filing-intelligence

SEC filing intelligence for AI agents.

От сообществаСбоиБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Search Companies: Search for companies by name or ticker with intelligent fuzzy matching. Handles partial names ("micro" -> Microsoft), typos, and variations. Returns ticker, full name, CIK, and busin
  • Get Company Overview: Get comprehensive financial overview for a company in a single call. Includes: current price, valuation (P/E, P/B, EV multiples, PEG), profitability (revenue, margins, returns),
  • Get Financials: Get multi-period financial statements: income statement, balance sheet, and cash flow in one call. Returns quantitative historical data with key metrics and trends. Default: all 3 stat

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

SEC filing intelligence for AI agents. Financials, filing analysis, screening, XBRL.

Как подключить

Как подключить filing-intelligence к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://filing-intelligence--metricduck.run.tools

  1. Откройте Claude (сайт claude.ai или приложение для компьютера).
  2. Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
  3. Нажмите Добавить пользовательский коннектор (Add custom connector).
  4. Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
  5. В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить filing-intelligence к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://filing-intelligence--metricduck.run.tools

  1. Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
  2. Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
  3. Откройте Настройки → Коннекторы и нажмите Создать (Create).
  4. Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
  5. В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
  6. В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить filing-intelligence к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://filing-intelligence--metricduck.run.tools

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

  1. В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
  2. Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
  3. Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (9)

Технические названия из tools/list. Нужны только разработчикам.

search_companiesSearch for companies by name or ticker with intelligent fuzzy matching. Handles partial names ("micro" -> Microsoft), typos, and variations. Returns ticker, full name, CIK, and business description. Best for: finding the right ticker before using other tools.
get_company_overviewGet comprehensive financial overview for a company in a single call. Includes: current price, valuation (P/E, P/B, EV multiples, PEG), profitability (revenue, margins, returns), cash flow (OCF, FCF, yields), balance sheet (debt, equity, ratios), capital allocation (buybacks, shares outstanding, shareholder yield), latest earnings insights, filing intelligence highlights, and company flags. Latest snapshot only — use get_financials for multi-year trends, get_filing_intelligence for deep filing analysis, compare_companies for peer benchmarking. Use search_companies first if unsure of the exact ticker.
get_financialsGet multi-period financial statements: income statement, balance sheet, and cash flow in one call. Returns quantitative historical data with key metrics and trends. Default: all 3 statements, quarterly, 2 years. For qualitative analysis (risks, accounting quality, management tone), use get_filing_intelligence instead. Use Cases: - "Show me AAPL's financials" -> all statements - "MSFT revenue trend 5 years" -> period="annual", years=5 - "Is Tesla's debt increasing?" -> statements=["balance"]
get_filing_intelligenceTriage layer for SEC filings — ranked signals with drill-down pointers to specific sections. Returns severity-ranked findings across 5 passes (narrative, accounting, hidden liabilities, risk, segments) for 10-K/10-Q filings, plus latest 8-K earnings release data (revenue, EPS, beat/miss, guidance). Includes get_filing_section() hints for drilling into the raw filing text. Use this to discover what's interesting, then get_filing_section() to read the actual content. Pass-specific queries (saves tokens): - Risks and threats? -> passes=["risk_landscape"] - Accounting quality / red flags? -> passes=["accounting"] - Management tone and strategy? -> passes=["narrative"] - Off-balance-sheet exposure? -> passes=["hidden_liabilities"] - Business segment breakdown? -> passes=["segments"] - Latest earnings release? -> passes=["earnings"] Use Cases: - "What should I look at in Apple's latest filing?" -> get_filing_intelligence("AAPL", limit=1) - "What risks does Tesla face?" -> get_filing_intelligence("TSLA", passes=["risk_landscape"]) - "Red flags for ENPH?" -> get_filing_intelligence("ENPH", passes=["accounting"]) - "How were NVDA's latest earnings?" -> get_filing_intelligence("NVDA", passes=["earnings"])
compare_companiesCompare a company against its peers with 70+ metrics, sector percentile rankings, and trends. Returns side-by-side comparison with pre-computed relative strengths and weaknesses. Peers auto-selected from same sector if custom_peers not specified. Use Cases: - "Compare AAPL vs MSFT" -> compare_companies("AAPL", custom_peers="MSFT") - "How does NVDA stack up?" -> compare_companies("NVDA")
screen_companiesScreen companies by financial criteria. Find stocks matching metric thresholds. Metric IDs: pe_ratio, pb_ratio, ev_ebitda, gross_margin, oper_margin, roe, roa, roic_v1, fcf_margin, debt_to_equity, etc. Sectors: TECH, FIN, HLTH, CONS, INDU, ENER, UTIL, REAL, MATL, COMM, COND Operators: gt (>), gte (>=), lt (<), lte (<=), eq (=), between Use Cases: - "High ROIC tech stocks" -> filters=[{metric_id:"roic_v1", operator:"gt", value:15}], sectors=["TECH"] - "Undervalued industrials" -> filters=[{metric_id:"pe_ratio", operator:"lt", value:15}], sectors=["INDU"]
list_filingsBrowse a company's SEC filings and discover available sections before reading content. Returns filing metadata (form type, dates, accession numbers) and per-section details (word count, table count, preview). Use this to find what to read, then use get_filing_section to retrieve the actual text. Covers 10-K annual, 10-Q quarterly, and 8-K current report filings. 10-K/10-Q include per-section details; 8-K returns filing metadata. Default: last 2 years. Use Cases: - "What filings does Apple have?" -> list_filings("AAPL") - "Show me Tesla's 10-K filings" -> list_filings("TSLA", form_type="10-K") - "Recent 8-K filings for MSFT?" -> list_filings("MSFT", form_type="8-K") - "What sections are in CRM's latest filing?" -> list_filings("CRM", years=1)
get_filing_sectionRead a specific section from an SEC filing (10-K, 10-Q, or 8-K earnings). Returns paginated section text (up to 10 chunks per page). Use list_filings first to discover available sections and accession numbers. If accession_number is omitted, returns the latest filing's section. 10-K/10-Q sections: risk_factors, mda_results_operations, mda_liquidity, mda_critical_accounting, business_description, footnote_revenue, footnote_segment, footnote_debt, footnote_accounting_policies 8-K earnings sections: earnings_press_release, earnings_financial_tables, earnings_segment_data, earnings_gaap_reconciliation, earnings_supplemental_tables For AI-generated filing analysis (scores, summaries), use get_filing_intelligence instead. Use Cases: - "Show me Apple's risk factors" -> get_filing_section("AAPL", "risk_factors") - "Read Tesla's MD&A" -> get_filing_section("TSLA", "mda_results_operations") - "What does CRM's revenue footnote say?" -> get_filing_section("CRM", "footnote_revenue") - "Read NVDA's earnings press release" -> get_filing_section("NVDA", "earnings_press_release") - "Show AAPL earnings tables" -> get_filing_section("AAPL", "earnings_financial_tables")
get_xbrl_factsSearch and extract raw XBRL facts from SEC filings. Access ~3,000 numeric facts per filing — the complete machine-readable data from SEC XBRL filings. Search by human-readable label (not XBRL concept names). Returns exact as-filed values with dimensional breakdowns (by segment, geography, product line, etc.). When to use this vs get_financials: - get_financials: derived metrics (revenue, margins, EPS) across multiple periods — use for standard analysis - get_xbrl_facts: raw filing data — use for industry-specific metrics, dimensional breakdowns, or verification How to discover concepts: - Search by what you're looking for: "medical cost", "goodwill", "revenue by segment" - Filing intelligence often names the metric — search for it here - Comma-separated terms for broader search: "debt,borrowing,credit facility" - Concept names in results are reusable across companies using the same taxonomy Use Cases: - "UNH medical cost ratio" -> search="medical cost ratio" - "AAPL revenue by segment" -> search="revenue,product" - "Compare goodwill across companies" -> search="goodwill" for each ticker - "Verify a number from filing text" -> search for the specific metric