Drillr — The financial MCP for AI agents by drillr.ai
MCP server · Data providers · indexed, not reviewed
Hostedvendor's own
Not reviewed
No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.
Financial data and research MCP for US/CN/JP equities: filings, statements, ownership, signals.
Facts
- MCP registry
ai.drillr/drillr· 2.3.0- Endpoint
https://gateway.drillr.ai/mcp/data- GitHub stars
- 8
- Registry entry
- updated 13 Sep 2026
From the official MCP registry, the package registries and our own checks. JSON · Markdown
Why it's listed
- It's published in the registry under drillr.ai, a namespace the registry only gives to whoever proves they control that domain.
Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.
Tools it lists 10 · about 4,590 tokens of context · checked 23 hours ago
| Tool | What it does | Hint |
|---|---|---|
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. Returns: summary… | read-only |
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. When `## Facts` is… | read-only |
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… | read-only |
ticker_lookup | 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" —… | read-only |
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 —… | read-only |
get_table_schema | Column definitions (name, type, description) for a data table, plus its usage note where one exists: required filters, ticker format, and market coverage. | read-only |
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;… | read-only |
news_search | 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… | read-only |
industry_inflections | 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… | read-only |
ai_adoption | 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… | read-only |
What https://gateway.drillr.ai/mcp/data answered to tools/list, asked without credentials over MCP 2025-11-25. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.
How its tools read to an agent 0 errors · 5 warnings · 1 note
- warnTC11get_table_schemaits one parameter, table_name, has no description
- warnTC15ai_adoptioninputSchema uses $ref/$defs
- warnTC15company_searchinputSchema uses $ref/$defs
- warnTC15filing_searchinputSchema uses $ref/$defs
- warnTC15industry_inflectionsinputSchema uses $ref/$defs
- noteTC24server10 of 10 tools have no outputSchema
The checks from /check and anchor check, run each day on the list above: about 4,590 tokens of definitions. Not part of the score yet. Check your own server.