# stocks_get_recent_filings Universe-wide SEC EDGAR filed-since feed, newest first. | Field | Value | | --- | --- | | Category | Stocks (`stocks`) | | Exposure | public | | MCP tool | `stocks_get_recent_filings` | | Documentation | https://www.agentdatasets.com/docs/tools/stocks_get_recent_filings | ## Description Universe-wide SEC EDGAR filed-since feed, newest first. Use this for polling "what filed since T" across the ingested universe or a bounded portfolio/list of tickers. Use `stocks_get_sec_filings` instead when you want one company's filing history or need to resolve by CIK. The result is the shared response envelope. `data` echoes the applied filters (`filed_after`, canonicalized `form_types`, canonicalized `tickers`) and contains the bounded `filings` list; `meta` holds provenance (`source`: "sec-edgar-submissions", and `as_of`, the freshest metadata timestamp on this page); `pagination` holds cursor paging state. Each row carries filing metadata and sec.gov links plus company identity (`ticker`, which may be null when the filer has no active ticker mapping, `cik`, `company_name`). Results are bounded per page: default 100, maximum 1000. To page, pass `pagination.next_cursor` back as `cursor`; when `pagination.has_more` is false, `next_cursor` is null and you have reached the oldest matching filing. Errors carry a machine `code`: `unknown_entity` for a well-formed ticker we hold no mapping for, and `bad_parameter` for malformed tickers, malformed cursors, or list/limit bounds the schema cannot reject. Example: `stocks_get_recent_filings(filed_after="2026-07-01", form_types=["10-K", "8-K"], tickers=["AAPL", "MSFT"], limit=25)`. ## Parameters Input schema advertised to MCP clients and mirrored by the REST query string. | Parameter | In | Type | Required | Default | Constraints | Description | | --- | --- | --- | --- | --- | --- | --- | | filed_after | input | `string (date) \| null` | no | null | — | Earliest filing date to include, inclusive (ISO 'YYYY-MM-DD'). Omit to start from the newest filings in the ingested universe. | | form_types | input | `array \| null` | no | null | max items 10 | Optional EDGAR form filters, up to 10 repeated values, e.g. ['10-K', '10-Q', '8-K']. Values are canonicalized with strip/upper and matched exactly; amendments carry '/A'. Omit to include all forms. | | tickers | input | `array \| null` | no | null | max items 20 | Optional ticker symbols to bound the feed, up to 20 values, e.g. ['AAPL', 'MSFT']. Each symbol is resolved through the ingested ticker universe; omit for all companies. | | limit | input | `integer` | no | 100 | min 1, max 1000 | Filings to return, newest first (1-1000). | | cursor | input | `string \| null` | no | null | — | Opaque pagination cursor from a previous response's `pagination.next_cursor`; omit to start from the newest filing. | ## Provenance - `sec-edgar-submissions` — U.S. Securities and Exchange Commission (EDGAR), Filing metadata only — form type, filing date, period of report, accession number, item codes — plus links to source documents on sec.gov; this connector never fetches or stores document contents (section extraction is `sec-edgar-archives`) (U.S. Government work, public domain (17 U.S.C. § 105)). See https://www.agentdatasets.com/docs/attribution.md Dataset registry: `stocks_filings`.