Skip to main content
Glama
Signal8 MCP Server

Signal8 MCP Server

Official

Search SEC Filings

search_sec_filings
Read-only

Search SEC filings by company, form type, date range, 8-K items, or full-text query; filter by company facts and page through results.

Instructions

Search and list SEC filings by company (CIK), form type, date range, 8-K item codes and excluded forms, optionally with a full-text query over filing bodies and by company facts (market cap, float, price, sector, industry, exchange, company type, foreign issuer, recent IPO). Rows carry id (the internal filingId used by the filing-document and exhibit tools), cik, company_name, accession_number, form_type, filing_date, acceptedAt, primaryDocument, bodyStored and itemNumbers (plus rank and snippet with q); pagination has total, totalRelation ("eq" exact; "gte" a lower bound cut at 10,000, when totalEstimate is "about N"), hasMore and nextCursor. The ciks filter matches the filing's own CIK: a Form 4 filed under the reporting owner's CIK is not returned for the issuer's CIK. Coverage: Signal8's SEC EDGAR archive, updated through the day, in its held range (see archiveFrom in each response; currently from late 2021, expanding back to 2016 as the history backfill fills in). Before archiveFrom it holds only a scatter, so absence before archiveFrom is not evidence a filing was never filed; SEC EDGAR itself covers earlier periods. Record-only rows (bodyStored: false) have no stored body; the document is at its sec.gov URL. Every response carries archiveFrom and rangeStartsBeforeArchive: a range with no dateFrom or starting before archiveFrom is not definitive (searchIndex.complete: false, reason: "outside_held_range", heldFrom): an empty result then means the archive holds no match from archiveFrom onward, not that no such filing exists. An empty text result is definitive only when searchIndex.complete is true. Full-text q: Query syntax: unquoted words all have to appear (any order, any distance); "quoted phrase" = exact wording; OR between alternatives (merger OR acquisition); -word or -"phrase" to exclude; w1 NEAR/10 w2 (also NEAR(10), or bare NEAR = within 10) = words close together; word* = prefix of 4+ letters (dilut* matches dilution, dilutive); $AAPL or a capitalised ticker scopes to that company; a form code (8-K, 10-Q, S-1), "item 5.02" / "8-K 1.05" and a bare year (2024) scope to that form / 8-K item / year. The archive's reading of the query is in meta.understanding (understand=false searches the words literally). facets=true adds facets per form / year / 8-K item over the whole result set (absent = not measured, never zero). sort=relevance caps page 1 per company; meta.diversity {maxPerCompany, hidden} names who has more (page with nextCursor or filter by CIK). section / exhibitTypes filters apply only when meta.sections / appliedFilters confirm them; otherwise meta.unsupported says why and the whole filing was searched. Company filters (minMarketCap … recentIpo): only issuer-filed forms are searched (third-party Form 4 / 144 / 13D/G go to companyFilter.droppedForms unless companyFilter.subjectMatch is true; with no formTypes the default is 10-K, 10-Q, 8-K, S-1, S-3, DEF 14A, 20-F, 40-F, 6-K); companies with no measured value are excluded, never assumed (companyFilter.unknown counts them); an unknown value is a 400 listing allowed names; when the archive cannot answer, the call fails with COMPANY_FILTER_NOT_APPLIED and never returns unfiltered rows; results are cursor-paged, cannot combine with acceptedFrom/acceptedTo/bodyStored, and carry no snippet. Results are filings, not a company list or count.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_sec_filings"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoFull-text query over filing bodies. Query syntax: unquoted words all have to appear (any order, any distance); "quoted phrase" = exact wording; OR between alternatives (merger OR acquisition); -word or -"phrase" to exclude; w1 NEAR/10 w2 (also NEAR(10), or bare NEAR = within 10) = words close together; word* = prefix of 4+ letters (dilut* matches dilution, dilutive); $AAPL or a capitalised ticker scopes to that company; a form code (8-K, 10-Q, S-1), "item 5.02" / "8-K 1.05" and a bare year (2024) scope to that form / 8-K item / year. Example: '$AAPL "share repurchase" -"no longer"', 'cyber* NEAR/10 incident', 'item 5.02 resign*'.
ciksNoComma-separated CIK numbers to filter by (e.g., "320193,1018724"; zero-padded also accepted)
pageNoPage number (1-indexed, default: 1). Ignored when cursor is set; not allowed with company filters.
sortNonewest (by acceptance time, default) or relevance (requires q; best match first)
itemsNoComma-separated 8-K item codes, all required (e.g., "2.02,9.01" = results + financial statements; "5.02" = officer/director changes; "1.01" = material agreements; "3.01" = delisting notice).
matchNoWord matching for q. exact = a word matches only itself ("split" does not match "splits" or "splitting"), which is EDGAR full-text search's own behaviour; stemmed = English word variations also match. Default when omitted: stemmed. The mode actually applied is in the response's meta.matchMode (with meta.matchModeFallbackReason when it differs from the one asked for); meta.engine names the search engine. Ignored without q.
cursorNoOpaque keyset cursor from a previous response's pagination.nextCursor. Stable for deep paging while new filings arrive (page is not). Required for page 2+ of a company-filtered search.
dateToNoEnd filing date (YYYY-MM-DD)
facetsNotrue = also return `facets`: { forms, years, items }, each a list of { value, count } over the whole result set (not just this page). Present only when the archive measured them (its OpenSearch engine); absent means not measured, not zero. Default false.
sectionNoRestricts matching to sections (comma-separated): business, risk_factors, cybersecurity, legal_proceedings, mdna, market_risk, controls (10-K/10-Q/20-F narrative items, by meaning: mdna is 10-K Item 7, 10-Q Part I Item 2 and 20-F Item 5), ex99 (press-release / EX-99.x exhibit text) and item_X_YY (the text under an 8-K item, e.g. item_5_02). Aliases: mda, risk, legal, cyber, press_release, 5.02. Unknown names are a 400. Requires q. Applied only when the response's meta.sections names it; otherwise meta.unsupported says why (e.g. the archive index does not have sections yet) and matches may come from anywhere in the filing.
sectorsNoCompany filter. Sector names separated by "|" (or a bare comma), exact and case-sensitive (e.g. "Healthcare|Technology"). An unknown name returns a 400 listing every valid sector.
dateFromNoStart filing date (YYYY-MM-DD). The archive only holds filings from its `archiveFrom` date (stated in every response; currently late 2021, expanding back to 2016): omitting dateFrom, or starting earlier, makes an empty result non-definitive.
maxFloatNoCompany filter. Maximum public float, in shares
maxPriceNoCompany filter. Maximum latest share price in USD
minFloatNoCompany filter. Minimum public float, in shares
minPriceNoCompany filter. Minimum latest share price in USD
pageSizeNoResults per page (default: 25, max: 100)
exchangesNoCompany filter. Comma-separated listing venues: NASDAQ, NYSE, AMEX (= NYSE American), OTC
formTypesNoComma-separated form types (e.g., "10-K,10-Q,8-K,S-1,S-3,424B5"). Exact match; amendments (e.g. "10-K/A") match only when listed. (With company filters, amendments are added automatically.)
recentIpoNoCompany filter. true = first listed within the last 365 days, with no evidence of earlier public status (renames and relistings are excluded). false is the same as omitting it.
industriesNoCompany filter. Industry names separated by "|", exact and case-sensitive (e.g. "Biotechnology|Airlines, Airports & Air Services"; some names contain ", ", so "|" is the safe separator; a bare comma with no space after it also separates). An unknown name returns a 400 listing every valid industry.
understandNoQuery understanding (default true): the archive recognises tickers/$TICKER, company names, form codes, "item N.NN" and expands synonyms, reporting what it applied in meta.understanding. false = search the words literally (also disables synonym expansion). Ignored without q.
companyTypesNoCompany filter. Comma-separated: operating, fund (registered funds/ETFs; adds N-CSR, N-CEN, N-PX, 485BPOS, 497/497K to the default forms), spac (blank-check companies)
excludeFormsNoComma-separated form types to exclude (e.g., "4,13F-HR"). Exact match.
exhibitTypesNoKeeps only filings carrying any of these exhibit types (comma-separated): a family such as EX-10 (material contracts) matches every member (EX-10.1, EX-10.2…); an exact type such as EX-99.1 (usually the press release) only itself. Others: EX-97 clawback policy, EX-3 charter/bylaws, EX-4 instruments/warrants, EX-21 subsidiaries, EX-23 consents. "10.1" is accepted for EX-10.1. Listed in appliedFilters when the rows prove it; otherwise in ignoredFilters / meta.unsupported, and the rows are then unfiltered.
maxMarketCapNoCompany filter. Maximum market cap in USD, e.g. 300000000 for under $300M
minMarketCapNoCompany filter. Minimum market cap in USD (price × shares outstanding), e.g. 50000000 for $50M
foreignIssuerNoCompany filter. true = companies with foreign-issuer evidence (a 20-F, 40-F or 6-K seen, or an ADR listing); false = none seen since the evidence log began (companyFilter.foreignEvidenceSince)
matchedSectionsNoPer-row `matchedSections` (default true): the sections the text matched in. Absent on a row means not measured (index without sections), not "matched nowhere". Ignored without q.

Output Schema

NameRequiredDescriptionDefault
dataNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed28 schema fields changedv0.20.0
    • changedInput schema / properties / ciks / description
      Previous value: -"Comma-separated CIK numbers to filter by (e.g., \"0000320193,0001018724\")"New value: +"Comma-separated CIK numbers to filter by (e.g., \"320193,1018724\"; zero-padded also accepted)"
    • addedInput schema / properties / companyTypes
      Added value: +{
      +  "description": "Company filter. Comma-separated: operating, fund (registered funds/ETFs; adds N-CSR, N-CEN, N-PX, 485BPOS, 497/497K to the default forms), spac (blank-check companies)",
      +  "type": "string"
      +}
    • addedInput schema / properties / cursor
      Added value: +{
      +  "description": "Opaque keyset cursor from a previous response's pagination.nextCursor. Stable for deep paging while new filings arrive (page is not). Required for page 2+ of a company-filtered search.",
      +  "type": "string"
      +}
    • changedInput schema / properties / dateFrom / description
      Previous value: -"Start date filter (YYYY-MM-DD)"New value: +"Start filing date (YYYY-MM-DD). The archive only holds filings from its `archiveFrom` date (stated in every response; currently late 2021, expanding back to 2016): omitting dateFrom, or starting earlier, makes an empty result non-definitive."
    • changedInput schema / properties / dateTo / description
      Previous value: -"End date filter (YYYY-MM-DD)"New value: +"End filing date (YYYY-MM-DD)"
    • addedInput schema / properties / exchanges
      Added value: +{
      +  "description": "Company filter. Comma-separated listing venues: NASDAQ, NYSE, AMEX (= NYSE American), OTC",
      +  "type": "string"
      +}
    • addedInput schema / properties / excludeForms
      Added value: +{
      +  "description": "Comma-separated form types to exclude (e.g., \"4,13F-HR\"). Exact match.",
      +  "type": "string"
      +}
    • addedInput schema / properties / exhibitTypes
      Added value: +{
      +  "description": "Keeps only filings carrying any of these exhibit types (comma-separated): a family such as EX-10 (material contracts) matches every member (EX-10.1, EX-10.2…); an exact type such as EX-99.1 (usually the press release) only itself. Others: EX-97 clawback policy, EX-3 charter/bylaws, EX-4 instruments/warrants, EX-21 subsidiaries, EX-23 consents. \"10.1\" is accepted for EX-10.1. Listed in appliedFilters when the rows prove it; otherwise in ignoredFilters / meta.unsupported, and the rows are then unfiltered.",
      +  "maxLength": 400,
      +  "type": "string"
      +}
    • addedInput schema / properties / facets
      Added value: +{
      +  "description": "true = also return `facets`: { forms, years, items }, each a list of { value, count } over the whole result set (not just this page). Present only when the archive measured them (its OpenSearch engine); absent means not measured, not zero. Default false.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / foreignIssuer
      Added value: +{
      +  "description": "Company filter. true = companies with foreign-issuer evidence (a 20-F, 40-F or 6-K seen, or an ADR listing); false = none seen since the evidence log began (companyFilter.foreignEvidenceSince)",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / formTypes / description
      Previous value: -"Comma-separated form types (e.g., \"10-K,10-Q,8-K,S-1,S-3,424B5\")"New value: +"Comma-separated form types (e.g., \"10-K,10-Q,8-K,S-1,S-3,424B5\"). Exact match; amendments (e.g. \"10-K/A\") match only when listed. (With company filters, amendments are added automatically.)"
    • addedInput schema / properties / industries
      Added value: +{
      +  "description": "Company filter. Industry names separated by \"|\", exact and case-sensitive (e.g. \"Biotechnology|Airlines, Airports & Air Services\"; some names contain \", \", so \"|\" is the safe separator; a bare comma with no space after it also separates). An unknown name returns a 400 listing every valid industry.",
      +  "type": "string"
      +}
    • addedInput schema / properties / items
      Added value: +{
      +  "description": "Comma-separated 8-K item codes, all required (e.g., \"2.02,9.01\" = results + financial statements; \"5.02\" = officer/director changes; \"1.01\" = material agreements; \"3.01\" = delisting notice).",
      +  "type": "string"
      +}
    • addedInput schema / properties / match
      Added value: +{
      +  "description": "Word matching for q. exact = a word matches only itself (\"split\" does not match \"splits\" or \"splitting\"), which is EDGAR full-text search's own behaviour; stemmed = English word variations also match. Default when omitted: stemmed. The mode actually applied is in the response's meta.matchMode (with meta.matchModeFallbackReason when it differs from the one asked for); meta.engine names the search engine. Ignored without q.",
      +  "enum": [
      +    "exact",
      +    "stemmed"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / matchedSections
      Added value: +{
      +  "description": "Per-row `matchedSections` (default true): the sections the text matched in. Absent on a row means not measured (index without sections), not \"matched nowhere\". Ignored without q.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / maxFloat
      Added value: +{
      +  "description": "Company filter. Maximum public float, in shares",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / maxMarketCap
      Added value: +{
      +  "description": "Company filter. Maximum market cap in USD, e.g. 300000000 for under $300M",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / maxPrice
      Added value: +{
      +  "description": "Company filter. Maximum latest share price in USD",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / minFloat
      Added value: +{
      +  "description": "Company filter. Minimum public float, in shares",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / minMarketCap
      Added value: +{
      +  "description": "Company filter. Minimum market cap in USD (price × shares outstanding), e.g. 50000000 for $50M",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • addedInput schema / properties / minPrice
      Added value: +{
      +  "description": "Company filter. Minimum latest share price in USD",
      +  "minimum": 0,
      +  "type": "number"
      +}
    • changedInput schema / properties / page / description
      Previous value: -"Page number (1-indexed, default: 1)"New value: +"Page number (1-indexed, default: 1). Ignored when cursor is set; not allowed with company filters."
    • addedInput schema / properties / q
      Added value: +{
      +  "description": "Full-text query over filing bodies. Query syntax: unquoted words all have to appear (any order, any distance); \"quoted phrase\" = exact wording; OR between alternatives (merger OR acquisition); -word or -\"phrase\" to exclude; w1 NEAR/10 w2 (also NEAR(10), or bare NEAR = within 10) = words close together; word* = prefix of 4+ letters (dilut* matches dilution, dilutive); $AAPL or a capitalised ticker scopes to that company; a form code (8-K, 10-Q, S-1), \"item 5.02\" / \"8-K 1.05\" and a bare year (2024) scope to that form / 8-K item / year. Example: '$AAPL \"share repurchase\" -\"no longer\"', 'cyber* NEAR/10 incident', 'item 5.02 resign*'.",
      +  "maxLength": 500,
      +  "type": "string"
      +}
    • addedInput schema / properties / recentIpo
      Added value: +{
      +  "description": "Company filter. true = first listed within the last 365 days, with no evidence of earlier public status (renames and relistings are excluded). false is the same as omitting it.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / section
      Added value: +{
      +  "description": "Restricts matching to sections (comma-separated): business, risk_factors, cybersecurity, legal_proceedings, mdna, market_risk, controls (10-K/10-Q/20-F narrative items, by meaning: mdna is 10-K Item 7, 10-Q Part I Item 2 and 20-F Item 5), ex99 (press-release / EX-99.x exhibit text) and item_X_YY (the text under an 8-K item, e.g. item_5_02). Aliases: mda, risk, legal, cyber, press_release, 5.02. Unknown names are a 400. Requires q. Applied only when the response's meta.sections names it; otherwise meta.unsupported says why (e.g. the archive index does not have sections yet) and matches may come from anywhere in the filing.",
      +  "maxLength": 400,
      +  "type": "string"
      +}
    • addedInput schema / properties / sectors
      Added value: +{
      +  "description": "Company filter. Sector names separated by \"|\" (or a bare comma), exact and case-sensitive (e.g. \"Healthcare|Technology\"). An unknown name returns a 400 listing every valid sector.",
      +  "type": "string"
      +}
    • addedInput schema / properties / sort
      Added value: +{
      +  "description": "newest (by acceptance time, default) or relevance (requires q; best match first)",
      +  "enum": [
      +    "newest",
      +    "relevance"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / understand
      Added value: +{
      +  "description": "Query understanding (default true): the archive recognises tickers/$TICKER, company names, form codes, \"item N.NN\" and expands synonyms, reporting what it applied in meta.understanding. false = search the words literally (also disables synonym expansion). Ignored without q.",
      +  "type": "boolean"
      +}
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only and non-destructive behavior, but the description adds substantial operational context: archive coverage, `archiveFrom` limitations, definitive versus non-definitive empty results, cursor pagination, facet absence semantics, and company-filter failure behavior. It also discloses when company filters drop forms and when unsupported section/exhibit filters leave results unfiltered, which goes well beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose is front-loaded, but the description is an extremely dense block covering many parameters, output fields, and edge cases. Most details are useful for a 29-parameter tool, yet it repeats schema and output-schema content such as `q` syntax, facet behavior, and returned field names, so it could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex search tool with 29 optional parameters and many coverage caveats, the description supplies the missing context an agent needs: held-range limits, when empty results are definitive, pagination behavior, facet semantics, and company-filter constraints. Given the output schema exists, the remaining return-value explanation is supplementary rather than required, but overall completeness is high.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, but the description adds meaningful conditional semantics not fully captured in the schema: the default form set used with company filters, issuer-filed-form restrictions, unknown-value exclusion, `COMPANY_FILTER_NOT_APPLIED` failure behavior, and cursor requirements for company-filtered paging. Some content repeats schema text, especially for `q`, but the added operational meaning is real.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource, 'Search and list SEC filings,' and enumerates its filters, optional full-text query, and returned filing fields. It also explicitly says results are filings, not a company list or count, and that `id` feeds the filing-document and exhibit tools, which helps distinguish its scope from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear usage context: search and list filings with optional full-text, facets, exhibit/section filters, and company filters. It gives some exclusions, such as not returning a company list or count, but does not explicitly name sibling alternatives such as search_filing_text or search_companies or state when to choose them instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools