aether-developer
Was dieses MCP kann
Searches SEC filings, earnings transcripts, institutional holdings, partner research, and EU financial regulations, with cited retrieval and marketplace publishing tools.
Tools
Eingabeschema
{'type': 'object', 'required': [], 'properties': {'cik': {'type': 'array', 'items': {'type': 'string', 'pattern': '^\\d{1,10}$'}, 'description': 'Exact SEC CIK values to scope retrieval. Values are normalized to 10 digits.'}, 'limit': {'type': 'number', 'default': 10, 'maximum': 50}, 'query': {'type': 'string', 'description': 'Natural language search query. OMIT IT for fetch mode: with no query nothing is embedded or scored and the matching sections come back in filing-date-desc then document order. Fetch mode requires an identifier (issuer.ticker / issuer.cik / issuer.company_name / cik[] / accession_number) â\x80\x94 a query-less call without one is rejected.'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'default': 'issuer', 'description': 'issuer (default): results limited to the resolved company. cross_company: search all filers â\x80\x94 for questions like "who names NVIDIA as a supplier". Cross-company results are slower, relevance-ranked only, and always carry `quality_caveat`.'}, 'domain': {'enum': ['public_equity', 'supply_chain', 'auto'], 'type': 'string', 'default': 'auto', 'description': 'public_equity = single-company filing search; supply_chain = cross-company supplier/customer relationship evidence; auto (default) = detect from the query.'}, 'fields': {'type': 'array', 'items': {'type': 'string'}}, 'issuer': {'type': 'object', 'properties': {'cik': {'type': 'string', 'pattern': '^(CIK\\s*)?\\d{1,10}$', 'description': 'SEC CIK, any padding.'}, 'ticker': {'type': 'string', 'description': 'US ticker symbol.'}, 'company_name': {'type': 'string', 'description': 'Legal or common company name; the route for non-US issuers.'}}, 'description': 'The company the question is about. Pass at least one of ticker (e.g. "NVDA"), cik (e.g. "1045810"), or company_name (required for non-US issuers, which have no US ticker). Scopes retrieval to that filer: fast and precise. Strongly recommended on every call, and REQUIRED in fetch mode.'}, 'profile': {'enum': ['bm25', 'hybrid', 'hybrid_rerank', 'hybrid_rerank_tickerprior'], 'type': 'string', 'default': 'hybrid', 'description': "Retrieval profile. `hybrid` (default) ranks by the engine's own fused score (saturated lexical + vector cosine), highest first. `bm25` is the lexical-only fallback. `hybrid_rerank` and `hybrid_rerank_tickerprior` are accepted as aliases of `hybrid` for one release â\x80\x94 the cross-encoder they named was removed on 2026-09-11."}, 'section': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 20}], 'description': 'Filing section(s), matched case-insensitively as a substring of the stored label â\x80\x94 "Item 1A" matches "Item 1A. Risk Factors". In fetch mode this is how you ask for one part of a filing.'}, 'form_type': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only return these filing forms, for example ["20-F"] or ["6-K"].'}, 'fiscal_year': {'oneOf': [{'type': 'integer', 'maximum': 2100, 'minimum': 1990}, {'type': 'array', 'items': {'type': 'integer', 'maximum': 2100, 'minimum': 1990}, 'maxItems': 10, 'minItems': 1}], 'description': "Issuer's fiscal year as the company labels it (NVIDIA FY2027 = year ending Jan 2027). Resolved from XBRL DEI fiscal-year focus where available, else from the issuer's fiscal year-end; an empty year widens ±1 with a caveat."}, 'jurisdiction': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Scope to non-US issuer jurisdictions (ISO-3166 alpha-2): "SE" (Sweden/Bolagsverket), "JP" (Japan/EDINET), "KR" (Korea/DART). These carry no US ticker and are otherwise buried by SEC-centric ranking. US filings have an empty jurisdiction tag, so this filter is for non-US scoping only â\x80\x94 omit it to include US (the default). A named non-US issuer surfaces even without this filter, via the company-name anchor.'}, 'prefer_recent': {'type': 'boolean', 'description': 'Prefer newer filings when relevance scores are close. Automatically enabled for latest/current/guidance queries.'}, 'return_format': {'enum': ['section', 'chunk', 'both'], 'type': 'string', 'default': 'section', 'description': "Response shape. 'section' (default) returns the full SEC section the matching chunk belongs to. 'chunk' returns the matching window only. 'both' returns both."}, 'accession_number': {'type': 'string', 'pattern': '^\\d{10}-\\d{2}-\\d{6}$', 'description': 'Exact SEC accession number. When set, retrieval is hard-scoped to that filing.'}, 'exclude_form_type': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Exclude filing forms. Company searches already suppress fund/proxy forms by default.'}}}
Ausgabeschema
{'type': 'object', 'required': ['query', 'mode', 'domain', 'results', 'total', 'source', 'latency_ms'], 'properties': {'mode': {'enum': ['search', 'fetch'], 'type': 'string', 'description': '"search" = ranked by relevance. "fetch" = no ranking; sections listed in filing-date-desc then document order, and `total` is the number of matching chunks.'}, 'query': {'type': 'string'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'description': 'Effective scope after issuer resolution.'}, 'total': {'type': 'integer'}, 'domain': {'enum': ['public_equity', 'supply_chain', 'auto'], 'type': 'string'}, 'source': {'type': 'string'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'text', 'source'], 'properties': {'id': {'type': 'string'}, 'text': {'type': 'string', 'description': 'Exact filing-section (or chunk) text.'}, 'source': {'type': 'string'}, 'citation': {'type': 'string', 'description': 'Accession-numbered citation.'}, 'metadata': {'type': 'object'}, 'as_of_date': {'type': 'string'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}}}}, 'latency_ms': {'type': 'integer'}, 'quality_caveat': {'type': 'string', 'description': 'Present when the result is not issuer-precise. Read it before trusting cross-company results.'}}}
Eingabeschema
{'type': 'object', 'properties': {'cik': {'type': 'string', 'description': 'Exact 10-digit filer CIK, e.g. 0002012383. Preferred when known.'}, 'limit': {'type': 'number', 'description': 'Positions to return, 1-200 (default 25), ranked by value.'}, 'issuer': {'type': 'object', 'properties': {'cik': {'type': 'string', 'pattern': '^(CIK\\s*)?\\d{1,10}$', 'description': 'SEC CIK.'}, 'ticker': {'type': 'string', 'description': 'US ticker symbol.'}, 'company_name': {'type': 'string', 'description': 'Legal or common company name.'}}, 'description': "The company the question is about, in the same shape financial_search and search take â\x80\x94 so an agent can carry ONE issuer object across tools. Alias only: `issuer.cik` fills in `cik` and `issuer.company_name` fills in `manager` when you have not set them. NOTE this tool identifies the FILING MANAGER, not the issuer held â\x80\x94 for who owns a stock, use holdings_by_security. Ownership is a structured lookup, so there is no scope or quality_caveat here â\x80\x94 `coverage_caveat` is this tool's equivalent."}, 'period': {'type': 'string', 'description': 'Quarter end as YYYY-MM-DD. Defaults to the most recent loaded quarter.'}, 'manager': {'type': 'string', 'description': "Manager name, partial match, e.g. 'Bridgewater' or 'BlackRock'. Largest matching filer wins."}}, 'additionalProperties': False}
Eingabeschema
{'type': 'object', 'properties': {'cusip': {'type': 'string', 'description': '9-character CUSIP, e.g. 67066G104. Use when the ticker is unmapped.'}, 'limit': {'type': 'number', 'description': 'Holders to return, 1-100 (default 20), ranked by value.'}, 'issuer': {'type': 'object', 'properties': {'cik': {'type': 'string', 'pattern': '^(CIK\\s*)?\\d{1,10}$', 'description': 'SEC CIK.'}, 'ticker': {'type': 'string', 'description': 'US ticker symbol.'}, 'company_name': {'type': 'string', 'description': 'Legal or common company name.'}}, 'description': "The company the question is about, in the same shape financial_search and search take â\x80\x94 so an agent can carry ONE issuer object across tools. Alias only: `issuer.ticker` fills in `ticker` when you have not set it. Ownership is a structured lookup, so there is no scope or quality_caveat here â\x80\x94 `coverage_caveat` is this tool's equivalent."}, 'period': {'type': 'string', 'description': 'Quarter end as YYYY-MM-DD, e.g. 2026-03-31. Defaults to the most recent loaded quarter.'}, 'ticker': {'type': 'string', 'description': 'Ticker, e.g. NVDA. Resolved to a CUSIP internally.'}}, 'additionalProperties': False}
Eingabeschema
{'type': 'object', 'properties': {'mode': {'enum': ['indexed', 'proxy', 'any'], 'type': 'string', 'default': 'any', 'description': 'Restrict to partners offering this mode.'}, 'limit': {'type': 'integer', 'default': 50, 'maximum': 200, 'minimum': 1}, 'ticker': {'type': 'string', 'description': 'Optional â\x80\x94 filter to partners that cover this ticker (either in indexed docs or proxy endpoints).'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['partners', 'total'], 'properties': {'total': {'type': 'integer'}, 'partners': {'type': 'array', 'items': {'type': 'object', 'required': ['slug', 'org_name', 'indexed', 'proxy_endpoints', 'modes'], 'properties': {'slug': {'type': 'string'}, 'modes': {'type': 'array', 'items': {'enum': ['indexed', 'proxy'], 'type': 'string'}}, 'indexed': {'type': 'object', 'required': ['doc_count', 'ticker_coverage_sample'], 'properties': {'doc_count': {'type': 'integer'}, 'ticker_coverage_sample': {'type': 'array', 'items': {'type': 'string'}}}}, 'org_name': {'type': 'string'}, 'description': {'type': ['string', 'null']}, 'proxy_endpoints': {'type': 'array', 'items': {'type': 'object', 'required': ['endpoint_slug', 'display_name', 'pricing_model'], 'properties': {'description': {'type': ['string', 'null']}, 'display_name': {'type': 'string'}, 'endpoint_slug': {'type': 'string'}, 'pricing_model': {'enum': ['free', 'per_call', 'subscription'], 'type': 'string'}, 'taxonomy_tags': {'type': 'array', 'items': {'type': 'string'}}, 'ticker_coverage': {'type': 'array', 'items': {'type': 'string'}}, 'monthly_request_cap': {'type': ['integer', 'null']}, 'price_per_call_usd_cents': {'type': 'integer'}}}}}}}}}
Eingabeschema
{'type': 'object', 'required': ['query', 'partners'], 'properties': {'limit': {'type': 'integer', 'default': 10, 'maximum': 50, 'minimum': 1}, 'query': {'type': 'string'}, 'issuer': {'type': 'object', 'properties': {'cik': {'type': 'string', 'pattern': '^(CIK\\s*)?\\d{1,10}$', 'description': 'SEC CIK. Accepted for symmetry; endpoint coverage is declared by ticker.'}, 'ticker': {'type': 'string', 'description': 'US ticker symbol.'}, 'company_name': {'type': 'string', 'description': 'Company name. Accepted for symmetry; endpoint coverage is declared by ticker.'}}, 'description': 'The company the question is about. Pass `ticker` to route only to endpoints that declare coverage of it, instead of relying on ticker detection over the query text.'}, 'partners': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Seller slugs to route to. Empty/omitted = no fan-out (you MUST pick partners explicitly for credits to be consumed â\x80\x94 no surprise charges).'}, 'endpoints': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Optional: scope to specific endpoint slugs (format `<seller>/<endpoint>`). Otherwise all active endpoints of the named partners.'}, 'ticker_filter': {'type': 'boolean', 'description': 'Legacy switch, still accepted. When true (default) and an issuer is known â\x80\x94 passed in `issuer` or recognized in the query â\x80\x94 route only to endpoints covering that ticker. false disables the filter entirely.'}, 'confirm_charge': {'type': 'boolean', 'default': False, 'description': 'Safety acknowledgement. Must be true to actually execute the call. If false (or omitted), returns a dry-run quote with estimated charges.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['query', 'dry_run', 'total_charge_usd_cents', 'results', 'source', 'latency_ms', 'charges_by_seller'], 'properties': {'query': {'type': 'string'}, 'source': {'type': 'string'}, 'dry_run': {'type': 'boolean', 'description': 'True when confirm_charge was false â\x80\x94 quote only, no credits consumed.'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['source', 'seller_slug', 'endpoint_slug', 'success'], 'properties': {'data': {'description': 'Seller-defined payload (null in dry-run quotes).'}, 'source': {'type': 'string', 'description': 'proxy:<seller_slug>/<endpoint_slug>'}, 'success': {'type': 'boolean'}, 'error_class': {'type': 'string'}, 'seller_slug': {'type': 'string'}, 'display_name': {'type': 'string'}, 'result_count': {'type': 'integer'}, 'endpoint_slug': {'type': 'string'}, 'upstream_status': {'type': 'integer'}, 'upstream_latency_ms': {'type': 'integer'}, 'price_charged_usd_cents': {'type': 'integer'}}}}, 'latency_ms': {'type': 'integer'}, 'charges_by_seller': {'type': 'array', 'items': {'type': 'object', 'required': ['seller_slug', 'cents', 'calls'], 'properties': {'calls': {'type': 'integer'}, 'cents': {'type': 'integer'}, 'seller_slug': {'type': 'string'}}}}, 'total_charge_usd_cents': {'type': 'integer'}}}
Eingabeschema
{'type': 'object', 'required': ['query'], 'properties': {'limit': {'type': 'integer', 'default': 10, 'maximum': 50, 'minimum': 1}, 'query': {'type': 'string', 'description': 'Natural-language search query.'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'default': 'issuer', 'description': "issuer (default): narrow to documents covering the named issuer. cross_company: search every seller's whole corpus â\x80\x94 always carries `quality_caveat`. Setting it drops the ticker filter."}, 'issuer': {'type': 'object', 'properties': {'cik': {'type': 'string', 'pattern': '^(CIK\\s*)?\\d{1,10}$', 'description': 'SEC CIK. Accepted for symmetry; partner coverage is declared by ticker.'}, 'ticker': {'type': 'string', 'description': 'US ticker symbol.'}, 'company_name': {'type': 'string', 'description': 'Company name. Accepted for symmetry; partner coverage is declared by ticker.'}}, 'description': 'The company the question is about. Pass `ticker` to filter to documents that declare coverage of it, instead of relying on ticker detection over the query text.'}, 'profile': {'enum': ['bm25', 'hybrid'], 'type': 'string', 'default': 'hybrid'}, 'partners': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Optional list of seller slugs to scope the search to. Empty/omitted = all active sellers.'}, 'doc_types': {'type': 'array', 'items': {'type': 'string'}, 'description': "Optional filter on doc_type field â\x80\x94 e.g. ['research_note', 'supply_chain']."}, 'ticker_filter': {'type': 'boolean', 'description': 'Legacy switch, still accepted. When true (default) and an issuer is known â\x80\x94 passed in `issuer` or recognized in the query â\x80\x94 filter to docs covering that ticker. false disables the filter entirely.'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['query', 'results', 'total', 'source', 'latency_ms'], 'properties': {'query': {'type': 'string'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'description': 'Effective scope after issuer resolution.'}, 'total': {'type': 'integer'}, 'source': {'type': 'string'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'text', 'source', 'citation', 'confidence'], 'properties': {'id': {'type': 'string'}, 'text': {'type': 'string'}, 'source': {'type': 'string', 'description': 'partner:<seller_slug>'}, 'citation': {'type': 'string'}, 'metadata': {'type': 'object', 'description': 'Per-document attribution: seller, title, doc_type, license, ticker coverage, retrieval diagnostics.'}, 'as_of_date': {'type': 'string'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}}}}, 'latency_ms': {'type': 'integer'}, 'quality_caveat': {'type': 'string', 'description': 'Present when the result is not issuer-precise. Read it before trusting cross-company results.'}}}
Eingabeschema
{'type': 'object', 'required': ['query'], 'properties': {'celex': {'type': ['string', 'array'], 'items': {'type': 'string'}, 'description': 'The act(s) to anchor on, by CELEX number â\x80\x94 e.g. 32014L0065 (MiFID II), 32023R1114 (MiCA), 32013R0575 (CRR), 32022R2554 (DORA), 32016R0679 (GDPR), 32024R1624 (AMLR). This is the subject of the call: pass it whenever you know which act you mean. Omitting it searches the whole 29-act corpus as scope=cross_company, with a quality_caveat.'}, 'limit': {'type': 'number', 'default': 10, 'maximum': 50}, 'query': {'type': 'string', 'description': 'Natural language query'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'default': 'issuer', 'description': 'issuer (default, requires `celex`): results come from that act only. cross_company: the whole corpus â\x80\x94 slower, relevance-ranked only, always carries `quality_caveat`. A `celex` filter you pass always applies.'}, 'article': {'type': 'string', 'description': 'Optional single-article filter, e.g. "20" or "12a"'}, 'profile': {'enum': ['bm25', 'hybrid'], 'type': 'string', 'default': 'hybrid'}, 'doc_type': {'type': 'string', 'description': 'Optional filter: regulation | directive | rts | its | decision'}, 'aml_topics': {'type': ['string', 'array'], 'items': {'type': 'string'}, 'description': 'Optional topic tag filter: cdd | edd | pep | str_reporting | governance | reporting | transaction_monitoring'}, 'chunk_type': {'type': 'string', 'description': 'Optional filter: paragraph | article_intro | recital | table | annex'}, 'prefer_consolidated': {'type': 'boolean', 'description': 'Prefer EUR-Lex consolidated text over original OJ text at equal relevance (hybrid only). Leave off to favor the as-published OJ text.'}}}
Ausgabeschema
{'type': 'object', 'required': ['query', 'results', 'total', 'source', 'latency_ms'], 'properties': {'query': {'type': 'string'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'description': 'Effective scope: issuer when anchored to a CELEX, else cross_company.'}, 'total': {'type': 'integer'}, 'source': {'type': 'string'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['doc_id', 'celex', 'breadcrumb', 'text', 'source_url', 'citation', 'confidence'], 'properties': {'text': {'type': 'string'}, 'celex': {'type': 'string'}, 'doc_id': {'type': 'string'}, 'article': {'type': 'string'}, 'eli_uri': {'type': 'string'}, 'citation': {'type': 'string'}, 'doc_type': {'type': 'string'}, 'paragraph': {'type': 'string'}, 'retrieval': {'type': 'object'}, 'aml_topics': {'type': 'array', 'items': {'type': 'string'}}, 'breadcrumb': {'type': 'string', 'description': "Human citation path, e.g. 'AMLR 2024/1624 · Art. 12 · para. 3'."}, 'chunk_type': {'type': 'string'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'source_url': {'type': 'string'}, 'is_consolidated': {'type': 'boolean'}}}}, 'latency_ms': {'type': 'integer'}, 'celex_filter': {'type': 'array', 'items': {'type': 'string'}}, 'quality_caveat': {'type': 'string', 'description': 'Present when the result is not CELEX-precise. Read it before trusting corpus-wide results.'}}}
Eingabeschema
{'type': 'object', 'required': [], 'properties': {'limit': {'type': 'integer', 'default': 10, 'maximum': 50, 'description': 'Max hits to return (1-50, default 10).'}, 'query': {'type': 'string', 'description': 'Natural language search query. OPTIONAL â\x80\x94 omit it (or pass an empty string) to select FETCH MODE, which ranks nothing and returns rows in filing order. Fetch mode REQUIRES an identifier: pass `issuer` (ticker, cik or company_name) or a single-element `tickers`, optionally narrowed with `fiscal_year`; a query-less call with no identifier is rejected. Fetch fans out to sec/jp/kr/transcripts only â\x80\x94 EU regulation has no issuer, so "every article, newest first" answers nothing.'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'default': 'issuer', 'description': 'issuer (default): every corpus is scoped to the named company. cross_company: search all issuers â\x80\x94 for questions like "who names NVIDIA as a supplier". Cross-company results are slower, relevance-ranked only, and always carry `quality_caveat`.'}, 'issuer': {'type': 'object', 'properties': {'cik': {'type': 'string', 'pattern': '^(CIK\\s*)?\\d{1,10}$', 'description': 'SEC CIK, any padding.'}, 'ticker': {'type': 'string', 'description': 'US ticker symbol.'}, 'company_name': {'type': 'string', 'description': 'Legal or common company name; the route for non-US issuers.'}}, 'description': 'The company the question is about. Pass at least one of ticker (e.g. "NVDA"), cik (e.g. "1045810"), or company_name (required for non-US issuers, which have no US ticker). Forwarded to every corpus that can use it. Strongly recommended on every call.'}, 'corpora': {'type': 'array', 'items': {'enum': ['sec', 'jp', 'kr', 'regulation', 'transcripts'], 'type': 'string'}, 'description': 'Optional corpus filter. Omit to search everything (recommended). Values: sec, jp, kr, regulation, transcripts. An explicit value always wins: a filing filter (form_type / accession_number / section) narrows an OMITTED fan-out to sec/jp/kr, but naming corpora here overrides that.'}, 'quarter': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 8}], 'description': 'Fiscal quarter(s) â\x80\x94 "Q2" or ["Q1","Q2"]. Exact, case-insensitive. Applies to the EARNINGS-CALL corpus only (with issuer.ticker and fiscal_year it names one call, the natural fetch-mode request); the filing and regulation corpora ignore it.'}, 'section': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 20}], 'description': 'Filing section(s), matched case-insensitively as a substring of the stored label â\x80\x94 "Item 1A" matches "Item 1A. Risk Factors". In fetch mode this is how you ask for one part of a filing. Filing corpora only; it narrows an omitted `corpora` to sec/jp/kr.'}, 'tickers': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Legacy alias of `issuer`, still accepted. One symbol (e.g. ["IBM"]) is read as issuer.ticker; several (e.g. ["IBM", "MU"]) is a cross-company question and is labelled scope=cross_company, though the filter to those companies still applies. Prefer `issuer`.'}, 'form_type': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Only return these filing forms, for example ["20-F"] or ["6-K"]. Forwarded to the filing corpora (sec/jp/kr). Because an earnings segment has no form type and an EU article has none either, setting this ALSO narrows an omitted `corpora` to sec/jp/kr rather than merging rows the filter could not reach.'}, 'fiscal_year': {'oneOf': [{'type': 'integer', 'maximum': 2100, 'minimum': 1990}, {'type': 'array', 'items': {'type': 'integer', 'maximum': 2100, 'minimum': 1990}, 'maxItems': 10, 'minItems': 1}], 'description': "Issuer's fiscal year as the company labels it (NVIDIA FY2027 = year ending Jan 2027). Forwarded verbatim to every corpus: on filings it is resolved from XBRL DEI fiscal-year focus where available, else from the issuer's fiscal year-end; on earnings calls it is that corpus's own labelled fiscal year. An empty year widens ±1 with a caveat."}, 'return_format': {'enum': ['section', 'chunk', 'both'], 'type': 'string', 'default': 'chunk', 'description': 'Response shape for the filing corpora. "chunk" (the unified default) returns the matching window only â\x80\x94 it keeps a five-corpus merge small. "section" returns the full SEC section the chunk belongs to, "both" returns both. The earnings-call and regulation corpora ignore it; their unit is a speaker turn / an article.'}, 'accession_number': {'type': 'string', 'pattern': '^\\d{10}-\\d{2}-\\d{6}$', 'description': 'Exact SEC accession number. When set, the filing corpora are hard-scoped to that filing, and an omitted `corpora` narrows to sec/jp/kr. It also counts as the identifier fetch mode requires, so `{accession_number}` with no `query` is a legal fetch.'}}}
Ausgabeschema
{'type': 'object', 'required': ['query', 'results', 'total', 'latency_ms'], 'properties': {'mode': {'enum': ['search', 'fetch'], 'type': 'string', 'description': '"search" = a `query` was given and hits are ranked by relevance. "fetch" = no `query`; the identifier and filters select rows and they come back in filing order, unranked.'}, 'query': {'type': 'string'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'description': 'Effective scope: the worst case across the corpora that answered. Any cross-company corpus makes the merged answer cross_company.'}, 'total': {'type': 'integer'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'corpus', 'citation', 'text', 'confidence', 'anchor_id'], 'properties': {'id': {'type': 'string'}, 'meta': {'type': 'object'}, 'text': {'type': 'string'}, 'corpus': {'enum': ['sec', 'jp', 'kr', 'regulation', 'transcripts'], 'type': 'string', 'description': 'Which corpus this hit came from.'}, 'citation': {'type': 'string', 'description': 'Accession-numbered / article-level citation.'}, 'anchor_id': {'type': 'string', 'description': 'Context-panel anchor (chunk/segment/doc id).'}, 'as_of_date': {'type': 'string'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'source_url': {'type': 'string'}, 'body_offset': {'type': 'integer', 'minimum': 0, 'description': 'Filing corpora only, and only when the chunk opens with furniture: the character offset in `text` where the EDGAR cover page / contents opener ends and the body begins. Absent means `text` opens with its own body. Crop from here, not from 0, or a rendered excerpt reads "UNITED STATES SECURITIES AND EXCHANGE COMMISSION" instead of the answer (1,462 chars on a TSMC monthly-revenue 6-K).'}, 'diagnostics': {'type': 'object', 'properties': {'mode': {'enum': ['search', 'fetch'], 'type': 'string', 'description': '"search" = ranked by relevance. "fetch" = filters only, returned in filing order.'}, 'issuer_how': {'enum': ['explicit_cik', 'explicit_ticker', 'company_name', 'company_name_resolved', 'company_name_unresolved', 'inferred_from_query', 'none'], 'type': 'string', 'description': 'How the issuer was resolved. `inferred_from_query` means the filter was a guess. `company_name_resolved` / `company_name_unresolved` are reported when a company_name ran through the name anchor first: resolved means the name mapped to CIKs and the call took the fast issuer-exact path, unresolved means it did not and the call ran cross-company â\x80\x94 the whole cost profile of the request.'}, 'junk_dropped': {'type': 'integer', 'description': 'Cover pages, exhibit indexes and [Reserved] sections removed.'}, 'candidate_pool': {'type': 'integer', 'description': 'Candidates retrieved before dedupe and diversity.'}, 'dedupe_dropped': {'type': 'integer', 'description': 'Near-duplicate / per-filing-cap suppressions across filings.'}, 'fiscal_year_semantics': {'enum': ['dei_fiscal_year_focus', 'issuer_fy_end_month', 'calendar_filed_window'], 'type': 'string', 'description': 'Which fiscal-year rule answered this call. Without it a caller cannot tell a real absence from a wrong one.'}}, 'description': 'Filing corpora only: the engine fields a caller can act on. Absent on corpora that do not produce them.'}, 'corpus_label': {'type': 'string'}, 'context_token': {'type': 'string'}}}}, 'latency_ms': {'type': 'integer'}, 'partial_errors': {'type': 'array', 'items': {'type': 'string'}}, 'quality_caveat': {'type': 'string', 'description': 'Present when any answering corpus was not issuer-precise. Read it before trusting the result.'}}}
Eingabeschema
{'type': 'object', 'required': ['seller_api_key'], 'properties': {'seller_api_key': {'type': 'string'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['documents'], 'properties': {'documents': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'external_doc_id', 'status'], 'properties': {'id': {'type': 'integer'}, 'error': {'type': ['string', 'null']}, 'title': {'type': ['string', 'null']}, 'status': {'type': 'string', 'description': 'pending | indexed | failed | revoked'}, 'license': {'type': ['string', 'null']}, 'doc_type': {'type': ['string', 'null']}, 'indexed_at': {'type': ['string', 'null']}, 'published_at': {'type': 'string'}, 'external_doc_id': {'type': 'string'}, 'ticker_coverage': {'type': ['array', 'null'], 'items': {'type': 'string'}}, 'vespa_chunk_count': {'type': ['integer', 'null'], 'description': 'DEPRECATED alias of `indexed_chunk_count`, same value, removed after one release.'}, 'indexed_chunk_count': {'type': ['integer', 'null'], 'description': 'How many chunks the background worker indexed for this document. Null until it has run.'}}}}}}
Eingabeschema
{'type': 'object', 'required': ['seller_api_key'], 'properties': {'seller_api_key': {'type': 'string'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['endpoints'], 'properties': {'endpoints': {'type': 'array', 'items': {'type': 'object', 'required': ['id', 'slug', 'display_name', 'status', 'secret_configured'], 'properties': {'id': {'type': 'integer'}, 'url': {'type': 'string'}, 'slug': {'type': 'string'}, 'status': {'type': 'string'}, 'created_at': {'type': 'string'}, 'updated_at': {'type': 'string'}, 'auth_method': {'type': 'string'}, 'description': {'type': ['string', 'null']}, 'http_method': {'type': 'string'}, 'display_name': {'type': 'string'}, 'pricing_model': {'type': 'string'}, 'taxonomy_tags': {'type': ['array', 'null'], 'items': {'type': 'string'}}, 'ticker_coverage': {'type': ['array', 'null'], 'items': {'type': 'string'}}, 'auth_header_name': {'type': ['string', 'null']}, 'response_jsonpath': {'type': ['string', 'null']}, 'secret_configured': {'type': 'boolean', 'description': 'Secrets are never returned â\x80\x94 only whether one is set.'}, 'monthly_request_cap': {'type': ['integer', 'null']}, 'last_health_check_at': {'type': ['string', 'null']}, 'last_health_check_ok': {'type': ['boolean', 'null']}, 'price_per_call_usd_cents': {'type': ['integer', 'null']}}}}}}
Eingabeschema
{'type': 'object', 'required': ['seller_api_key', 'external_doc_id', 'content'], 'properties': {'title': {'type': 'string'}, 'content': {'type': 'string', 'description': 'Document text. Up to ~2 MB.'}, 'license': {'type': 'string'}, 'doc_type': {'type': 'string'}, 'metadata': {'type': 'object', 'additionalProperties': True}, 'source_url': {'type': 'string'}, 'seller_api_key': {'type': 'string', 'description': 'Your seller API key (aether_sk_â\x80¦).'}, 'external_doc_id': {'type': 'string'}, 'ticker_coverage': {'type': 'array', 'items': {'type': 'string'}}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['document_id', 'external_doc_id', 'status'], 'properties': {'notice': {'type': 'string'}, 'status': {'type': 'string', 'description': 'pending until the index worker completes'}, 'document_id': {'type': 'integer'}, 'published_at': {'type': 'string'}, 'external_doc_id': {'type': 'string'}}}
Eingabeschema
{'type': 'object', 'required': ['seller_api_key', 'slug', 'display_name', 'url'], 'properties': {'url': {'type': 'string'}, 'slug': {'type': 'string', 'description': 'lowercase kebab-case; unique per seller'}, 'secret': {'type': 'string', 'description': 'Encrypted at rest; never returned.'}, 'auth_method': {'enum': ['bearer', 'header', 'basic', 'none'], 'type': 'string'}, 'description': {'type': 'string'}, 'http_method': {'enum': ['POST', 'GET'], 'type': 'string'}, 'display_name': {'type': 'string'}, 'pricing_model': {'enum': ['free', 'per_call', 'subscription'], 'type': 'string'}, 'taxonomy_tags': {'type': 'array', 'items': {'type': 'string'}}, 'seller_api_key': {'type': 'string'}, 'ticker_coverage': {'type': 'array', 'items': {'type': 'string'}}, 'auth_header_name': {'type': 'string', 'description': "Required when auth_method='header'."}, 'request_template': {'type': 'object', 'additionalProperties': True}, 'response_jsonpath': {'type': 'string', 'description': 'e.g. $.results'}, 'monthly_request_cap': {'type': 'integer', 'minimum': 1}, 'price_per_call_usd_cents': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['endpoint_id', 'slug', 'status'], 'properties': {'slug': {'type': 'string'}, 'status': {'type': 'string'}, 'created_at': {'type': 'string'}, 'endpoint_id': {'type': 'integer'}}}
Eingabeschema
{'type': 'object', 'required': ['slug', 'org_name', 'contact_email'], 'properties': {'slug': {'type': 'string', 'description': 'Lowercase kebab-case identifier shown in attribution.'}, 'org_name': {'type': 'string'}, 'description': {'type': 'string', 'description': 'Free-text description shown to agents in list_partners.'}, 'invite_code': {'type': 'string', 'description': 'Optional operator-issued invite. Bypasses per-IP rate limit and auto-approves.'}, 'contact_email': {'type': 'string'}}, 'additionalProperties': False}
Ausgabeschema
{'type': 'object', 'required': ['seller_id', 'slug', 'status', 'api_key', 'notice'], 'properties': {'slug': {'type': 'string'}, 'notice': {'type': 'string'}, 'status': {'type': 'string', 'description': 'active | pending_review'}, 'api_key': {'type': 'string', 'description': 'Shown once â\x80\x94 cannot be retrieved later.'}, 'org_name': {'type': 'string'}, 'seller_id': {'type': 'integer'}, 'api_key_id': {'type': 'integer'}, 'api_key_prefix': {'type': 'string'}}}
Eingabeschema
{'type': 'object', 'required': [], 'properties': {'limit': {'type': 'number', 'default': 10, 'maximum': 50}, 'order': {'enum': ['relevance', 'earliest', 'latest'], 'type': 'string', 'default': 'relevance', 'description': "Sort order. 'earliest'/'latest' sort matched hits chronologically (use 'earliest' for onset/first-mention queries); 'relevance' sorts by rank score."}, 'query': {'type': 'string', 'description': 'Natural language query. OMIT IT for fetch mode: with no query nothing is embedded or scored and the matching segments come back newest call first, then in the order they were spoken. Fetch mode requires a ticker.'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'default': 'issuer', 'description': "issuer (default): results limited to the issuer's own calls. cross_company: search every issuer's calls â\x80\x94 slower, relevance-ranked only, and always carries `quality_caveat`. Setting it drops the ticker filter, so a caveated answer is never secretly a scoped one."}, 'issuer': {'type': 'object', 'properties': {'cik': {'type': 'string', 'pattern': '^(CIK\\s*)?\\d{1,10}$', 'description': 'SEC CIK. Accepted for symmetry with financial_search; this corpus scopes on ticker.'}, 'ticker': {'type': 'string', 'description': 'US ticker symbol.'}, 'company_name': {'type': 'string', 'description': 'Reserved for non-US calls once the ASR corpus carries them.'}}, 'description': 'The company whose calls you mean. Pass `ticker` (e.g. "NVDA"); this corpus is keyed on ticker, so that is the field that scopes it. Strongly recommended on every call.'}, 'ticker': {'type': 'string', 'description': 'Optional ticker filter (e.g. NVDA). Legacy alias of `issuer.ticker`.'}, 'date_to': {'type': 'string', 'description': 'Point-in-time upper bound on call date, inclusive ISO YYYY-MM-DD'}, 'profile': {'enum': ['bm25', 'hybrid'], 'type': 'string', 'default': 'hybrid'}, 'quarter': {'oneOf': [{'type': 'string'}, {'type': 'array', 'items': {'type': 'string'}, 'maxItems': 8}], 'description': 'Fiscal quarter(s) â\x80\x94 "Q2" or ["Q1","Q2"]. Exact, case-insensitive. With issuer.ticker and fiscal_year this names one call, which is the natural fetch-mode request.'}, 'date_from': {'type': 'string', 'description': 'Point-in-time lower bound on call date, inclusive ISO YYYY-MM-DD'}, 'fiscal_year': {'oneOf': [{'type': 'integer', 'maximum': 2100, 'minimum': 1990}, {'type': 'array', 'items': {'type': 'integer', 'maximum': 2100, 'minimum': 1990}, 'maxItems': 10, 'minItems': 1}], 'description': "Fiscal year(s) the question concerns â\x80\x94 the ISSUER'S OWN fiscal year, as printed on its cover page, matched exactly against each segment's fiscal-year label. Offset-fiscal-year issuers work as stated: NVDA fiscal_year 2027 returns the calls held during calendar 2026, AAPL 2025 the Q1-Q4 FY2025 calls. If the requested year matches nothing the search retries once at ±1 and says so in `quality_caveat`. Independent of date_from/date_to, which bound the CALL DATE and still apply on top."}, 'source_type': {'enum': ['press_release', 'furnished_transcript', 'asr_call'], 'type': 'string', 'description': 'Provenance filter: asr_call = our ASR of the real call (Q&A); furnished_transcript = issuer transcript exhibit; press_release = 8-K press exhibit.'}, 'speaker_role': {'type': 'string', 'description': 'Optional speaker role filter: CEO / CFO / Analyst / Operator'}, 'lookback_quarters': {'type': 'number', 'description': 'Keep calls within last N quarters (default: no filter)'}}}
Ausgabeschema
{'type': 'object', 'required': ['query', 'mode', 'results', 'total', 'source', 'latency_ms'], 'properties': {'mode': {'enum': ['search', 'fetch'], 'type': 'string', 'description': '"search" = ranked by relevance. "fetch" = no ranking; segments listed newest call first then in spoken order, and `confidence` is 0 on every result because there is no relevance signal.'}, 'query': {'type': 'string'}, 'scope': {'enum': ['issuer', 'cross_company'], 'type': 'string', 'description': 'Effective scope after issuer resolution.'}, 'total': {'type': 'integer'}, 'source': {'type': 'string'}, 'results': {'type': 'array', 'items': {'type': 'object', 'required': ['segment_id', 'ticker', 'fiscal_year', 'quarter', 'call_date', 'speaker_name', 'speaker_role', 'text', 'source_url', 'citation', 'confidence'], 'properties': {'text': {'type': 'string', 'description': 'Verbatim speaker-turn text.'}, 'ticker': {'type': 'string'}, 'quarter': {'type': 'string'}, 'citation': {'type': 'string'}, 'call_date': {'type': 'string'}, 'retrieval': {'type': 'object'}, 'confidence': {'type': 'number', 'maximum': 1, 'minimum': 0}, 'segment_id': {'type': 'string'}, 'source_url': {'type': 'string'}, 'fiscal_year': {'type': 'integer'}, 'source_type': {'type': 'string'}, 'speaker_name': {'type': 'string'}, 'speaker_role': {'type': 'string'}, 'segment_index': {'type': 'integer'}, 'segment_total': {'type': 'integer'}, 'speaker_company': {'type': 'string'}}}}, 'latency_ms': {'type': 'integer'}, 'ticker_filter': {'type': 'string'}, 'quality_caveat': {'type': 'string', 'description': 'Present when the result is not issuer-precise. Read it before trusting cross-company results.'}}}
Letzte Tool-Änderungen
Ähnliche MCP-Server
agentdata-nl
Provides paid company, insolvency, sanctions, regulatory, crypto-market, news, payment-counterparty, and structured web research …
Insurers Global
Provides a source-linked directory of licensed insurers, regulators, insurance groups, ownership relationships, historical names …
Official Source Evidence
Provides paid public-source snapshots, SEC Form D funding signals, and exact-address OFAC payment preflight checks through x402 p…
CVM: Processos Administrativos Sancionadores
Queries official CVM records for administrative sanctioning proceedings.
CVM Processos Sancionadores
Looks up public CVM enforcement proceedings for individuals or companies using CPF or CNPJ.
CVM: Processos Sancionadores Julgados
Queries official records of adjudicated CVM sanctioning proceedings.
crowdspace
Searches crowdfunding and P2P lending platforms and provides market statistics, industry news, and country-specific regulatory in…
304NotModified
Provides sourced, dated factual answers on regulatory and business topics and performs deterministic financial market calculation…