# SEC EDGAR AI Scraper - LLM-ready filings, RAG chunks & signals (`dominvo/sec-edgar-ai-scraper`) Actor SEC EDGAR as LLM-ready data: section-aware Markdown, RAG chunks with stable IDs + SHA-256, XBRL facts, Form 4/13F, section diff, scored signals. Multi-event PPE. Pairs with sec-edgar-mcp. - **URL**: https://apify.com/dominvo/sec-edgar-ai-scraper.md - **Developed by:** [Domin Vo](https://apify.com/dominvo) (community) - **Categories:** AI, Agents, Developer tools - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing Pay per event + usage This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README **Pull SEC filings as clean JSON or LLM-ready Markdown — without writing a single line of EDGAR code.** This Actor turns the entire [SEC EDGAR](https://www.sec.gov/edgar) corpus — 10-K, 10-Q, 8-K, **13F filings**, **Form 4** insider transactions, Form 144, XBRL facts, DEF 14A proxies, S-1 prospectuses, N-PORT mutual-fund holdings, Schedule 13D activist stakes, Form ADV, and 60+ more — into uniform rows you can pipe straight into an LLM, vector store, or notebook. ### What does SEC EDGAR AI Scraper do? One Actor, **70 modes**, every U.S. public company. Pick a mode (e.g. `form_13f_filings`, `form_4_filings`, `xbrl_facts`), feed it a ticker (`AAPL`), CIK (`0000320193`), or company name, and get structured rows back in seconds. No User-Agent headers, no fair-use throttling, no XBRL parser to maintain. Every row uses the same envelope — `sha256`, `mode`, `cik`, `accession`, `filing_date`, `payload` — so a 13F holding and an 8-K filing ingest the same way downstream. Three things make this Actor different from any other **SEC EDGAR scraper**: 1. **RAG-native output.** `filing_markdown`, `filing_chunks`, and `section_diff` ship section-aware Markdown, stable chunk IDs with SHA-256 fingerprints, and year-over-year diffs — drop straight into LangChain, LlamaIndex, or your own retrieval pipeline. 2. **Hedge-fund signals.** `signal_pack`, `insider_cluster`, `lockup_expiration`, `discrete_signals`, and `activist_clustering` compute composite signals on top of raw filings. You don't get a thin wrapper around `data.sec.gov` — you get the alpha layer. 3. **Pay only for rows you keep.** 20 bundled event types, priced from $0.0001 to $0.04. The **first 20 rows of every run are free** — prototype at zero cost. ### Why use SEC EDGAR AI Scraper? - **Quant funds & analysts** — pull **13F filings**, Form 4 insider trades, Schedule 13D activist stakes, and Form 144 planned sales into Python, R, or a warehouse with one HTTP call. Build signals without building a parser. - **Fintech & RegTech apps** — power compliance copilots, audit tools, and disclosure-monitoring products with a real **SEC filings API**. Section diffs flag the exact paragraphs that changed between 10-Ks. - **AI agents & RAG pipelines** — section-aware Markdown plus deterministic chunk IDs give your agent citations with provenance. Every chunk has a SHA-256 it can quote back. - **Bloomberg Terminal alternative on a budget** — get the SEC slice of the Terminal (13F changes, insider trades, proxy fights, M&A registrations) for cents per query instead of $24K a seat. ### How to use SEC EDGAR AI Scraper 1. Click **Try for free** on the Actor page. 2. Pick a `mode` (e.g. `form_13f_filings`). 3. Enter `identifiers` — tickers (`AAPL`), CIKs (`0000320193`), names, or domains. 4. *(Optional)* Set `since` / `until` dates, a `forms` filter, or a `limit`. 5. Click **Save & Start**. Stream results to JSON, CSV, Excel, NDJSON, or Markdown. Or call it from Python: ```python from apify_client import ApifyClient client = ApifyClient("") run = client.actor("dominvo/sec-edgar-ai-scraper").call(run_input={ "mode": "form_13f_filings", "identifiers": ["BRK.A", "RENTECH"], "since": "2026-01-01", "limit": 200, }) for row in client.dataset(run["defaultDatasetId"]).iterate_items(): print(row["payload"]["issuer"], row["payload"]["value"]) ```` Schedule daily runs, chain modes via [Apify integrations](https://apify.com/integrations), or trigger on a webhook — same API. ### Input — picking a mode 70 modes, one Actor. Pick the mode that matches the form or signal you need: | Goal | Mode | |---|---| | Section 16 insider trades | `form_4_filings` | | Institutional 13F holdings | `form_13f_filings` | | Activist 5%+ stakes | `form_13d_filings`, `activist_clustering` | | Planned insider sales (90-day early warning) | `form_144_filings`, `lockup_expiration` | | Annual / quarterly reports | `form_10k_filings`, `form_10q_filings` | | 8-K item alerts with severity tags | `form_8k_filings`, `discrete_signals` | | Proxy fights, exec comp, audit fees | `form_def14a_filings`, `def14a_exec_comp` | | IPO prospectus + lockup calendar | `form_s1_filings`, `lockup_expiration` | | M\&A registration deals | `form_s4_filings`, `form_to_tender`, `form_14d9_recommendation` | | Foreign issuers (FPI / ADR / Canadian) | `form_20f_filings`, `form_6k_filings`, `form_40f_filings` | | Mutual fund / ETF holdings + proxy votes | `form_nport_filings`, `form_npx_filings` | | US-GAAP / IFRS XBRL data | `xbrl_facts`, `xbrl_statements`, `xbrl_frames`, `xbrl_metrics` | | Cross-cutting EDGAR search | `filings_search`, `filings_feed`, `filings_index` | | Section-aware Markdown for RAG | `filing_markdown`, `filing_chunks` | | Year-over-year 10-K text diff | `section_diff`, `disclosure_compare` | | Hedge-fund composite signals | `signal_pack`, `insider_cluster` | | Resolve ticker ↔ CIK ↔ name ↔ domain | `cik_ticker_map` | | SEC enforcement & adviser data | `litigation_releases`, `aaer_releases`, `comment_letters`, `form_adv_filings` | Common inputs: `identifiers` (array), `since` / `until` (ISO date), `forms` (array filter), `limit` (cap rows), `incremental` (skip unchanged rows), `output_format` (`json` / `ndjson` / `csv` / `xlsx` / `markdown`). ```json { "mode": "form_4_filings", "identifiers": ["TSLA", "MSFT"], "since": "2026-01-01", "transaction_codes": ["S", "P"], "limit": 500 } ``` ### Output — JSON, CSV, Excel, Markdown Every row uses the same envelope with a mode-specific `payload`: ```json { "sha256": "9f1c2a…", "mode": "form_4_filings", "cik": "0001318605", "accession": "0001209191-26-012345", "filing_date": "2026-05-12", "payload": { "issuer": "Tesla, Inc.", "reporter": "Elon Musk", "relationship": ["Director", "Officer", "10% Owner"], "transaction_date": "2026-05-10", "transaction_code": "S", "shares": 1500000, "price_per_share": 247.18, "total_value": 370770000, "shares_owned_after": 411062076 } } ``` Switch `output_format` per run: - **`json`** — Apify dataset rows (default). - **`ndjson` / `csv` / `xlsx`** — single file streamed to the key-value store at end of run. - **`markdown`** — **LLM-ready `output.md`** bundle: one `### heading` per record, ready to paste into Claude, ChatGPT, or your RAG pipeline. The only SEC Actor that ships native Markdown output. ### Data fields by mode | Mode | What you get | Persona | |---|---|---| | `form_4_filings` | Section 16 insider trades, one row per transaction | Quant / Hedge | | `form_13f_filings` | 13F-HR institutional holdings, one row per CUSIP | Quant / Hedge | | `form_13d_filings` | Schedule 13D activist 5%+ stakes + group filer clustering | Quant / Hedge | | `form_144_filings` | Restricted-stock sale notices — 90-day forward signal | Quant / Hedge | | `form_10k_filings` / `form_10q_filings` | Annual / quarterly reports with section index | Fintech / RegTech | | `form_8k_filings` | 8-K Items with severity tags + restatement flags | Fintech / RegTech | | `xbrl_facts` / `xbrl_statements` / `xbrl_metrics` / `xbrl_frames` | US-GAAP / IFRS XBRL data, atomic or normalized | Fintech / Quant | | `filing_markdown` / `filing_chunks` | Section-aware Markdown + stable RAG chunk IDs | LLM / Agentic | | `section_diff` / `disclosure_compare` | Paragraph-level YoY 10-K diff | LLM / Agentic | | `signal_pack` / `discrete_signals` / `insider_cluster` | Hedge-fund composite signals | Quant / Hedge | | `litigation_releases` / `aaer_releases` / `comment_letters` | SEC enforcement & restatement early-warning data | RegTech / Forensic | | `cik_ticker_map` | Resolve ticker / CIK / name / domain | All | | `filings_search` / `filings_feed` / `filings_index` | EDGAR full-text search + real-time + historical | All | Full 70-mode catalog in the Input tab dropdown. ### Pricing — how much does it cost to pull SEC filings? **Pay per row, not per second.** The **first 20 rows of every run are free**, so prototyping is free. Beyond that, only the rows you receive are charged: | Data shape | Example modes | Price per row | |---|---|---| | CIK / ticker lookup | `cik_ticker_map` | $0.0001 | | Filing index / feed / search hit | `filings_index`, `filings_search`, `filings_feed` | $0.0004 | | Insider transaction | `form_4_filings`, `form_144_filings` | $0.0005 | | Institutional holding | `form_13f_filings`, `form_nport_filings`, `form_npx_filings` | $0.0005 | | XBRL atomic fact | `xbrl_facts`, `xbrl_frames`, `xbrl_metrics` | $0.0002 | | XBRL statement row | `xbrl_statements` | $0.001 | | Form filing record | `form_10k_filings`, `form_8k_filings`, `form_s1_filings`, etc. | $0.002 | | 10-K section extract | `section_extract` modes (MD\&A, Risk Factors, ICFR, …) | $0.001 | | Filing as Markdown (section-aware) | `filing_markdown` | $0.003 | | RAG chunk | `filing_chunks` | $0.0008 | | Year-over-year section diff op | `section_diff`, `disclosure_compare` | $0.002 | | DEF 14A proxy row | `def14a_exec_comp`, `def14a_audit_fees`, … | $0.001 | | Fund report (N-CSR / N-CEN) | `form_ncsr_filings`, `form_ncen_filings` | $0.001 | | Enforcement / Form ADV record | `litigation_releases`, `aaer_releases`, `form_adv_filings` | $0.001 | | Risk signal | `signal_pack`, `insider_cluster`, `activist_clustering` | $0.002 | | AI brief / summary | `ai_summary`, `ai_importance` | $0.04 | | Run started | once per run | $0.005 | | Change detected (incremental) | only when a record's SHA-256 differs | $0.0003 | **Worked examples:** - Daily 13F sweep of 100 funds (~5,000 holdings) → **$2.50** (minus the first 20 free rows). - Full 10-K of Apple as RAG chunks (~400 chunks) → **$0.32**. - Insider trades for the FAANG 5 over 2025 (~3,000 rows) → **$1.50**. ### Tips & advanced options - **Use `incremental: true` on schedules.** Re-run the same input and you only pay `$0.0003` per row whose SHA-256 actually changed. Most days that's a handful of rows out of thousands. - **Start with a mid-cap** (`MDB`, `NET`, `SHOP`) when testing — Berkshire-class filings can blow past 1 GB of memory on RAG-heavy modes. - **Chain modes via the Apify API.** Resolve identifiers with `cik_ticker_map`, then fan out to `form_4_filings` and `form_13f_filings` in parallel runs. Same dataset. - **Pick the right output format.** `markdown` for agents and RAG, `csv` / `xlsx` for analysts, `ndjson` for warehouses, `json` for everyone else. - **No Apify Proxy needed.** SEC fair-use requires identifying User-Agent (set automatically) and prohibits residential-proxy obfuscation — a single egress IP is fine and faster. ### FAQ, disclaimers & support **Is this legal?** Yes. SEC EDGAR is public-domain U.S. government data. This Actor follows SEC fair-use guidelines (identifying User-Agent, ≤10 req/s) and does not scrape any restricted source. **Is it official?** No. This is an independent third-party tool consuming the official SEC endpoints (`data.sec.gov`, `www.sec.gov`). Not affiliated with the SEC. **Do I need to register a User-Agent or rate-limit my requests?** No. We handle SEC fair-use compliance, rate limits, retries, and pagination in the background. **Can I use this as a Python SEC EDGAR API?** Yes. `ApifyClient("…").actor("dominvo/sec-edgar-ai-scraper").call(...)` is the one-line drop-in. Works from any language with an HTTP client. **Does it cover foreign issuers?** Yes — `form_20f_filings` (FPIs), `form_6k_filings` (foreign current reports), and `form_40f_filings` (Canadian) cover the non-U.S. surface. **Can I get LLM-ready output?** Yes — set `output_format: markdown` and we bundle every row into one `output.md` file ready for RAG ingestion. Or use `filing_chunks` / `filing_markdown` modes directly. **What if I need a mode that isn't built yet?** File an issue in the Issues tab. New modes ship along the priority order in the catalog; custom modes and bespoke chunking schemas are available on request. *** Built on the [Apify SDK](https://docs.apify.com/sdk/python/), [Crawlee for Python](https://crawlee.dev/python), and [`edgartools`](https://pypi.org/project/edgartools/) ≥ 5.31. Runs on a 2 GB memory tier with Apify Standby enabled. # Actor input Schema ## `mode` (type: `string`): Which mode to run. Catalog grows as new modes ship. ## `tickers` (type: `array`): Stock tickers to look up (e.g. MDB, NET). Auto-resolved to CIK. ## `ciks` (type: `array`): Raw 10-digit CIKs (zero-padded or bare). ## `companies` (type: `array`): Fuzzy company-name lookups. Only used by cik\_ticker\_map. ## `domains` (type: `array`): Website domains (TLD stripped, treated as name hint). Only used by cik\_ticker\_map. ## `date_from` (type: `string`): Earliest filing date (YYYY-MM-DD). Optional. Used by filings modes. ## `date_to` (type: `string`): Latest filing date (YYYY-MM-DD). Optional. Used by filings modes. ## `since_accession` (type: `string`): Skip filings with accession number ≤ this value. For incremental resume. ## `forms` (type: `array`): Optional list of SEC form types to filter by (e.g. \['10-K', '8-K']). Used by ai\_importance; if omitted, all forms are scored. ## `output_format` (type: `string`): json streams to the default dataset. ndjson/csv/xlsx/markdown flush to the key-value store at end of run. ## `form` (type: `string`): SEC form type to scope filing fetches (e.g. 10-K, 10-Q, S-1). Used by Tier 2 RAG/composite modes such as filing\_chunks. ## `sections` (type: `array`): Section keys to extract from each filing. Used by filing\_chunks and similar Tier 2 modes. Common keys: risk\_factors, mda, business, legal\_proceedings, icfr. ## `window_tokens` (type: `integer`): Token-window size for chunking section text. Used by filing\_chunks. ## `overlap_tokens` (type: `integer`): Token overlap between adjacent chunks. Must be < window\_tokens. Used by filing\_chunks. ## `section` (type: `string`): Single section key to diff. Used by section\_diff. ## `mode_shape` (type: `string`): section\_diff: emit one record per diff op (per\_op, default) or one bundle per filing pair (per\_section). ## `max_pairs` (type: `integer`): Cap on the number of adjacent (old, new) filing pairs diffed per issuer, newest first. Used by section\_diff. ## `model` (type: `string`): OpenRouter model slug for primary summarization. Used by ai\_summary. ## `fallback_model` (type: `string`): OpenRouter model slug used as a fallback if the primary call fails. Used by ai\_summary. ## `openrouter_api_key` (type: `string`): OpenRouter API key. If omitted, the actor reads OPENROUTER\_API\_KEY from env. Required by ai\_summary. ## `max_input_chars` (type: `integer`): Maximum character length of the combined section text passed to the LLM. Used by ai\_summary. ## `timeout` (type: `integer`): Timeout in seconds for each OpenRouter HTTP call. Used by ai\_summary. ## `lookback_quarters` (type: `integer`): Trailing window in quarters (90 days each). Used by disclosure\_compare (default 4 when date\_from omitted) and signal\_pack (default 8). ## `signals` (type: `array`): Subset of signal names to score. Omit to score all 12. Used by signal\_pack. ## `metrics` (type: `array`): Which side-by-side metrics to compute. Used by disclosure\_compare (filing\_cadence, insider\_activity, eight\_k\_severity, activist\_flag) and peer\_benchmark (gross\_margin, operating\_margin, revenue\_growth\_yoy, roe, fcf\_margin). ## `fiscal_year` (type: `integer`): Filter facts to a single fiscal year (e.g. 2024). Used by xbrl\_facts. ## `window_days` (type: `integer`): Rolling window (in days). Used by insider\_cluster (default 60) and activist\_clustering (default 90). ## `min_filers` (type: `integer`): Minimum number of unique 13D filers within the rolling window to qualify as a wolf-pack cluster. Used by activist\_clustering. ## `min_insiders` (type: `integer`): Minimum distinct insiders required to declare a cluster. Used by insider\_cluster. ## `direction` (type: `string`): Restrict clusters by trade side: buy = non-sell codes only, sell = sell-side codes only, any = either (homogeneous per cluster). Used by insider\_cluster. ## `lookahead_days` (type: `integer`): Optional cap on how far in the future a projected lockup expiration date may fall. Records with expiration\_date > today + lookahead\_days are skipped. Used by lockup\_expiration. ## `signal_types` (type: `array`): Subset of discrete signal sub-types to emit. Omit (or leave empty) for all 7. Allowed values: late\_filing, going\_concern, material\_weakness, restatement, auditor\_change, cfo\_change, ceo\_change. Used by discrete\_signals. ## `variant` (type: `string`): Which Reg A+ form variant to fetch. 'any' fetches all four. Used by form\_reg\_a\_family. ## `subtype` (type: `string`): Which SC TO sub-type to fetch. 'any' fetches both. Used by form\_to\_tender. ## `include_amendments` (type: `boolean`): When true, also fetch S-4/A amendment filings alongside S-4 originals. Used by form\_s4\_filings. ## `release_ids` (type: `array`): Specific release IDs to fetch (e.g. 'AAER-4520' for aaer\_releases, 'lr-25700' for litigation\_releases). When omitted, all index rows matching the other filters are fetched. ## `respondent_name` (type: `string`): Case-insensitive substring match against the release index title. Used by aaer\_releases and litigation\_releases. ## `year` (type: `integer`): Calendar year for the enforcement yearly archive. Defaults to current year when omitted. Used by litigation\_releases and administrative\_proceedings. ## `pair_window_days` (type: `integer`): Maximum number of days after an UPLOAD (staff letter) within which a CORRESP (registrant response) is paired. Used by comment\_letters. ## `firm_names` (type: `array`): Investment-adviser firm names to look up in IAPD. Each name resolves to one or more CRD numbers via IAPD firm search. Used by form\_adv\_filings. ## `crd_numbers` (type: `array`): Direct IAPD CRD numbers to fetch firm reports for. Bypasses firm-name search. Used by form\_adv\_filings. ## `include_disciplinary_only` (type: `boolean`): When true, emit one record per disclosure event instead of one summary record per firm. Used by form\_adv\_filings. ## `file_numbers` (type: `array`): Specific administrative-proceeding file numbers to fetch directly (e.g. '3-21800'). When set, the index is skipped. Used by administrative\_proceedings. ## `concepts` (type: `array`): XBRL concept names or patterns (e.g. \['Revenues', 'NetIncomeLoss']). Used by xbrl\_facts (filter) and xbrl\_frames (axis — at least one required). Empty = no filter on xbrl\_facts. ## `periods` (type: `array`): XBRL Frames period codes — instant ('CY2024Q1I') or duration ('CY2024Q1', 'CY2024'). At least one required by xbrl\_frames. ## `units` (type: `array`): XBRL units of measure ('USD', 'shares', 'USD/shares'). Used by xbrl\_frames. ## `taxonomy` (type: `string`): XBRL taxonomy ('us-gaap', 'ifrs-full', 'dei', 'srt'). Used by xbrl\_frames. ## `max_rows_per_frame` (type: `integer`): Cap rows emitted per (concept, period, unit) frame. Used by xbrl\_frames. ## `fiscal_periods` (type: `array`): Filter facts to specific fiscal periods (\['FY', 'Q1', 'Q2', 'Q3']). Empty = all periods. Used by xbrl\_facts. ## `statement_types` (type: `array`): Filter facts to specific statement types (\['IncomeStatement', 'BalanceSheet', 'CashFlowStatement']). Empty = all. Used by xbrl\_facts. ## `max_facts` (type: `integer`): Cap facts emitted per filing. Used by xbrl\_facts. ## `transaction_codes` (type: `array`): Form 4 transaction codes to keep (P=buy, S=sell, A=grant, M=exercise, F=tax withhold, G=gift, D=disposition, plus long-tail X/C/J/V/I/U). Empty = all codes. Used by form\_4\_filings. ## `item_codes` (type: `array`): 8-K Item numbers to keep (e.g. '2.02' earnings, '4.01' auditor change, '4.02' restatement, '5.02' exec change). Empty = all items. Used by form\_8k\_filings. ## Actor input object example ```json { "mode": "cik_ticker_map", "tickers": [ "MDB" ], "ciks": [], "companies": [], "domains": [], "forms": [], "output_format": "json", "form": "10-K", "sections": [ "risk_factors", "mda", "business" ], "window_tokens": 1024, "overlap_tokens": 256, "section": "risk_factors", "mode_shape": "per_op", "max_pairs": 3, "model": "google/gemini-2.5-flash", "fallback_model": "groq/llama-3.1-8b-instant", "max_input_chars": 80000, "timeout": 60, "lookback_quarters": 4, "signals": [], "metrics": [ "filing_cadence", "insider_activity", "eight_k_severity", "activist_flag" ], "window_days": 60, "min_filers": 2, "min_insiders": 3, "direction": "any", "signal_types": [], "variant": "any", "subtype": "any", "include_amendments": true, "release_ids": [], "pair_window_days": 90, "firm_names": [], "crd_numbers": [], "include_disciplinary_only": false, "file_numbers": [], "concepts": [], "periods": [], "units": [ "USD" ], "taxonomy": "us-gaap", "max_rows_per_frame": 5000, "fiscal_periods": [], "statement_types": [], "max_facts": 5000, "transaction_codes": [], "item_codes": [] } ``` # Actor output Schema ## `results` (type: `string`): No description # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "tickers": [ "MDB" ] }; // Run the Actor and wait for it to finish const run = await client.actor("dominvo/sec-edgar-ai-scraper").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "tickers": ["MDB"] } # Run the Actor and wait for it to finish run = client.actor("dominvo/sec-edgar-ai-scraper").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "tickers": [ "MDB" ] }' | apify call dominvo/sec-edgar-ai-scraper --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=dominvo/sec-edgar-ai-scraper", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "SEC EDGAR AI Scraper - LLM-ready filings, RAG chunks & signals", "description": "SEC EDGAR as LLM-ready data: section-aware Markdown, RAG chunks with stable IDs + SHA-256, XBRL facts, Form 4/13F, section diff, scored signals. Multi-event PPE. Pairs with sec-edgar-mcp.", "version": "0.0", "x-build-id": "nrCGQTuSU9vhRzGfB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dominvo~sec-edgar-ai-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dominvo-sec-edgar-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dominvo~sec-edgar-ai-scraper/runs": { "post": { "operationId": "runs-sync-dominvo-sec-edgar-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dominvo~sec-edgar-ai-scraper/run-sync": { "post": { "operationId": "run-sync-dominvo-sec-edgar-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "cik_ticker_map", "company_filings", "form_4_filings", "form_13d_filings", "form_13f_filings", "filing_markdown", "form_10q_filings", "form_d_filings", "form_8k_filings", "form_10k_filings", "xbrl_statements", "xbrl_facts", "xbrl_frames", "form_def14a_filings", "section_mda", "form_3_filings", "section_risk_factors", "form_5_filings", "form_13g_filings", "filing_text", "xbrl_metrics", "filings_index", "filings_feed", "filings_search", "section_icfr", "form_20f_filings", "form_s1_filings", "form_424b_prospectus", "form_s3_filings", "form_144_filings", "form_nport_filings", "form_6k_filings", "def14a_audit_fees", "def14a_exec_comp", "def14a_pay_vs_performance", "def14a_directors", "section_legal_proceedings", "section_business", "form_40f_filings", "form_atsn_filings", "section_subsidiaries", "form_ncsr_filings", "form_ncen_filings", "def14a_beneficial_owners", "form_npx_filings", "form_c_filings", "filing_chunks", "ai_importance", "section_diff", "ai_summary", "disclosure_compare", "peer_benchmark", "signal_pack", "insider_cluster", "lockup_expiration", "discrete_signals", "activist_clustering", "form_sd_disclosures", "form_25_notifications", "form_15_terminations", "form_8a_registrations", "form_reg_a_family", "form_14d9_recommendation", "form_to_tender", "form_s4_filings", "aaer_releases", "comment_letters", "administrative_proceedings", "litigation_releases", "form_adv_filings" ], "type": "string", "description": "Which mode to run. Catalog grows as new modes ship.", "default": "cik_ticker_map" }, "tickers": { "title": "Tickers", "type": "array", "description": "Stock tickers to look up (e.g. MDB, NET). Auto-resolved to CIK.", "default": [], "items": { "type": "string" } }, "ciks": { "title": "CIKs", "type": "array", "description": "Raw 10-digit CIKs (zero-padded or bare).", "default": [], "items": { "type": "string" } }, "companies": { "title": "Company names", "type": "array", "description": "Fuzzy company-name lookups. Only used by cik_ticker_map.", "default": [], "items": { "type": "string" } }, "domains": { "title": "Domains", "type": "array", "description": "Website domains (TLD stripped, treated as name hint). Only used by cik_ticker_map.", "default": [], "items": { "type": "string" } }, "date_from": { "title": "From date", "type": "string", "description": "Earliest filing date (YYYY-MM-DD). Optional. Used by filings modes." }, "date_to": { "title": "To date", "type": "string", "description": "Latest filing date (YYYY-MM-DD). Optional. Used by filings modes." }, "since_accession": { "title": "Resume since accession", "type": "string", "description": "Skip filings with accession number ≤ this value. For incremental resume." }, "forms": { "title": "Form types", "type": "array", "description": "Optional list of SEC form types to filter by (e.g. ['10-K', '8-K']). Used by ai_importance; if omitted, all forms are scored.", "default": [], "items": { "type": "string" } }, "output_format": { "title": "Output format", "enum": [ "json", "ndjson", "csv", "xlsx", "markdown" ], "type": "string", "description": "json streams to the default dataset. ndjson/csv/xlsx/markdown flush to the key-value store at end of run.", "default": "json" }, "form": { "title": "Form type", "type": "string", "description": "SEC form type to scope filing fetches (e.g. 10-K, 10-Q, S-1). Used by Tier 2 RAG/composite modes such as filing_chunks.", "default": "10-K" }, "sections": { "title": "Sections", "type": "array", "description": "Section keys to extract from each filing. Used by filing_chunks and similar Tier 2 modes. Common keys: risk_factors, mda, business, legal_proceedings, icfr.", "default": [ "risk_factors", "mda", "business" ], "items": { "type": "string" } }, "window_tokens": { "title": "Window tokens", "minimum": 1, "type": "integer", "description": "Token-window size for chunking section text. Used by filing_chunks.", "default": 1024 }, "overlap_tokens": { "title": "Overlap tokens", "minimum": 0, "type": "integer", "description": "Token overlap between adjacent chunks. Must be < window_tokens. Used by filing_chunks.", "default": 256 }, "section": { "title": "Section", "enum": [ "risk_factors", "mda", "business", "legal_proceedings", "icfr" ], "type": "string", "description": "Single section key to diff. Used by section_diff.", "default": "risk_factors" }, "mode_shape": { "title": "Output shape (section_diff)", "enum": [ "per_op", "per_section" ], "type": "string", "description": "section_diff: emit one record per diff op (per_op, default) or one bundle per filing pair (per_section).", "default": "per_op" }, "max_pairs": { "title": "Max filing pairs (section_diff)", "minimum": 1, "type": "integer", "description": "Cap on the number of adjacent (old, new) filing pairs diffed per issuer, newest first. Used by section_diff.", "default": 3 }, "model": { "title": "LLM model (ai_summary)", "type": "string", "description": "OpenRouter model slug for primary summarization. Used by ai_summary.", "default": "google/gemini-2.5-flash" }, "fallback_model": { "title": "Fallback LLM model (ai_summary)", "type": "string", "description": "OpenRouter model slug used as a fallback if the primary call fails. Used by ai_summary.", "default": "groq/llama-3.1-8b-instant" }, "openrouter_api_key": { "title": "OpenRouter API key (ai_summary)", "type": "string", "description": "OpenRouter API key. If omitted, the actor reads OPENROUTER_API_KEY from env. Required by ai_summary." }, "max_input_chars": { "title": "Max input characters (ai_summary)", "minimum": 1, "type": "integer", "description": "Maximum character length of the combined section text passed to the LLM. Used by ai_summary.", "default": 80000 }, "timeout": { "title": "LLM request timeout seconds (ai_summary)", "minimum": 1, "type": "integer", "description": "Timeout in seconds for each OpenRouter HTTP call. Used by ai_summary.", "default": 60 }, "lookback_quarters": { "title": "Lookback quarters (disclosure_compare / signal_pack)", "minimum": 1, "type": "integer", "description": "Trailing window in quarters (90 days each). Used by disclosure_compare (default 4 when date_from omitted) and signal_pack (default 8).", "default": 4 }, "signals": { "title": "Signal filter (signal_pack)", "type": "array", "description": "Subset of signal names to score. Omit to score all 12. Used by signal_pack.", "default": [], "items": { "type": "string" } }, "metrics": { "title": "Metrics (disclosure_compare / peer_benchmark)", "type": "array", "description": "Which side-by-side metrics to compute. Used by disclosure_compare (filing_cadence, insider_activity, eight_k_severity, activist_flag) and peer_benchmark (gross_margin, operating_margin, revenue_growth_yoy, roe, fcf_margin).", "default": [ "filing_cadence", "insider_activity", "eight_k_severity", "activist_flag" ], "items": { "type": "string" } }, "fiscal_year": { "title": "Fiscal year (xbrl_facts)", "type": "integer", "description": "Filter facts to a single fiscal year (e.g. 2024). Used by xbrl_facts." }, "window_days": { "title": "Window days (insider_cluster / activist_clustering)", "minimum": 1, "type": "integer", "description": "Rolling window (in days). Used by insider_cluster (default 60) and activist_clustering (default 90).", "default": 60 }, "min_filers": { "title": "Min filers per cluster (activist_clustering)", "minimum": 2, "type": "integer", "description": "Minimum number of unique 13D filers within the rolling window to qualify as a wolf-pack cluster. Used by activist_clustering.", "default": 2 }, "min_insiders": { "title": "Min insiders (insider_cluster)", "minimum": 2, "type": "integer", "description": "Minimum distinct insiders required to declare a cluster. Used by insider_cluster.", "default": 3 }, "direction": { "title": "Direction (insider_cluster)", "enum": [ "buy", "sell", "any" ], "type": "string", "description": "Restrict clusters by trade side: buy = non-sell codes only, sell = sell-side codes only, any = either (homogeneous per cluster). Used by insider_cluster.", "default": "any" }, "lookahead_days": { "title": "Lookahead days (lockup_expiration)", "minimum": 1, "type": "integer", "description": "Optional cap on how far in the future a projected lockup expiration date may fall. Records with expiration_date > today + lookahead_days are skipped. Used by lockup_expiration." }, "signal_types": { "title": "Signal type filter (discrete_signals)", "type": "array", "description": "Subset of discrete signal sub-types to emit. Omit (or leave empty) for all 7. Allowed values: late_filing, going_concern, material_weakness, restatement, auditor_change, cfo_change, ceo_change. Used by discrete_signals.", "default": [], "items": { "type": "string" } }, "variant": { "title": "Reg A+ variant (form_reg_a_family)", "enum": [ "1-A", "1-K", "1-SA", "1-U", "any" ], "type": "string", "description": "Which Reg A+ form variant to fetch. 'any' fetches all four. Used by form_reg_a_family.", "default": "any" }, "subtype": { "title": "SC TO subtype (form_to_tender)", "enum": [ "TO-I", "TO-T", "any" ], "type": "string", "description": "Which SC TO sub-type to fetch. 'any' fetches both. Used by form_to_tender.", "default": "any" }, "include_amendments": { "title": "Include amendments (form_s4_filings)", "type": "boolean", "description": "When true, also fetch S-4/A amendment filings alongside S-4 originals. Used by form_s4_filings.", "default": true }, "release_ids": { "title": "Release IDs (aaer_releases / litigation_releases)", "type": "array", "description": "Specific release IDs to fetch (e.g. 'AAER-4520' for aaer_releases, 'lr-25700' for litigation_releases). When omitted, all index rows matching the other filters are fetched.", "default": [], "items": { "type": "string" } }, "respondent_name": { "title": "Respondent name (aaer_releases / litigation_releases)", "type": "string", "description": "Case-insensitive substring match against the release index title. Used by aaer_releases and litigation_releases." }, "year": { "title": "Year (litigation_releases / administrative_proceedings)", "minimum": 1995, "type": "integer", "description": "Calendar year for the enforcement yearly archive. Defaults to current year when omitted. Used by litigation_releases and administrative_proceedings." }, "pair_window_days": { "title": "Pair window days (comment_letters)", "minimum": 1, "type": "integer", "description": "Maximum number of days after an UPLOAD (staff letter) within which a CORRESP (registrant response) is paired. Used by comment_letters.", "default": 90 }, "firm_names": { "title": "IAPD firm names (form_adv_filings)", "type": "array", "description": "Investment-adviser firm names to look up in IAPD. Each name resolves to one or more CRD numbers via IAPD firm search. Used by form_adv_filings.", "default": [], "items": { "type": "string" } }, "crd_numbers": { "title": "IAPD CRD numbers (form_adv_filings)", "type": "array", "description": "Direct IAPD CRD numbers to fetch firm reports for. Bypasses firm-name search. Used by form_adv_filings.", "default": [], "items": { "type": "string" } }, "include_disciplinary_only": { "title": "Disciplinary events only (form_adv_filings)", "type": "boolean", "description": "When true, emit one record per disclosure event instead of one summary record per firm. Used by form_adv_filings.", "default": false }, "file_numbers": { "title": "File numbers (administrative_proceedings)", "type": "array", "description": "Specific administrative-proceeding file numbers to fetch directly (e.g. '3-21800'). When set, the index is skipped. Used by administrative_proceedings.", "default": [], "items": { "type": "string" } }, "concepts": { "title": "XBRL concepts", "type": "array", "description": "XBRL concept names or patterns (e.g. ['Revenues', 'NetIncomeLoss']). Used by xbrl_facts (filter) and xbrl_frames (axis — at least one required). Empty = no filter on xbrl_facts.", "default": [], "items": { "type": "string" } }, "periods": { "title": "Periods (xbrl_frames)", "type": "array", "description": "XBRL Frames period codes — instant ('CY2024Q1I') or duration ('CY2024Q1', 'CY2024'). At least one required by xbrl_frames.", "default": [], "items": { "type": "string" } }, "units": { "title": "Units (xbrl_frames)", "type": "array", "description": "XBRL units of measure ('USD', 'shares', 'USD/shares'). Used by xbrl_frames.", "default": [ "USD" ], "items": { "type": "string" } }, "taxonomy": { "title": "Taxonomy (xbrl_frames)", "enum": [ "us-gaap", "ifrs-full", "dei", "srt" ], "type": "string", "description": "XBRL taxonomy ('us-gaap', 'ifrs-full', 'dei', 'srt'). Used by xbrl_frames.", "default": "us-gaap" }, "max_rows_per_frame": { "title": "Max rows per frame (xbrl_frames)", "minimum": 1, "type": "integer", "description": "Cap rows emitted per (concept, period, unit) frame. Used by xbrl_frames.", "default": 5000 }, "fiscal_periods": { "title": "Fiscal periods (xbrl_facts)", "type": "array", "description": "Filter facts to specific fiscal periods (['FY', 'Q1', 'Q2', 'Q3']). Empty = all periods. Used by xbrl_facts.", "default": [], "items": { "type": "string" } }, "statement_types": { "title": "Statement types (xbrl_facts)", "type": "array", "description": "Filter facts to specific statement types (['IncomeStatement', 'BalanceSheet', 'CashFlowStatement']). Empty = all. Used by xbrl_facts.", "default": [], "items": { "type": "string" } }, "max_facts": { "title": "Max facts per filing (xbrl_facts)", "minimum": 1, "type": "integer", "description": "Cap facts emitted per filing. Used by xbrl_facts.", "default": 5000 }, "transaction_codes": { "title": "Transaction codes (form_4_filings)", "type": "array", "description": "Form 4 transaction codes to keep (P=buy, S=sell, A=grant, M=exercise, F=tax withhold, G=gift, D=disposition, plus long-tail X/C/J/V/I/U). Empty = all codes. Used by form_4_filings.", "default": [], "items": { "type": "string" } }, "item_codes": { "title": "8-K item codes (form_8k_filings)", "type": "array", "description": "8-K Item numbers to keep (e.g. '2.02' earnings, '4.01' auditor change, '4.02' restatement, '5.02' exec change). Empty = all items. Used by form_8k_filings.", "default": [], "items": { "type": "string" } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```