The stock-analysis API you don't have to build

I was building a feature that needed to say something useful about a stock — not just print its P/E, but actually read the situation: is this cheap or expensive, what is the bull case, is the insider buying real or routine. I went looking for an API.

Every finance API I found sold me raw data. Alpha Vantage, Twelve Data, Yahoo Finance, FMP — they will hand you fundamentals, prices, filings, all of it. Great. Now I get to write the part that turns forty metrics into "this looks expensive but the moat is widening." That is the part that is actually hard, and the part I did not want to own forever.

So I would be wiring three data providers, normalizing their conflicting field names, writing and tuning the prompts, handling the rate limits and the caching, and then maintaining all of it as the upstreams change. For a feature, not a product.

What I wanted instead

A single endpoint. Ticker in, analysis out — already synthesized, already structured.

That is what I ended up building for myself, and then put on RapidAPI as the Agent Toolbelt AI Stock Research API. It pulls live fundamentals from Polygon, Finnhub, and Financial Modeling Prep, then returns a Motley-Fool-style read as typed JSON. The numbers are in there too, but the point is the verdict and the reasoning.

Here is a real stock-thesis response:

{
  "verdict": "bullish",
  "oneLiner": "Nvidia owns the essential infrastructure for the AI revolution with a defensible software moat.",
  "keyStrengths": [
    "~80%+ data center GPU market share",
    "CUDA moat creates switching costs",
    "42 buy / 5 hold / 1 sell analyst consensus"
  ],
  "keyRisks": [
    "36.9x P/E leaves no margin for error",
    "Competition from AMD and custom silicon"
  ],
  "insiderRead": "Two executives bought ~47k shares each — meaningful open-market purchases, not routine grants.",
  "dataSnapshot": { "currentPrice": 180.4, "peRatio": 36.9, "marketCapBillions": 4452.2 }
}

That is one HTTP call. No data-provider accounts, no prompt engineering, no normalization layer.

The endpoints

Each one takes a ticker (or a list) and returns structured JSON:

• stock-thesis — verdict, thesis, strengths, risks, valuation, what to watch
• valuation-snapshot — a very-cheap-to-very-expensive verdict with P/E, P/S, EV/EBITDA, FCF yield, ROE, and a specific buy-zone price
• insider-signal — a Form 4 read: real open-market buying versus routine noise
• earnings-analysis — EPS beat/miss history, revenue trend, next earnings date
• bear-vs-bull — steelmanned bull and bear cases, a net verdict, and the key debate
• compare-stocks — a head-to-head on two or three tickers with a winner and per-ticker breakdown
• moat-analysis — a Buffett-style moat rating (wide/narrow/none) with sources and durability
• watchlist-scan — rank two to fifteen tickers by value, quality, growth, or income in one call

US-listed equities. Every metric is tagged with its source, so you can see whether a figure is trailing-twelve-month from FMP or normalized from Finnhub.

Calling it

On RapidAPI, auth is handled for you — subscribe, copy the snippet, and the key and host get filled in. The body is the only thing you write:

curl -X POST 'https://<rapidapi-host>/api/tools/stock-thesis' \
  -H 'X-RapidAPI-Key: YOUR_KEY' \
  -H 'X-RapidAPI-Host: <rapidapi-host>' \
  -H 'Content-Type: application/json' \
  -d '{"ticker": "NVDA"}'

There is a free tier to test against before you wire it into anything, and paid plans that scale by call volume. If you would rather skip the marketplace, you can get a key directly at agenttoolbelt.live and call the same endpoints.

When this is the wrong tool

If you need tick-level price feeds, options chains, or to run your own models on raw fundamentals — buy raw data; this is not that. This is for when you want the judgment layer (a verdict, a thesis, a ranked watchlist) without building and maintaining it yourself. The output is AI-generated and informational, not investment advice — do your own due diligence.

If that is the layer you were about to build, it is on RapidAPI here. I would rather you spend the afternoon on your actual product.