mcp-edgar

SEC EDGAR — Public Company Filings

The Securities and Exchange Commission's filings database. Every public company in the US files here, every filing is timestamped and immutable, and every disclosure (revenue, debt, risk factors, executive compensation, M&A activity, insider trading) is structured for machine retrieval. Free and authoritative.

Part of Pipeworx — an MCP gateway connecting AI agents to 1855+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Why this matters for AI agents

If your agent is answering anything about a US public company — financials, legal exposure, IP, executive turnover, recent material events — the answer is in EDGAR. The data is structured (XBRL), so you don't have to parse PDFs.

The two key flows — and the one call that does both:

0. Snapshot (one call). "Give me the SEC picture on Apple." → edgar_company_snapshot({ticker_or_cik: "AAPL"}) → CIK + the recent substantive filings (10-K/10-Q/8-K/20-F/40-F/6-K/DEF 14A by default; Form 4 noise excluded unless you ask for form_type: "all") + the headline XBRL figures from the latest annual report (revenue, net income, assets, cash, EPS…). This is flows 1 and 2 collapsed: the resolve → list → pull chain that depth users otherwise assemble by hand three calls at a time. A filer with no XBRL (a fund or trust) still returns its filings with financials_status: "unavailable" and the reason. edgar_ticker_to_cik now returns a next hint pointing here.

1. Filings flow. "Show me Apple's recent 10-Q." → edgar_ticker_to_cik("AAPL") → edgar_company_filings(cik) → list of filings with accession numbers, form types, filing dates.

2. Concepts flow. "What was Apple's revenue trend the last 4 quarters?" → edgar_company_concept(cik, "Revenues") → time series of XBRL-tagged values across periods.

3. Peer/competitor flow. "Who competes with Apple?" → edgar_companies_by_sic({ticker_or_cik: "AAPL"}) → resolves Apple's own SIC code (3571, Electronic Computers) and returns other SEC filers under that code, listed-ticker peers first. Pass a sic code directly instead of a company to browse an industry cold.

4. Entity-resolution flow (parent ↔ subsidiary). sponsor_to_filer({sponsor: "Merck Sharp and Dohme"}) resolves a subsidiary/operating name up to its listed parent (MRK). filer_to_sponsors({ticker_or_cik: "MRK"}) goes the other way — the parent's full disclosed subsidiary list from Exhibit 21 of its latest 10-K, with jurisdiction and filing provenance. Pass name_filter to check one candidate name without reading the whole list.

5. Product-level revenue. "How much revenue did Keytruda generate?" → edgar_product_revenue({ticker_or_cik: "MRK", product_filter: "Keytruda"}). edgar_company_concept/edgar_company_facts only expose undimensioned XBRL totals — a product/segment breakdown is tagged with an XBRL dimension (a "Keytruda [Member]"), invisible to those APIs. This reads SEC's own rendered Financial Report of that dimensional data straight out of the revenue-disaggregation note, with a citation (accession, filing date, report URL). With no form_type it resolves 10-K, then 20-F, then 40-F, so foreign private issuers work the same way (edgar_product_revenue({ticker_or_cik: "NVS", product_filter: "Entresto"}) reads Novartis's 20-F); the form actually used comes back as resolved_form. Not every filer tags product-level revenue in XBRL — Neurocrine discloses revenue by major customer and United Therapeutics only its recognition policy, and both return an explicit not_found rather than an empty array.

6. Operating KPIs that never reach XBRL (press releases). "Tesla's Q3 2026 vehicle deliveries and production" / "how much energy storage did Tesla deploy." A company's quarterly production, delivery, and shipment/deployment KPIs are reported in its press release — the exhibit attached to an 8-K — not in the structured financial statements, so edgar_company_concept/edgar_company_facts correctly have nothing to return for them. edgar_filing_exhibit_text({ticker_or_cik: "TSLA", filed: "2026-10"}) reads the exhibit text directly (the 8-K's OWN primary document typically just says "see the attached exhibit" and carries none of the numbers) and defaults to the EX-99.* attachment, the universal convention for an Item 2.02/7.01 earnings or KPI release. Pass search for a specific figure ("vehicle deliveries", "Megapack", "same-store sales") instead of reading the whole release. Generalizes to any US filer's 8-K press release, not just Tesla's.

Both flows are usually preceded by edgar_ticker_to_cik or resolve_entity({type: "company", value: "AAPL"}) to get the canonical 10-digit CIK.

Auth

None. SEC EDGAR is a free, public, no-auth service. Pipeworx forwards a polite User-Agent header to comply with SEC's API guidelines.

Citable URIs

pipeworx://edgar/company/{cik}/filings
pipeworx://edgar/company/{cik}/facts

Embed in your output. Stable across reorganizations — companies rebrand, but their CIK doesn't change.

Form types worth knowing

For insider trades specifically, see the dedicated insider-trading pack — it surfaces Form 4 / 13D / 13G changes with cleaner schemas.

Common pitfalls

• Concept name drift. SEC filers occasionally change the XBRL concept they tag for revenue. The default Revenues concept may be stale for newer fiscal years; try RevenueFromContractWithCustomerExcludingAssessedTax as a fallback.

• Period mismatches. Fiscal years end at different times across companies (Apple = Sept, Microsoft = June, Google = Dec). When comparing, always disclose the period.

• CIK formatting. Some endpoints want zero-padded 10-digit (0000320193), some want unpadded (320193). Pipeworx accepts either; the cik_padded field in edgar_ticker_to_cik is the canonical form for resource URIs.

• Real-time-ish, not real-time. Filings appear on EDGAR within minutes of submission, but Pipeworx caches results. For breaking-news-grade timeliness, set Cache-Control: no-cache (anonymous limit applies) or check the _meta.cache.fresh_until field.

• Concept availability differs. Smaller filers tag fewer XBRL concepts than large ones. edgar_company_concept may return empty arrays for valid concepts that the company simply doesn't report. Use edgar_company_facts to see which concepts a company DOES report.

• The company argument is spelled three different ways across this pack, and edgar_company_concept accepts all of them. edgar_company_filings/edgar_insider_transactions/edgar_product_revenue name it ticker_or_cik, edgar_fund_holdings/edgar_ticker_to_cik name it ticker, and edgar_company_concept/edgar_company_facts name it cik (which takes a ticker too). A model filling arguments reaches for whichever word it read last, so edgar_company_concept declares ticker and ticker_or_cik as aliases of cik, and metric as an alias of concept. Measured before that change (fleet #2058): of 11 times the ask_pipeworx adjudicator selected this tool over 16 never-before-asked questions, 9 calls were rejected by the gateway's required-argument pre-flight — every one of them because it had sent ticker or ticker_or_cik rather than cik, and a third of those sent metric rather than concept as well. Both calls that used cik+concept succeeded. The outcome recorded for the rejected ones was partial, not an error, because a single-tool selection that arrives as a one-element tools array runs the fan-out branch — so the word for "the only lookup never ran" was the same word used for "some of several lookups ran".

• A filing you did not NAME is a filing we CHOSE, and the envelope now says which (fleet #3319). edgar_filing_text and edgar_filing_documents auto-resolve the LATEST filing of form_type when accession is omitted, and every field then describes that filing as though it had been asked for. Measured live 2026-10-18: a grounded question about "Tesla's September 29 2026 8-K" reached edgar_filing_text({ticker:"TSLA", form_type:"8-K", search:"credit facility"}), resolved to the 2026-10-02 8-K — a different filing, 3,061 chars, zero matches — and refused not_in_source 5 tries out of 5, while the filing asked about sat one row further down the same index with all three credit tranches in it. So every response carries accession_source ("caller" | "auto_selected") plus, when we chose, an auto_selected block naming what was requested, what was picked, what was read with its exact-match count, and the candidates that were not read. Pass filed ("2026-09-29", "2026-09", "September 29, 2026") whenever the question names a date; for an 8-K the newest filing is routinely not the one meant. When only a search is available, edgar_filing_text reads on past a candidate whose text contains no exact match (bounded to 4 documents, exact matches only), and if none match it falls back to the newest WITH a warning that a zero-match result there is inconclusive about the company rather than about that filing.