Drillr — The financial MCP for AI agents

Tools provided

Tools the agent exposes — your AI client calls them automatically when it needs them.

• filing_list — 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. Coverage: US, Japan, and China A-shares. US bare (NVDA), Japan `.T` (6758.T), A-shares `.SH`/`.SZ` (600519.SH). 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

  write

  runs when your client calls it …ran · ✓ done
• filing_search — 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; resolve company names with ticker_lookup first. Coverage: US, Japan, and China A-shares. When `## Facts` is empty, read `## Passages`. `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.

  write

  runs when your client calls it …ran · ✓ done
• company_search — 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. `ma

  write

  runs when your client calls it …ran · ✓ done
• ticker_lookup — Resolve a company name, brand, or ticker substring to canonical ticker(s). Use this FIRST when the user mentions a company by name/brand/nickname before running any ticker-keyed tool. 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. Returned symbols carry their market suffix: US bare (AAPL), Japan `.T` (675

  write

  runs when your client calls it …ran · ✓ done
• run_sql — 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). Core equity coverage: US, Japan, Hong

  write

  runs when your client calls it …ran · ✓ done
• get_table_schema — Use BEFORE run_sql when you're unsure which columns a table has. Look up column definitions (name, type, description) for a data table.

  write

  runs when your client calls it …ran · ✓ done
• list_tables — 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

  write

  runs when your client calls it …ran · ✓ done
• news_search — Use for any news, event, development, or statement question about a company, theme, or the market. Covers US, Japan, Hong Kong and A-share markets; The `ticker` filter takes exchange-suffixed symbols: US bare (AAPL), Japan `.T` (7203.T), Hong Kong `.HK` (00700.HK), A-share `.SH`/`.SZ` (600519.SH). Returns Markdown: a `## Stories` numbered list (each storyline once), then flat `## Events` and `## Claims` tables (claims = attributed statements: analyst actions, corporate guidance, central-bank

  write

  runs when your client calls it …ran · ✓ done
• industry_inflections — Search industry inflections identified through structured research of earnings calls held by US-listed companies after July 2026, 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 `qu

  write

  runs when your client calls it …ran · ✓ done
• ai_adoption — Search concrete enterprise AI applications disclosed in US company earnings calls from September 2023 to the present. 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), evolu

  write

  runs when your client calls it …ran · ✓ done