Drillr — The financial MCP for AI agents

little-grebe-inc/drillr-mcp-server

A financial research toolkit that pipes 90+ SQL tables, SEC filing search, and live market signals into your AI agent. You get standardized statements back to the 1980s, paragraph-cited 10-K/10-Q searches, earnings transcripts with structured summaries, and a cross-asset signal feed covering equities, macro, and alt-data for the AI value chain. Every MCP tool maps 1:1 to a REST endpoint, same key and billing. Runs over Streamable HTTP with Bearer auth. Use it when you need your agent to fact-check financial claims, compare margin dynamics across peers, or track insider moves without leaving the prompt loop. Ships with fiscal period helpers and schema inspection so the model can navigate tables autonomously.

GitHub stars: 10
tools: 10
transport: HTTP
last updated: Sep 13, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://gateway.drillr.ai/mcp/data --name drillr

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http drillr https://gateway.drillr.ai/mcp/data

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 10 tools

Verified live against the running server on Nov 6, 2026.

filing_listUse 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 (...2 params

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 (...

Parameters* required

filing_typesarray

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...

ticker*string

Stock ticker, e.g. NVDA, 6758.T, 00700.HK, 600519.SH

filing_searchSearch 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 th...8 params

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 th...

Parameters* required

as_ofvalue

Publication cutoff date YYYY-MM-DD. Rows with missing published_at still appear; not a strict point-in-time snapshot

fiscal_periodvalue

Q1 | Q2 | Q3 | Q4 | H | 9M | FY, or a list of those

period_endvalue

Calendar end date YYYY-MM-DD (calendar, not fiscal)

period_startstring

Calendar start date YYYY-MM-DD (calendar, not fiscal; resolve fiscal periods via financial_statements period_start/period_end)

period_typestring

instant or durationone of instant · duration

query*string

Natural-language financial metric query

ticker*string

Required. Canonical or historical ticker; one only. Resolve company names with ticker_lookup first

top_kinteger

Max results; 1-30, default 10

company_searchUse 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 in...2 params

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 in...

Parameters* required

marketvalue

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.

query*string

Natural-language company description

ticker_lookupResolve 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...2 params

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...

Parameters* required

marketstring

Optional market filter: 'us' | 'jp' | 'cn'. Omit to search all markets.one of us · jp · hk · cn · kr

query*string

Company name or ticker substring (case-insensitive). Matches historical names + tickers too.

run_sqlPostgreSQL 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...1 params

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...

Parameters* required

sql*string

PostgreSQL SELECT query

get_table_schemaColumn definitions (name, type, description) for a data table, plus its usage note where one exists: required filters, ticker format, and market coverage.1 params

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

Parameters* required

table_name*string

one of

financial_statements · company_snapshot · price_volume_history · earning_call_summary · insider_and_institution_activities · index_price

list_tablesList 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 i...1 params

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 i...

Parameters* required

categoriesarray

Altdata category names (see tool description for the list). Omit, or pass "all", for the category index.

news_searchUse 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 =...8 params

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 =...

Parameters* required

order_bystring

Result ordering. relevance (default) | event_time (newest event time first) | create_time (most recently ingested first).one of relevance · event_time · create_time

querystring

Semantic query (English). One of query/theme/ticker/since/until required.

search_typestring

all (default) | events | claims (opinions/statements only).one of all · events · claims

sincestring

ISO8601; filter time_event >= since.

themestring

Theme word, resolved to the nearest canonical theme. Not valid with search_type=claims.

tickervalue

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...

top_kinteger

Story count. Default 10, max 50.

untilstring

ISO8601; filter time_event < until.

industry_inflectionsSearch 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...5 params

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...

Parameters* required

impact_companiesboolean

Include the per-company company_impacts list. Default false.default: false

keywordstring

Optional case-insensitive text contained in the theme name or research summary, up to 200 characters.

limitinteger

Results per page. Default 10, max 10.

pageinteger

One-based page number. Default 1.

tickervalue

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.

ai_adoptionSearch 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. Ret...6 params

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. Ret...

Parameters* required

application_namestring

Case-insensitive partial application-name match. Empty means no filter.

company_namestring

Case-insensitive partial company-name match. Empty means no filter.

limitinteger

Results per page. Default 10, max 10.

pageinteger

One-based page number. Default 1.

sincestring

Only return observations with update_date on or after this date. Use YYYY-MM-DD.

tickervalue

Optional US ticker filter, up to 10 symbols. Accepts one symbol or a list. Company names are not resolved.

Readme

🌐 English · 中文

drillr · The financial data and research MCP for AI agents

Filings, statements, earnings, ownership, events, executives, analyst data, company discovery and research signals for US, China and Japan equities — every figure traced to the document it came from.

View the full README on GitHub

Details

Repository: github.com/little-grebe-inc/drillr-mcp-server
Website: drillr.ai/docs/mcp?ref=mp_registry
Category: Data & Analytics
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related Data & Analytics MCP servers

View all

HasData Google Mapshasdata/google-maps-mcpGoogle Maps places, reviews, contributor history, photos and posts as JSON. No Google Cloud.10stars

HasData Google Scholarhasdata/google-scholar-mcpGoogle Scholar search results, citation counts and citation export formats, as structured JSON.10stars

HasData TikTokhasdata/tiktok-mcpPublic TikTok profiles, videos, comments and keyword search as JSON. No developer account.10stars

Pipeworxpipeworx-io/pipeworxLive data gateway for AI — 3,300+ tools across 750+ sources, with citations10stars

Seatableseatable/seatable-mcpMCP server for SeaTable — read, write, search, link, and query data in your bases10stars

Web Validator by DigestSEOakzar1el/mcp-web-validatorAudit public webpages and supplied markup for HTML, CSS, SEO, JSON-LD, and link issues.9stars