Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Edgar Company Facts Filings

БесплатноНе проверен

SEC EDGAR filings and XBRL financial facts for AI agents (ticker/CIK/name). Apify Actor + MCP.

GitHubEmbed

Описание

SEC EDGAR filings and XBRL financial facts for AI agents (ticker/CIK/name). Apify Actor + MCP.

README

Resolves US tickers, CIKs or company names via SEC EDGAR and returns filings and XBRL financial facts as structured rows, from $1.50 per 1,000 companies. You pay $0.0015 per resolved company, $0.001 per filing row, $0.0002 per fact row and $0.002 per text excerpt. Error rows are free. Example: 2 companies with 5 filings each and 16 fact rows each cost 2 × $0.0015 + 10 × $0.001 + 32 × $0.0002 = $0.02, plus Apify's $0.00005 Actor-start fee.

Apify Store · MCP via Apify · Contact: [email protected]

Public Apify Actor that turns the SEC’s public EDGAR data into clean, structured rows for AI agents and MCP clients. Look up by ticker, CIK, or company name. Returns official entity metadata, recent filings (10-K, 10-Q, 8-K and more) with document URLs, XBRL company facts (Assets, Revenues, NetIncomeLoss, diluted EPS and more), and optional plain-text excerpts. Every row carries a schema version, a source SEC URL, and a timestamp. Errors are machine-readable codes.

Not investment advice. Output is a structured mirror of public SEC EDGAR data for research and tooling. It is not a recommendation to buy, sell, or hold any security.

When to use this (LLM / tool selection)

Use this Actor when an agent needs:

  • Map a ticker, CIK, or company name → official SEC CIK / entity metadata
  • Recent SEC filings (10-K, 10-Q, 8-K, …) with document URLs
  • XBRL company facts (Assets, NetIncomeLoss, EPS, …) from companyfacts
  • Optional plain-text excerpts from primary filing documents

Do not use it for realtime quotes, options chains, insider Form 4 parsing beyond what submissions expose, or non-US registries.

MCP connection (Apify hosted)

Connect any MCP client to Apify’s MCP server with this Actor scoped in:

{
  "mcpServers": {
    "fairquery-edgar": {
      "type": "http",
      "url": "https://mcp.apify.com/?tools=fetch-actor-details,fairquery/edgar-company-facts-filings"
    }
  }
}

Clients without OAuth can add "headers": {"Authorization": "Bearer <APIFY_TOKEN>"}.

MCP URL: https://mcp.apify.com/?tools=fetch-actor-details,fairquery/edgar-company-facts-filings

Actor id: fairquery/edgar-company-facts-filings (lowercase).

Example agent prompts

  • "Using the EDGAR tool, get Apple's and Microsoft's 10-K and 10-Q filings since 2023 and their latest Assets, NetIncomeLoss and diluted EPS."
  • "Find the CIK for Nvidia and list its last five 8-K filings with links."

Local stdio MCP server

This repo also ships a stdio MCP server (TypeScript, @modelcontextprotocol/sdk) under mcp/ with single-purpose tools. Six are free and call sec.gov directly (no token, brand User-Agent Fairquery, throttled to ≤5 req/s); one optional bulk tool runs the Apify Actor. initialize and tools/list work without a token.

Tool What it does Paging Cost
edgar_resolve_company Ticker / CIK / name fragment → SEC CIK, ticker, registrant name – free
edgar_list_filings One company's filings, filter by formTypes, since, until; optional full history limit/offset free
edgar_get_filing_document Primary (or named) filing document from sec.gov Archives as plain text, by URL or accession number offset/maxChars (chars) free
edgar_get_filing_index Every file of one filing (primary document, exhibits, XBRL data files) with SEC document type, size and a direct URL, plus header facts (form, filing date, period, 8-K items, filers), from the EDGAR filing index page; optional docTypes filter limit/offset free
edgar_get_company_facts XBRL facts: list available concepts (with search) or time series for concepts, filter by form / fiscal period / date limit/offset free
edgar_get_concept_across_companies One concept for one period across all filers (SEC frames API), sortable, optional company filter limit/offset free
edgar_batch_export Multi-company export of filings + facts + excerpts via the Apify Actor – pay-per-event, needs APIFY_TOKEN

Paged tools return {count, total, offset, hasMore, nextOffset, meta, items}. Errors are returned as {error, message, retryable} with codes such as COMPANY_NOT_FOUND, FILING_NOT_FOUND, NOT_FOUND, INVALID_URL, SEC_FETCH_FAILED.

Live test of all free tools: cd mcp && npm run build && node scripts/live-test.mjs.

Install & run (Node)

cd mcp
npm install
npm run build
node dist/index.js            # free tools
APIFY_TOKEN=your_token node dist/index.js   # also enables edgar_batch_export

MCP client config (Cursor / Claude Desktop)

{
  "mcpServers": {
    "fairquery-edgar": {
      "command": "node",
      "args": ["/absolute/path/to/edgar-company-facts-filings/mcp/dist/index.js"],
      "env": {
        "APIFY_TOKEN": "your_apify_token"
      }
    }
  }
}

Docker

Build from mcp/:

cd mcp
docker build -t fairquery-edgar-mcp .
docker run -i -e APIFY_TOKEN=your_token fairquery-edgar-mcp

The repo-root Dockerfile builds this stdio MCP server (build context = repository root) and is what Glama uses. The Apify Actor image is built from .actor/Dockerfile.

Glama

glama.json lists fairquery as maintainer. After Glama indexes the server, claim ownership if needed.

Data sources (SEC fair access)

Resource URL
Tickers map https://www.sec.gov/files/company_tickers.json
Submissions https://data.sec.gov/submissions/CIK##########.json
Company facts https://data.sec.gov/api/xbrl/companyfacts/CIK##########.json

The Actor sends User-Agent: Fairquery [email protected] and throttles to ≤ 5 requests/second.

Input

Field Type Default Description
companies string[] — Tickers (AAPL), CIKs (320193), or name fragments (Apple)
mode filings | facts | both both Which row types to emit (always emits company when resolved)
formTypes string[] ["10-K","10-Q","8-K"] Form filter (case-insensitive); pass [] for all forms
since YYYY-MM-DD — Keep filings with filingDate >= since
maxFilingsPerCompany int (1–200) 5 Cap filing rows per company
metrics string[] ["Assets","NetIncomeLoss","EarningsPerShareDiluted","Revenues"] XBRL concept names (case-insensitive); [] uses a curated 10-concept us-gaap set
maxFactsPerMetric int (1–50) 4 Most-recent values per concept/unit
includeTextExcerpt bool false Fetch primary document text
excerptMaxChars int (200–20,000) 2000 Excerpt length cap in characters

Example input

{
  "companies": ["AAPL", "MSFT"],
  "mode": "both",
  "formTypes": ["10-K", "10-Q"],
  "since": "2023-01-01",
  "maxFilingsPerCompany": 5,
  "metrics": ["Assets", "NetIncomeLoss", "EarningsPerShareDiluted"],
  "includeTextExcerpt": false
}

Minimal:

{"companies":["AAPL"],"mode":"both","formTypes":["10-K"],"metrics":["Assets","NetIncomeLoss"]}

Output

One dataset row per company, filing, fact, text excerpt, or error. Every row includes:

  • schema_version — currently 1.0.0
  • type — company | filing | fact | text_excerpt | error
  • source_url — SEC URL the row came from
  • scraped_at — ISO timestamp

Error rows (machine-readable)

{
  "schema_version": "1.0.0",
  "type": "error",
  "code": "COMPANY_NOT_FOUND",
  "message": "Could not resolve company query: ZZNOTREAL",
  "retryable": false,
  "query": "ZZNOTREAL",
  "source_url": "https://data.sec.gov/"
}

Codes include: INPUT_EMPTY, COMPANY_NOT_FOUND, RESOLVE_FAILED, SUBMISSIONS_FETCH_FAILED, FACTS_FETCH_FAILED, EXCERPT_FETCH_FAILED.

Run summary

Key-value store record RUN_SUMMARY with counts, SEC request total, and echoed input.

Fact order: for each concept and unit, fact rows are sorted by period end date (newest first), then by filing date. A value that later filings re-report (for example the prior-year column of a 10-Q) is returned once, from the latest filing, so maxFactsPerMetric gives you the most recent periods.

Pricing

No subscription. You pay for these events:

Event Price When
company-resolved $0.0015 Each successfully resolved company row
filing $0.001 Each filing row
financial-fact $0.0002 Each XBRL fact row
text-excerpt $0.002 Each primary-document text excerpt row
apify-actor-start $0.00005 Once per run, per GB of memory (Apify default event)

Error rows (COMPANY_NOT_FOUND, FACTS_FETCH_FAILED, …) are not charged.

Worked example: {"companies": ["AAPL", "MSFT"], "mode": "both", "maxFilingsPerCompany": 5, "metrics": ["Assets", "NetIncomeLoss", "EarningsPerShareDiluted", "Revenues"], "maxFactsPerMetric": 4} returns 2 company rows, up to 10 filing rows and up to 32 fact rows: 2 × $0.0015 + 10 × $0.001 + 32 × $0.0002 = $0.02 at most, plus $0.00005. Turning on includeTextExcerpt adds $0.002 per filing.

To cap spend, use mode: "facts" or "filings", lower maxFilingsPerCompany / maxFactsPerMetric, or set a maximum cost per run in the run options (the Actor stops cleanly at the limit). Prices are from the Store pricing tab (October 2026).

Memory / runtime

Default 256 MB, timeout 300s. HTTP-only (no browser).

Troubleshooting

Symptom Cause and fix
API call rejected: companies is required The input had no companies. The sample tickers in the Console form are prefill only and are not sent with API calls.
COMPANY_NOT_FOUND The ticker, CIK or name fragment is not in the SEC ticker map (for example a non-US or delisted company). Try the CIK. These rows are free.
Fewer filings than expected formTypes defaults to 10-K, 10-Q and 8-K. Pass [] for all forms, and check since and maxFilingsPerCompany.
A metric is missing from the facts The company does not report that us-gaap concept (for example Revenues vs RevenueFromContractWithCustomerExcludingAssessedTax). Use the exact XBRL concept name. Some concepts stop being reported: Apple's Revenues values end in 2018, while RevenueFromContractWithCustomerExcludingAssessedTax is current.
SUBMISSIONS_FETCH_FAILED / FACTS_FETCH_FAILED SEC servers were slow or rate-limiting (retryable: true). The Actor stays at or below 5 requests/second; re-run later.

FAQ

Where does the data come from?

From the SEC's public EDGAR JSON endpoints (ticker map, submissions, companyfacts), fetched with a declared User-Agent under SEC fair-access rules.

Is this investment advice?

No. It is a structured mirror of public SEC data for research and tooling.

Does it include real-time prices or non-US companies?

No. It covers SEC registrants only, with no market data.

How much does a run cost?

From $0.0015 per resolved company, plus $0.001 per filing row, $0.0002 per fact row and $0.002 per excerpt. A two-company example with filings and facts costs about $0.02.

Can an AI agent call it?

Yes, through Apify MCP (see the scoped URL in the MCP section above). The stdio MCP server in the GitHub repo also has free tools that query sec.gov directly.

Fairquery family

Other Fairquery tools on the Apify Store. Each one returns structured rows with machine-readable error codes, and error rows are never charged:

All Fairquery Actors: https://apify.com/fairquery

Kits & templates

Optional guides from Fairquery for wiring this Actor into agents and automations (the Actor works fine without them):

Disclaimer

Data originates from the U.S. Securities and Exchange Commission EDGAR system. Fairquery and this Actor provide no warranty of completeness or fitness for trading decisions. This is not investment advice.

Links

Development

Local development, tests and deployment notes are in DEVELOPMENT.md. The Apify Store README is .actor/README.md.

from github.com/fairquery/edgar-company-facts-filings

Установка Edgar Company Facts Filings

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/fairquery/edgar-company-facts-filings

FAQ

Edgar Company Facts Filings MCP бесплатный?

Да, Edgar Company Facts Filings MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Edgar Company Facts Filings?

Нет, Edgar Company Facts Filings работает без API-ключей и переменных окружения.

Edgar Company Facts Filings — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить Edgar Company Facts Filings в Claude Desktop, Claude Code или Cursor?

Открой Edgar Company Facts Filings на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

$5

Stripe

Payments, customers, subscriptions

Stripeавтор: Stripe

malamutemayhem/unclick-agent-native-endpoints

110+ tools for AI agents spanning social media, finance, gaming, music, AU-specific services, and utilities. Zero-config local tools plus platform connectors. n

malamutemayhemавтор: malamutemayhem

whiteknightonhorse/APIbase

API hub covering travel (Amadeus, Sabre), Polymarket prediction markets, crypto and weather, paid per call via x402 in USDC.

whiteknightonhorseавтор: whiteknightonhorse

trackerfitness729-jpg/sitelauncher-mcp-server

Deploy live HTTPS websites on subdomains or custom .xyz domains, paid in USDC on Base, with templates for crypto tokens and AI agent profiles.

trackerfitness729-jpgавтор: trackerfitness729-jpg

embeddedlayers/mcp-analytics

Statistical analysis, forecasting and ML on CSV files or live data from Shopify, Stripe, GA4 and more, with interactive HTML reports.

embeddedlayersавтор: embeddedlayers

carrierone/verilexdata-mcp

Pay-per-query x402 datasets: NPI healthcare, SEC filings, OFAC sanctions, crypto whales, Polymarket signals, patents and economic indicators.

carrieroneавтор: carrierone

paracetamol951/P-Link-MCP

HTTP 402 (Payment Required) implementation using Solana.

paracetamol951автор: paracetamol951

tipdotmd/tip-md-x402-mcp-server

Cryptocurrency tipping using the x402 payment protocol and CDP Wallet.

tipdotmdавтор: tipdotmd

laundromatic/shopgraph

Structured product data from the open web — Schema.org + AI extraction for e-commerce enrichment. Pay per call via Stripe. [shopgraph.dev](https://shopgraph.dev

laundromaticавтор: laundromatic

mrslbt/xendit-mcp

Xendit payment gateway for Southeast Asia: invoices, disbursements, balance checks and bank transfers.

mrslbtавтор: mrslbt

Compare Edgar Company Facts Filings with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории finance