asset timeline | A dated sequence of recent events and price moves that shows how a commodity or currency pair developed. | 7 days | GET /research/asset/timeline/{ticker} | |
| Asset price drivers | The forces currently moving a commodity or currency pair, with the supply, demand or market events behind them. | 7 days | GET /research/asset/price-drivers/{ticker} | |
| Asset events | Upcoming and recent events that could affect a commodity or currency pair, with their dates and relevance. | 7 days | GET /research/asset/events/{ticker} | |
| Market | ||||
| Market this week | The latest weekly briefing. short returns the email, and long returns the website article. The call does not charge the wallet. | latest stored text | GET /research/market/whatsnew-weeklyCache only | |
| Daily market briefing | The latest daily briefing. The email and the website use the same article. A trader subscription is required, and the call does not charge the wallet. | latest stored text | GET /research/market/whatsnew-todayCache only | |
| CIO view | The latest CIO view of the macro regime, allocation, and scenarios. short returns the email, and long returns the website text. An investor or trader subscription is required. | latest stored text | GET /research/market/cio-viewCache only | |
| Weekly market timeline | A dated sequence of the structural shifts that have shaped the market over recent months. | 8 days | GET /research/market/timeline-weeklyCache only | |
Beyond AI context objects, we also offer raw market data, financial forecasts, and fundamental screeners. These are available through subscription packages with daily request quotas.
| Object | What it is |
|---|---|
| Data API | Fundamentals, prices, dividends, macro and more: the base package, and the market-data tools MCP exposes. |
| Analytics API | Screener, key figures, market cap, relative move and benchmark, standalone or as an add-on. |
| Forecast API | AI-powered revenue and earnings forecasts, standalone or as a Data API add-on. |
| NAAIM Exposure Index API | Current weekly NAAIM Exposure Index readings and more than 20 years of history, as an official NAAIM partner. |
These are excerpts from stored public objects. The date and freshness window determine whether a later request can read the same result for the cache price.
https://api.leeway.tech/api/v1/public/ai/research/equity/whatsnew/AAPL.NASDAQ?apitoken=YOUR_TOKENApple faces mounting pressure from storage costs as AI data centers worldwide drive unprecedented price increases. The company has responded by raising prices on Macs, iPads, and other hardware by double-digit percentages in some cases, a measure it avoided even during the COVID crisis. Simultaneously, Apple is lobbying the Trump administration for permission to source DRAM from Chinese manufacturer CXMT, which already sits on the Pentagon's restricted list. The company lacks its own memory manufacturing capacity and remains structurally dependent on external suppliers.
In the second quarter of fiscal 2026, Apple generated $111.2 billion in revenue, up 17% year-over-year. iPhone revenue reached $57 billion, while Services hit a record $31 billion. The company authorized a new $100 billion share repurchase program, which combined with remaining capacity from the previous program brings total buyback capacity to approximately $164 billion.
The planned CEO transition from Tim Cook to John Ternus in September, coupled with repeated delays in the Siri AI rollout, has raised internal and external questions about execution velocity. A data breach at supplier Tata Electronics, in which over 200,000 Apple-related files surfaced on the dark web, has added reputational and regulatory pressure.
https://api.leeway.tech/api/v1/public/ai/research/equity/timeline/RACE.MI?apitoken=YOUR_TOKENInstitutional investor sentiment remains constructive following second-quarter 2026 operating results. The company exceeded consensus expectations, raised its full-year EBITDA guidance, and reaffirmed the pricing power of the brand during the rollout of its first fully electric model.
On 30 July 2026, Ferrari reported second-quarter revenue of €1.94 billion and adjusted EBITDA of €755 million, corresponding to an operating margin of 39.0 percent. Management raised full-year EBITDA guidance to at least €2.97 billion, supported by sustained demand for personalisations and favorable foreign exchange movements.
Each object has a default freshness period. The request can set a stricter or more lenient maximum age, but a cache read is possible only when the stored object meets that request.
The full billing rules, freshness settings and wallet details are explained on the research cost page
You pay for your own request. If the requested language version is served from a fresh shared object, you pay two cents. If no suitable version exists, your request starts generation or translation and carries the provider cost actually incurred.
No. The cache stores the generated public research object identified by its research type and instrument. Your prompt, conversation, portfolio and account details are not shared.
The research type and requested instrument identify the object, while its language, date and maximum age determine whether the requested version is fresh enough to serve. A different research type, instrument or language version requires a different stored result.
The next request starts a new generation or translation and pays the provider cost actually incurred. That new version then becomes available to later callers during its own freshness window.
The first call after the requested version is missing or stale funds the research work itself. Later callers do not repeat that work; they read the stored version for two cents.
Add the Leeway MCP and ask your agent to fetch the research object it needs. The connection lets the assistant use the shared cache instead of repeating the same broad search.
Top up the wallet when a new generation is needed. Then share the page with people who follow the same stocks, assets or markets: shared use makes repeated research less wasteful.
