AI-semiconductor SEC Filings Tracker — Financial Reports & XBRL Data

Used by equity analysts, AI-industry researchers, and supply-chain-risk teams tracking the AI-hardware buildout, answering questions like "What was Nvidia's revenue in Q3 2023?"

Scrape SEC EDGAR company filings (10-K, 10-Q, 8-K, and more), structured XBRL financial facts (Assets, Revenue, Net Income, 500+ concepts), and perform full-text search across all SEC filing text — all via the official SEC JSON APIs. No proxy needed. No authentication required.

This tracker is pre-configured for the major AI semiconductor cluster of real, well-known, large-cap public-market companies with SEC EDGAR filings: Nvidia (NVDA), Advanced Micro Devices (AMD), Broadcom (AVGO), Taiwan Semiconductor Manufacturing (TSM), and Intel (INTC).

$2.00/1K filing records · $5.00/1K XBRL financial facts · $3.00/1K full-text search hits. First 10 results free per mode. No subscription needed. Official SEC data. 500+ XBRL financial concepts. Zero proxy cost.

What you can do

• Get all 10-K/10-Q/8-K filings for the AI semiconductor cluster by ticker symbol (NVDA, AMD, AVGO, TSM, INTC) or CIK number
• Extract structured financial data (XBRL): Assets, Revenues, Net Income, EPS, LongTermDebt, and 500+ other GAAP concepts — one row per reporting period
• Full-text search across all SEC filings to find companies mentioning specific topics (e.g. "supply chain disruption", "fabrication yield", "artificial intelligence")

Quick start

Scrape Nvidia and Broadcom annual/quarterly reports:

{
  "mode": "filings",
  "tickers": ["NVDA", "AVGO"],
  "formTypes": ["10-K", "10-Q"],
  "maxItems": 20
}

Get Nvidia's financial facts (Assets, Revenue, Net Income):

{
  "mode": "companyFacts",
  "tickers": ["NVDA"],
  "concepts": ["Assets", "Revenues", "NetIncomeLoss"]
}

Search for 10-K filings mentioning "supply chain disruption":

{
  "mode": "searchFilings",
  "searchQueries": ["supply chain disruption"],
  "formTypes": ["10-K"],
  "maxItems": 100
}

Output schema

Each result contains:

Field	Type	Description
cik	string	10-digit zero-padded SEC CIK
company_name	string	Company name from SEC
ticker	string	Stock ticker (e.g. "NVDA")
form_type	string	SEC form type (10-K, 10-Q, 8-K, etc.)
filing_date	string	Date filed (ISO: YYYY-MM-DD)
accession_number	string	Unique filing ID with dashes
primary_document	string	Main filing document filename
report_date	string	Period covered (ISO: YYYY-MM-DD)
filing_url	string	Direct HTTPS URL to the filing document
items	array	Form items listed (e.g. ["1A", "7A"] for 8-K)
parse_confidence	float	Data quality score (0.0–1.0; 1.0 = all fields present)
warnings	array	List of quality warning codes

For companyFacts mode, additional fields: concept, label, namespace, unit, value, period_end, fiscal_year, fiscal_period, frame.

For searchFilings mode, additional fields: query, file_description.

Why this scraper?

• Official SEC APIs — not HTML scraping. Zero fragility. No class-name changes break it.
• Ticker→CIK auto-lookup — just provide NVDA, AMD, AVGO, TSM, INTC; no need to look up CIK numbers manually
• Direct filing URLs — each row includes the full HTTPS URL to the primary filing document (10-K PDF/HTML)
• parse_confidence field — machine-readable quality score in every row (unique to this actor)
• Zero proxy cost — SEC APIs are public and accessible from anywhere
• XBRL structured data — 500+ financial concepts extracted as clean rows (no parsing required)

Common form types

Form	Description
10-K	Annual report (comprehensive financial statements)
10-Q	Quarterly report (financial statements)
8-K	Current report (material events: earnings, mergers, leadership changes)
DEF 14A	Proxy statement (shareholder meeting, executive compensation)
S-1	IPO registration statement
4	Insider trading report
13F	Institutional investment manager holdings

Rate limits and fair use

The SEC Fair-Access Policy requires a descriptive User-Agent header on every request (included automatically). The SEC allows up to 10 requests/second. This actor stays well below that limit with built-in throttling.

Pricing

Pay-per-result (PPE) — charged per item returned, not per run:

Mode	Event	Rate	Example
filings	filing-item	$2.00/1K	1,000 10-K records = $2.00
companyFacts	xbrl-facts-record	$5.00/1K	500 XBRL concept rows = $2.50
searchFilings	search-hit	$3.00/1K	200 full-text hits = $0.60

First 10 results free per mode. Compute time billed separately to your Apify account.

Worked examples:

• 5 tickers × 10 years of 10-Q filings (40 rows each) = 200 records = $0.40
• Nvidia financials, 3 XBRL concepts × 20 quarters = 60 rows = $0.30
• Full-text search "supply chain disruption" in 10-K filings, 500 hits = $1.50

FAQ

Do I need an API key or proxy? No. The SEC EDGAR APIs are fully public — no authentication, no proxy, no signup. This actor includes the required SEC-compliant User-Agent header automatically.

What ticker symbols work? Any US exchange ticker (NYSE, NASDAQ, etc.). The actor auto-resolves tickers to CIK numbers using the SEC's official company_tickers.json. For private companies or foreign filers, provide a CIK directly.

What output formats are available? JSON, CSV, Excel — download from the Apify dataset. filing_url links directly to the SEC EDGAR filing document.

What if a ticker isn't found? The record is logged as failed and the run continues. Check that the ticker is a current US exchange listing — delisted tickers may not resolve.

vs. Competitors

Feature	This Actor	Financial data vendors
Data source	Official SEC EDGAR API	Vendor aggregation
Auth required	No	Paid subscription
Ticker → CIK auto-resolve	Yes	Usually
XBRL structured data	500+ concepts	Varies
Full-text filing search	Yes (EFTS)	Rare/expensive
parse_confidence	Yes	No
Cost	$2-5/1K	$50-200/1K typical

Use with AI agents (MCP)

An agent calls this tool to look up SEC filings, financial facts, and full-text filing search mid-conversation — e.g. "Get Nvidia's net income for the last 5 years", "Find all 8-K filings for TSM in 2024", or "Search 10-K filings mentioning 'artificial intelligence'."

Point your MCP client at this tool:

{
  "mcpServers": {
    "apify": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://mcp.apify.com/?tools=bovi/ai-semiconductor-sec-filings-tracker",
        "--header",
        "Authorization: Bearer <YOUR_APIFY_TOKEN>"
      ]
    }
  }
}

Minimal agent input (XBRL financial facts):

{
  "mode": "companyFacts",
  "tickers": ["NVDA"],
  "concepts": ["Assets", "Revenues", "NetIncomeLoss"]
}

Integrations

Built for equity analysts, AI-industry researchers, and supply-chain-risk teams extracting structured financials and filings from public companies — the JSON/dataset output drops into the tools you already run, no glue code:

• n8n / Make / Zapier — trigger a run or pipe every new dataset item into 500+ apps (Google Sheets, Airtable, Slack, HubSpot, your database) with no code: n8n, Make, Zapier.
• Webhooks — fire your own endpoint the moment a run finishes, to push results straight into your pipeline (docs).
• MCP server — expose this actor as a tool to Claude, Cursor, or any MCP client so an AI agent can pull this data mid-conversation (guide).
• API & SDKs — fetch the dataset as JSON, CSV, or Excel through the Apify REST API or the Python / JS SDKs.

See all Apify integrations.

Legal notice

This actor accesses publicly available SEC EDGAR data as permitted by the Securities Exchange Act. EDGAR is a public service of the U.S. Securities and Exchange Commission. This actor is not affiliated with or endorsed by the SEC.

Usage statistics

This Actor creates a small, content-free summary at the end of each run. It is used only to monitor reliability and improve this Actor. A copy is saved as USAGE_STATS in your own Apify key-value store, so you can see the exact record created for your run.

Set disableUsageStats to true in the input to opt out. Nothing is sent then; your USAGE_STATS record only says that statistics were disabled.

Only these fields are recorded:

• schema version, Actor name and build number;
• UTC start and finish hour (not a precise timestamp);
• run duration, number of results and time to the first result, each as a coarse range;
• whether the result was empty, the end status, and an error type from a fixed list;
• memory setting and counts of charged events;
• names of the input fields you set, never their values;
• the selected option for input fields that offer a fixed list of choices (for example a sort order).

We do not collect input text, search terms, URLs, domains, usernames, email addresses, names, proxy credentials, tokens, scraped records, output items, raw error messages, stack traces, or hashes of any of those values. Records are kept for no longer than 13 months, used only as aggregated operational statistics, and never sold or shared.

Additional fields (Phase 2)

This Actor also records your Apify user ID, whether Apify marks the account as paying, the size range of list inputs, the selected country when the input offers a fixed list of countries, and one category from a fixed Actor taxonomy. We use these fields only for aggregate reliability, repeat-use and cross-Actor analysis; reports suppress any cell with fewer than five distinct users.

The same disableUsageStats: true input flag turns these fields off too. The user ID is removed after 13 months; we do not export, sell, share, or attempt to re-identify this data.

Run-outcome signals (v2)

To learn whether a run did what it was asked to do, the record also holds a few more coarse ranges and yes/no flags. None of them contains content:

• the result limit you asked for (a range, when the input has one) and what share of it was delivered;
• results delivered per input item you listed (a range);
• output quality as ranges: how fully the result fields were filled, the share of rows that look like errors, the share of duplicate rows, and how many different fields appeared. These are counted in memory while results are saved; no result content is kept;
• how the run was started (console, API, schedule, webhook, another Actor);
• how it ended: stopped by you, timed out, reached the requested limit, stopped by the charge limit, and how many times the platform moved the run;
• if this Actor reports it: how many items to process worked or failed (ranges) and one failure reason from a fixed list;
• a short code made from the names of the input fields you set, never their values.

Repeat-run fingerprint (v2)

When your Apify user ID is recorded (see above), the record also holds an 8-character one-way code made from your input (proxy settings left out) and this Actor's name. It only lets us see that the same account ran the same input again soon after an unsatisfying run; we never see the input itself. It is stored only in the database, never published, and reports use it in aggregate with the same five-user minimum. It is the one exception to the statement above that no hashes are collected, and disableUsageStats: true turns it off.