ai.drillr/drillr

Est-ce que ai.drillr/drillr est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.drillr/drillr » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 10 outils

• ai_adoption≈ 538 tokens

  Search concrete enterprise AI applications disclosed in US company earnings calls. Filter by ticker, partially match a company name, search for an application or workflow by name, or use since in YYYY-MM-DD format to include only observations updated on or after that date. Returns a data array ordered by update_date descending. Each result contains ticker, company_name, application_name, first_report_date, update_date, summary (an AI application summary), evolution_summary, business_position, deployment_stage, deployment_scope, value_type, metrics (application-related metrics), and evidence (supporting management quotes, with speaker and section when available). Use this tool to identify where and how a company applies AI, assess deployment maturity, scope, and disclosed value, and inspect the supporting evidence. Use no filters to browse the most recently updated observations. No matches return an empty data array.

  Paramètres, retour & exemple (6)

  Paramètres

  • page · integer · optionnel
    One-based page number. Default 1.
  • limit · integer · optionnel
    Results per page. Default 10, max 10.
  • since · string · optionnel
    Only return observations with update_date on or after this date. Use YYYY-MM-DD.
  • ticker · ? · optionnel
    Optional US ticker filter, up to 10 symbols. Accepts one symbol or a list. Company names are not resolved.
  • company_name · string · optionnel
    Case-insensitive partial company-name match. Empty means no filter.
  • application_name · string · optionnel
    Case-insensitive partial application-name match. Empty means no filter.

  Exemple d'appel

  {"name": "ai_adoption", "arguments": {"page": 1, "limit": 1, "since": "texte", "ticker": "texte", "company_name": "texte", "application_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• company_search≈ 404 tokens

  Use for qualitative company discovery (industry, business model, supply chain, competitors, management background). For numerical screening (revenue, margins, ratios, growth rates) use run_sql on company_snapshot instead. Drillr's company knowledge graph — searchable across industry classification, product offerings, business model, segment structure, competitive landscape, supply chain, management background, and customer profile. Coverage: US, Japan, Hong Kong, China A-shares, and Korea. `market` accepts one lowercase value or a list from `us | jp | hk | cn | kr`; omit it or pass `[]` for all five. List order does not set priority. Pass a natural-language description (for example, "Hong Kong and China EV battery suppliers"). Returns a structured list of matching companies with context snippets. ONLY for finding a LIST of companies by description.

  Paramètres, retour & exemple (2)

  Paramètres

  • query · string · requis
    Natural-language company description
  • market · ? · optionnel
    Optional market filter. Pass one lowercase value or a list from 'us' | 'jp' | 'hk' | 'cn' | 'kr'. Omit or pass [] for all five; list order does not set priority.

  Exemple d'appel

  {"name": "company_search", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• filing_list≈ 344 tokens

  Use to discover which SEC filings exist for a ticker before searching content. For the actual content use filing_search instead. List indexed SEC filings for a given ticker with a summary header. Returns: summary (period coverage, per-type counts) + table of up to 50 filings (fiscal_year, fiscal_quarter, filing_type, filing_date, period_start, period_end). filing_types filter: omit for main reports only (US 10-K/10-Q/20-F/S-1/DEF 14A + /A amendments; JP 120/140/160; A-share annual_report / quarterly_report / q1_report; excludes ad-hoc 8-K/6-K); pass [] for all indexed types; pass explicit allowlist to override.

  Paramètres, retour & exemple (2)

  Paramètres

  • ticker · string · requis
    Stock ticker, e.g. NVDA, 6758.T, 00700.HK, 600519.SH
  • filing_types · array · optionnel
    Filter by filing type. Omit for default (periodic reports + IPO/shelf registrations + amendments; excludes ad-hoc disclosures). Pass [] for all indexed types. Pass an explicit allowlist to override — use values from the `filing_type` column of a prior unfiltered call.

  Exemple d'appel

  {"name": "filing_list", "arguments": {"ticker": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• filing_search≈ 502 tokens

  Search one company's SEC filings. Returns `## Facts` (exact as-reported and restated financial values) and `## Passages` (matching filing text) — both come back in one call. `ticker` is REQUIRED. When `## Facts` is empty, read `## Passages` — the figure is usually stated in the filing text. `period_start`/`period_end` match by interval overlap; `fiscal_period` sets granularity (Q1..Q4/H/9M/FY). Pass an explicit period window for the most recent figure.

  Paramètres, retour & exemple (8)

  Paramètres

  • as_of · ? · optionnel
    Publication cutoff date YYYY-MM-DD. Rows with missing published_at still appear; not a strict point-in-time snapshot
  • query · string · requis
    Natural-language financial metric query
  • top_k · integer · optionnel
    Max results; 1-30, default 10
  • ticker · string · requis
    Required. Canonical or historical ticker; one only. Resolve company names with ticker_lookup first
  • period_end · ? · optionnel
    Calendar end date YYYY-MM-DD (calendar, not fiscal)
  • period_type · string · optionnel · instant | duration
    instant or duration
  • period_start · string · optionnel
    Calendar start date YYYY-MM-DD (calendar, not fiscal; resolve fiscal periods via financial_statements period_start/period_end)
  • fiscal_period · ? · optionnel
    Q1 | Q2 | Q3 | Q4 | H | 9M | FY, or a list of those

  Exemple d'appel

  {"name": "filing_search", "arguments": {"query": "texte", "ticker": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_table_schema≈ 645 tokens

  Column definitions (name, type, description) for a data table, plus its usage note where one exists: required filters, ticker format, and market coverage.

  Paramètres, retour & exemple (1)

  Paramètres

  • table_name · string · requis · financial_statements | company_snapshot | price_volume_history | earning_call_summary | insider_and_institution_activities | index_price | equity_extended_rt | analyst_ratings

  Exemple d'appel

  {"name": "get_table_schema", "arguments": {"table_name": "financial_statements"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• industry_inflections≈ 550 tokens

  Search industry inflections identified through structured research of earnings calls held by US-listed companies, including the change mechanism, impact scope, market attention and affected companies. All filters are optional and combine with AND. With no filters, returns the newest first page. Results are ordered by `quarter` descending. If nothing matches, returns the text `No relevant industry inflections found.` Returns JSON as `{ "data": [...] }`. Every result contains `quarter`, `name` (English title), `regime_type` (change mechanism), `impact_scope`, `impact_degree` (`limited` | `significant` | `structural`), `attention_verdict` (market-absorption judgment), `change_summary`, `first_seen` (`YYYY-MM-DD`), and `source_tickers` (companies whose calls are primary evidence). When `impact_companies` is true, `company_impacts` contains items with `ticker`, `relation`, `direction`, `magnitude`, `impact_stage`, `evidence_status`, `affected_business`, and `impact`.

  Paramètres, retour & exemple (5)

  Paramètres

  • page · integer · optionnel
    One-based page number. Default 1.
  • limit · integer · optionnel
    Results per page. Default 10, max 10.
  • ticker · ? · optionnel
    Optional company filter, up to 10 US ticker symbols. Returns themes where any supplied ticker is a source company or an affected company. Use symbols such as AAPL, not company names.
  • keyword · string · optionnel
    Optional case-insensitive text contained in the theme name or research summary, up to 200 characters.
  • impact_companies · boolean · optionnel
    Include the per-company company_impacts list. Default false.

  Exemple d'appel

  {"name": "industry_inflections", "arguments": {"page": 1, "limit": 1, "ticker": "texte", "keyword": "texte", "impact_companies": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_tables≈ 443 tokens

  List alternative-data tables under the given categories. Returns each table's name, one-line purpose, and column names (call get_table_schema if you need column types/comments). Batch up to 5 categories in one call; omit categories, or pass ["all"], to get the category index instead. Use this BEFORE run_sql when you want to explore alt-data — run_sql alone won't tell you which tables exist. Available categories: - Energy & Power — US power plants, electricity prices, regional hourly generation/demand - Data Centers — facilities, GPU clusters, cooling - Semiconductors — AI chip specs, sales, ownership, foundry revenue, customs trade - Compute Pricing — GPU rental, cloud VM spot/on-demand, instance specs - Model Development — model specs, benchmarks, AI companies, AI polling, LLM arena - Inference Economics — LLM API pricing across providers - Macro & Trade — UN Comtrade, US Census trade flows, FRED macro series - Prediction Markets — Polymarket and Kalshi events, markets, trades, daily aggregates - Critical Minerals — USGS mineral deposits, country supply, critical materials

  Paramètres, retour & exemple (1)

  Paramètres

  • categories · array · optionnel
    Altdata category names (see tool description for the list). Omit, or pass "all", for the category index.

  Exemple d'appel

  {"name": "list_tables", "arguments": {"categories": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• news_search≈ 572 tokens

  Use for any news, event, development, or statement question about a company, theme, or the market. The `ticker` filter takes exchange-suffixed symbols. Returns Markdown: a `## Stories` numbered list (each storyline once), then flat `## Events` and `## Claims` tables (claims = attributed statements: analyst actions, corporate guidance, central-bank remarks). The Events `story` column refers back to the Stories number. `sources` counts corroborating reports; `first_reported`/`last_reported` give the reporting span. Lowest-ranked stories are dropped to fit length; the meta line flags how many were omitted. At least one of query/theme/ticker/since/until is required. Per-parameter detail is on the input schema — search_type=claims needs query/ticker/a time window, not theme.

  Paramètres, retour & exemple (8)

  Paramètres

  • query · string · optionnel
    Semantic query (English). One of query/theme/ticker/since/until required.
  • since · string · optionnel
    ISO8601; filter time_event >= since.
  • theme · string · optionnel
    Theme word, resolved to the nearest canonical theme. Not valid with search_type=claims.
  • top_k · integer · optionnel
    Story count. Default 10, max 50.
  • until · string · optionnel
    ISO8601; filter time_event < until.
  • ticker · ? · optionnel
    Exact ticker symbol(s) — a single symbol, an array, or a comma-separated string; multiple tickers are an OR/overlap filter. Exchange-suffixed (AAPL, 7203.T, 600519.SH). Company names/brands are NOT resolved here.
  • order_by · string · optionnel · relevance | event_time | create_time
    Result ordering. relevance (default) | event_time (newest event time first) | create_time (most recently ingested first).
  • search_type · string · optionnel · all | events | claims
    all (default) | events | claims (opinions/statements only).

  Exemple d'appel

  {"name": "news_search", "arguments": {"query": "texte", "since": "texte", "theme": "texte", "top_k": 1, "until": "texte", "ticker": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• run_sql≈ 386 tokens

  PostgreSQL SELECT over financial / market / alt-data tables — returns structured rows. Hard rules (query fails otherwise): - SELECT only, no CTE (`WITH ... AS`) — use subqueries. - Period columns are TEXT, not dates — `period_end` is 'YYYY-MM'. Compare as strings (`period_end >= '2024-01'`); a `::date` cast on it fails. - Filter structured tables by ticker (`WHERE ticker IN ('AAPL','MSFT')`; screening: add `ticker NOT LIKE '%-%'` to drop preferred stock). Tables by domain (get_table_schema gives columns + coverage note): - Market: price_volume_history (OHLCV history; MUST filter ticker + time_frame), index_price, equity_extended_rt (pre/after/overnight quotes) - Fundamentals: financial_statements (GAAP income/balance/cashflow), company_snapshot (ratios, per-share, growth) - Earnings: earning_call_summary, earning_call_calendar - Analyst: analyst_ratings, analyst_ratings_consensus - Ownership: insider_and_institution_activities - 8-K events: executive_change, company_deal_events, debt_issuance, securities_offering - Executives: executive_profile, executive_compensation - Alt-data: macro / industry / trade / AI-supply-chain — call list_tables(categories=[...])

  Paramètres, retour & exemple (1)

  Paramètres

  • sql · string · requis
    PostgreSQL SELECT query

  Exemple d'appel

  {"name": "run_sql", "arguments": {"sql": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• ticker_lookup≈ 244 tokens

  Resolve a company name, brand, or ticker substring to canonical ticker(s). Input: - query (required): company name, brand, or ticker substring, e.g. "Apple", "AAPL", "OpenAI" - market (optional): "us" | "jp" | "cn" — omit to search all markets Returns up to 5 matches ranked by prefix-hit first, then name length; symbols carry their market suffix.

  Paramètres, retour & exemple (2)

  Paramètres

  • query · string · requis
    Company name or ticker substring (case-insensitive). Matches historical names + tickers too.
  • market · string · optionnel · us | jp | hk | cn | kr
    Optional market filter: 'us' | 'jp' | 'cn'. Omit to search all markets.

  Exemple d'appel

  {"name": "ticker_lookup", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://gateway.drillr.ai/mcp/data