Drillr — The financial MCP for AI agents

Browser sign-in, no API key to copy. One hosted Streamable HTTP endpoint, ten tools: turn a name or a description into tickers, list and search a company's filings (structured as-reported facts and the filed text), run read-only SQL over the financial tables, and pull research signals from earnings calls and news.

⭐ If drillr helps your agent, star us — that's how we know to keep building this in the open.

Install drillr MCP

To install or connect drillr MCP, read the official installation guide. It is the maintained source for client-specific setup, browser OAuth sign-in, and connection checks.

Paste this into the app where you want to use drillr:

Please connect drillr MCP in this app using this installation guide: https://drillr.ai/developer/mcp-install.md. Walk me through sign-in and verify the connection.

The public server is drillr-data at https://gateway.drillr.ai/mcp/data (Streamable HTTP). Browser OAuth is the default. The guide covers client-specific requirements and the API-key fallback for clients without OAuth support.

For manual setup and tool reference, see drillr.ai/docs/mcp.

Agent skill

The companion drillr skill adds research workflows for MCP and REST. Installing the skill is optional for connecting the MCP server:

npx skills add Little-Grebe-Inc/drillr-skill

Distribution options

• Smithery listing
• This repository also provides a Claude Code plugin marketplace:

/plugin marketplace add Little-Grebe-Inc/drillr-mcp-server
/plugin install drillr

After installing a plugin, use the official guide for sign-in and verification in the selected client.

Hello World

"What does NVDA's latest 10-K say about supply commitments, and how did data-center revenue move over the last four quarters?"

1. The agent calls ticker_lookup if it only has a name, filing_list to see what is indexed, then filing_search — which returns as-reported facts (value, period, XBRL concept, accession number) and the passages they sit in, in one call.
2. For the quarterly series it calls run_sql on financial_statements.
3. You get an answer whose every number cites its filing. Typical round-trip 8–15 s.

The ten tools

Each tool has a page at https://drillr.ai/docs/mcp/<tool> with parameters, limits and error shapes; the server's tools/list carries the same descriptions. The set stays small on purpose: the agent composes them.

Group	Tool	What it does	Cost
Company	ticker_lookup	Name, brand or ticker substring → canonical symbols, historical names included	free
	company_search	Natural-language description → companies with a match reason; US / CN / JP / HK / KR; all matches returned	3–5 cr
Filings	filing_list	Which filings are indexed for a ticker: fiscal period, type, filing date	0.1 cr
	filing_search	Search one company's filings; returns structured as-reported facts and the filing text together	0.1 cr
Datasets	list_tables	Alt-data category index, or the tables under up to five categories	free
	get_table_schema	One table's columns, types and usage note — required filters, coverage, gotchas	free
	run_sql	One read-only PostgreSQL SELECT over the financial, market and alt-data tables	0.1 cr
Signal	industry_inflections	Industry changes synthesized from many US earnings calls: mechanism, scope, degree, per-company impact	1 cr
	ai_adoption	Concrete enterprise AI applications disclosed on US earnings calls: workflow, stage, value, evidence	1 cr
	news_search	Semantic search over company and market news: storylines, events, attributed claims	0.2 cr

What the data is

Built by drillr from primary sources — filings taken from each market's official channel (SEC EDGAR, cninfo, EDINET) and parsed in house, what companies publish on the web (IR pages, earnings calls, news), and drillr's own estimates. No data vendor in between. Every reported figure links back to the passage it was filed in. Provenance per dataset: https://drillr.ai/docs/provenance.

Dataset	What is in it	How to reach it	Coverage
Company	Ticker resolution from any name, code, ISIN, CIK or CUSIP; discovery by description; profile (exchange, industry, listing date, website, headcount)	ticker_lookup, company_search; company_snapshot via SQL	US CN JP (discovery + HK KR)
Filings	Filing index with form type, date and official link; full-text search in EN / ZH / JA; as-reported fact records with value, unit, period, filing and position, linked in a knowledge graph so the right version of a figure wins	filing_list, filing_search	US CN JP
Financials	Income statement, balance sheet, cash flow as reported under each market's standard, annual and quarterly; precomputed valuation, margin, return, growth, leverage and liquidity metrics	run_sql on financial_statements, company_snapshot	US JP HK CN KR
Prices	Daily / weekly / monthly OHLCV, indices, pre- and after-market quotes	run_sql on price_volume_history, index_price, equity_extended_rt	equities US JP HK CN KR; indices, FX, crypto, commodities
Earnings	Calendar with estimates and actuals; structured call summaries (highlights, guidance, risks, segments, Q&A)	run_sql on earning_call_calendar, earning_call_summary	US JP
Ownership	Insider holdings and transactions (Forms 3 / 4 / 5); institutional quarterly positions (13F-HR)	run_sql on insider_and_institution_activities	US
Events	8-K corporate events: executive changes, deals, debt issuance, securities offerings; 13D / G stake changes	run_sql on executive_change, company_deal_events, debt_issuance, securities_offering	US
Executives	Roster with status; annual compensation from DEF 14A	run_sql on executive_profile, executive_compensation	US
Analyst	Individual rating and target changes; consensus distribution and targets	run_sql on analyst_ratings, analyst_ratings_consensus	US
Signal	Conclusions drawn by drillr with the evidence quoted: industry inflections, enterprise AI adoption, cross-source news storylines and attributed claims	industry_inflections, ai_adoption, news_search	US (news: US CN JP + macro)
Alt-data (secondary)	9 categories, 65 tables around the AI supply chain and macro: energy & power, data centers, semiconductors, compute pricing, model development, inference economics, macro & trade, prediction markets, critical minerals	list_tables → get_table_schema → run_sql	global

Ticker forms: US bare (AAPL), A-shares .SH / .SZ (600519.SH), Japan .T (6758.T), Hong Kong .HK (00700.HK), Korea .KS / .KQ (005930.KS); indices ^GSPC; quote symbols with . or ^ in SQL. Freshness: filings, ownership and events within minutes of the filing; calls and news within minutes to hours; statements and analyst data daily.

Benchmark: the drillr MCP-powered model scores 94.06 % on Vals Finance Agent, and drillr publishes its own restatement-aware benchmark — https://drillr.ai/drillr-benchmark.

REST API

The same data as 29 typed REST endpoints for scripts and pipelines — one X-API-KEY header, JSON out, public OpenAPI 3.1 contract:

curl -H "X-API-KEY: $DRILLR_API_KEY" \
  "https://gateway.drillr.ai/api/v2/income-statements?ticker=AAPL&period=FY&limit=4"

Reference: https://drillr.ai/docs/api · Contract: https://gateway.drillr.ai/api/v2/openapi.json. The older /api/v1/data/* tool mirrors are documented in docs/rest-api.md.

Pricing and limits

One credit wallet across MCP and REST. Free: 80 credits on sign-up. Plus $29 / 300 cr per month, Ultra $99 / 1,500 cr, Enterprise for redistribution and SLA. run_sql returns 100 rows (500 on Ultra), 10 s per statement, 5 in flight; company_search is capped per day (20 / 100 / 500). Failed calls are not billed. https://drillr.ai/pricing

Out of scope

Private or unlisted companies · on-chain crypto metrics (CEX prices only) · options chains, order book, tick data · placing orders · drillr does not produce its own price forecasts.

Community

Discord	WeChat
Devs building agentic research products — office hours, debugging help, early access.	Chinese-speaking dev community — fastest product feedback.

License

MIT — see LICENSE.