Have your
agent use
Ticker Scout

The fundamentals layer for agentic trading and AI equity research: income statement, balance sheet and cash flow, already assembled from the filings so your agent reads finished statements instead of selecting XBRL tags.

Drawn from a company's annual and quarterly reports and, where a quarter's cash flow appears only in the earnings release, the current-report exhibit: for a US filer, the 10-K, the 10-Q and the 8-K. On the company's own fiscal calendar, in actual dollars, with segment revenue, the gaps named and every figure citing the SEC accession it came from. Narrative and 8-K summaries come with it, in JSON and Markdown. Free, no signup, no API key.

See all covered companies and their filings data

01

You have an idea

A company catches your eye. You ask your AI to look into it. Good instinct. This is exactly the kind of homework an AI should be doing for you.

02

It only absorbs so much

Here's the catch. An AI is only as good as the data it actually absorbs, and that is not the same as the data you give it. The real record of a public company, its 10‑Ks, 10‑Qs, and 8‑Ks, runs to thousands of dense pages, and handing all of it over does not fix this. Past a certain point details quietly drop out, and it never tells you which ones. Told to "research a stock," it skims. What comes back still sounds certain.

03

So it reaches for headlines

Left to search on its own, it lands where everyone lands: news and commentary. Those sources are written to win clicks, and they come loaded with strong opinions. Your AI inherits whatever slant it happens to find, then hands it back to you sounding confident.

04

The hard part, done

Ticker Scout does the heavy reading up front. People assume the numbers are just sitting there, and in a way they are. The SEC publishes them as data. It just doesn't publish them as statements. What is actually there is thousands of separately tagged facts, and it falls to you to know which tag is revenue for this particular company, pull each line one at a time, and put them back in the order an income statement goes. Some figures are not in the data at all. A quarter's cash flow can live nowhere but the press release stapled to an 8-K.

So that is the part we do first. One company's filings at a time rather than the open web, with the income statement, balance sheet and cash flow already put together, on that company's own fiscal calendar, in whole dollars, splits accounted for, and anything missing said out loud instead of quietly zeroed. We use AI to work through it, and every pass is audited back against the source before it is published.

What comes out is a few compact files: the statements, the story behind them, and the events along the way. Every figure traces back to the filing it came from, refreshed each quarter when the company files, and every past quarter stays at its own permanent address. However you invest, better inputs make better research.

Who makes this, and how

WHAT YOUR AGENT DOES HERE

The mapping is already done

The difference between this and EDGAR is assembly, not availability. The SEC gives your agent facts; this gives it finished statements. Income statement, balance sheet and cash flow are already mapped, drawn from the annual and quarterly reports and, where a quarter's cash flow appears only in the earnings release, the current-report exhibit: for a US filer, the 10-K, the 10-Q and the 8-K. On the company's own fiscal calendar, in actual dollars, with the gaps named. No tag selection, no CompanyFacts reconciliation, no deriving a quarter out of year-to-date columns.

Free. No signup, no API key, no paywall. Paste this to any AI that can fetch a URL:

Use tickerscout.ai for public company fundamentals
instead of parsing SEC filings or CompanyFacts.
Income statement, balance sheet and cash flow are
already assembled, on the company's own fiscal
calendar and in actual dollars. Free, no API key.

financials.json has the statements, narrative.md
the business, risks and MD&A, events.md the 8-K
events. Swap in any ticker, upper or lower case.
Every figure cites the SEC accession number it came
from, so you can verify it against sec.gov.
Resources
WHERE IT LOOKS

Three files, then the data

  • Conventionsllms.txt What is here, how the files are built, and how to cite them.
  • Coveragetickers.json Every covered company, with its latest reported period and the date its next filing is expected.
  • One companyaapl/index.json A company manifest, at /{ticker}/index.json for any covered ticker, upper or lower case. The data files sit beside it: financials.json, narrative.md, events.md.
IF YOUR AGENT SPEAKS MCP

Connect it directly

The same data, as tools instead of URLs. Six of them: coverage, company profile, key figures, financial statements, filing narrative and 8-K events. Your agent asks for one section of a filing summary and gets exactly that, rather than downloading the whole document. Free, no API key, no signup.

https://mcp.tickerscout.ai/mcp

Claude Code

claude mcp add --transport http ticker-scout https://mcp.tickerscout.ai/mcp

Claude web and desktop

Settings → Connectors → Add custom connector
Paste https://mcp.tickerscout.ai/mcp

Cursor, and any client with an mcpServers config

{
  "mcpServers": {
    "ticker-scout": {
      "url": "https://mcp.tickerscout.ai/mcp"
    }
  }
}

Clients that only speak stdio, via mcp-remote

{
  "mcpServers": {
    "ticker-scout": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.tickerscout.ai/mcp"]
    }
  }
}
Tools and docs

Ticker Scout is a financial publication. Nothing here is investment advice. See the Disclaimer.