Server definition
- Hash
- sha256:32f2a6263dfdb2d34ea8a4f261376a2633c936892da4a68e90ce0b978bfa3282
- What it is
- What a remote MCP server returned when asked what it offers: 10 tools
The blob, as servednamed by its sha256
{
"instructions": "Drillr's data backend for global financial markets.\n\nCore equity coverage: US, Japan, and China A-shares. Ticker format: US bare (AAPL); Japan `.T` (6758.T); A-shares `.SH`/`.SZ` (600519.SH). Quote symbols containing \".\" or \"^\" in SQL.\n\nSpecialized datasets can be narrower: earnings calls/calendar US+JP; analyst, ownership, executive, 8-K events, and extended-hours US-only. Resolve company names with ticker_lookup first. Before treating an empty result as a finding, call get_table_schema — its note states the table's coverage.\n\nTools:\n- list_tables / get_table_schema: discover tables; one table's columns + coverage note\n- run_sql: read-only SQL over the financial tables\n- company_search: companies by natural-language description\n- ticker_lookup: name or ticker to canonical symbol\n- filing_list: a company's SEC filings\n- filing_search: as-reported facts (original and restated) + filing text\n- industry_inflections: industry inflection research (US)\n- ai_adoption: enterprise AI applications from earnings calls (US)\n- news_search: company and market news",
"tools": [
{
"description": "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.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"application_name": {
"description": "Case-insensitive partial application-name match. Empty means no filter.",
"maxLength": 200,
"type": "string"
},
"company_name": {
"description": "Case-insensitive partial company-name match. Empty means no filter.",
"maxLength": 200,
"type": "string"
},
"limit": {
"description": "Results per page. Default 10, max 10.",
"maximum": 10,
"minimum": 1,
"type": "integer"
},
"page": {
"description": "One-based page number. Default 1.",
"minimum": 1,
"type": "integer"
},
"since": {
"description": "Only return observations with update_date on or after this date. Use YYYY-MM-DD.",
"type": "string"
},
"ticker": {
"anyOf": [
{
"maxLength": 16,
"pattern": "^[A-Z0-9]+(?:[.-][A-Z0-9]+)*$",
"type": "string"
},
{
"items": {
"$ref": "#/properties/ticker/anyOf/0"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
}
],
"description": "Optional US ticker filter, up to 10 symbols. Accepts one symbol or a list. Company names are not resolved."
}
},
"type": "object"
},
"name": "ai_adoption",
"outputSchema": null
},
{
"description": "Use for qualitative company discovery (industry, business model, supply chain, competitors, management background). For numerical screening (revenue, margins, ratios, growth rates) use run_sql on company_snapshot instead.\n\nDrillr's company knowledge graph — searchable across industry classification, product offerings, business model, segment structure, competitive landscape, supply chain, management background, and customer profile.\n\nCoverage: US, Japan, Hong Kong, China A-shares, and Korea. `market` accepts one lowercase value or a list from `us | jp | hk | cn | kr`; omit it or pass `[]` for all five. List order does not set priority.\n\nPass a natural-language description (for example, \"Hong Kong and China EV battery suppliers\"). Returns a structured list of matching companies with context snippets.\n\nONLY for finding a LIST of companies by description.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"market": {
"anyOf": [
{
"enum": [
"us",
"jp",
"hk",
"cn",
"kr"
],
"type": "string"
},
{
"items": {
"$ref": "#/properties/market/anyOf/0"
},
"maxItems": 5,
"type": "array"
}
],
"description": "Optional market filter. Pass one lowercase value or a list from 'us' | 'jp' | 'hk' | 'cn' | 'kr'. Omit or pass [] for all five; list order does not set priority."
},
"query": {
"description": "Natural-language company description",
"minLength": 1,
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "company_search",
"outputSchema": null
},
{
"description": "Use to discover which SEC filings exist for a ticker before searching content.\nFor the actual content use filing_search instead.\n\nList indexed SEC filings for a given ticker with a summary header.\n\nReturns: summary (period coverage, per-type counts) + table of up to 50 filings\n(fiscal_year, fiscal_quarter, filing_type, filing_date, period_start, period_end).\n\nfiling_types filter: omit for main reports only (US 10-K/10-Q/20-F/S-1/DEF 14A\n+ /A amendments; JP 120/140/160; A-share annual_report / quarterly_report /\nq1_report; excludes ad-hoc 8-K/6-K); pass [] for all indexed types; pass explicit\nallowlist to override.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"filing_types": {
"description": "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.",
"items": {
"type": "string"
},
"type": "array"
},
"ticker": {
"description": "Stock ticker, e.g. NVDA, 6758.T, 00700.HK, 600519.SH",
"type": "string"
}
},
"required": [
"ticker"
],
"type": "object"
},
"name": "filing_list",
"outputSchema": null
},
{
"description": "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.\n\n`ticker` is REQUIRED. When `## Facts` is empty, read `## Passages` — the figure is usually stated in the filing text.\n\n`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.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"as_of": {
"$ref": "#/properties/period_start",
"description": "Publication cutoff date YYYY-MM-DD. Rows with missing published_at still appear; not a strict point-in-time snapshot"
},
"fiscal_period": {
"anyOf": [
{
"enum": [
"Q1",
"Q2",
"Q3",
"Q4",
"H",
"9M",
"FY"
],
"type": "string"
},
{
"items": {
"$ref": "#/properties/fiscal_period/anyOf/0"
},
"maxItems": 7,
"minItems": 1,
"type": "array"
}
],
"description": "Q1 | Q2 | Q3 | Q4 | H | 9M | FY, or a list of those"
},
"period_end": {
"$ref": "#/properties/period_start",
"description": "Calendar end date YYYY-MM-DD (calendar, not fiscal)"
},
"period_start": {
"description": "Calendar start date YYYY-MM-DD (calendar, not fiscal; resolve fiscal periods via financial_statements period_start/period_end)",
"type": "string"
},
"period_type": {
"description": "instant or duration",
"enum": [
"instant",
"duration"
],
"type": "string"
},
"query": {
"description": "Natural-language financial metric query",
"minLength": 1,
"type": "string"
},
"ticker": {
"description": "Required. Canonical or historical ticker; one only. Resolve company names with ticker_lookup first",
"minLength": 1,
"type": "string"
},
"top_k": {
"description": "Max results; 1-30, default 10",
"maximum": 30,
"minimum": 1,
"type": "integer"
}
},
"required": [
"query",
"ticker"
],
"type": "object"
},
"name": "filing_search",
"outputSchema": null
},
{
"description": "Column definitions (name, type, description) for a data table, plus its usage note where one exists: required filters, ticker format, and market coverage.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"table_name": {
"enum": [
"financial_statements",
"company_snapshot",
"price_volume_history",
"earning_call_summary",
"insider_and_institution_activities",
"index_price",
"equity_extended_rt",
"analyst_ratings",
"analyst_ratings_consensus",
"earning_call_calendar",
"executive_profile",
"executive_compensation",
"executive_change",
"company_deal_events",
"debt_issuance",
"securities_offering",
"eia_generators",
"eia_retail_prices",
"eia_regional_hourly",
"epochai_data_centers",
"epochai_data_center_timelines",
"epochai_gpu_clusters",
"epochai_dc_cooling_towers",
"epochai_dc_chillers",
"epochai_chip_types",
"epochai_ml_hardware",
"epochai_chip_organizations",
"epochai_chip_sales_cumulative",
"epochai_chip_sales_by_chip",
"epochai_chip_sales_by_designer",
"epochai_chip_owners_cumulative_by_chip",
"epochai_chip_owners_cumulative_by_designer",
"epochai_chip_owners_quarters_by_chip",
"tsmc_revenue",
"twcustoms_trade",
"computeprices_gpus_dim",
"computeprices_gpu_offer_daily",
"computeprices_gpu_offers",
"computeprices_providers_dim",
"skypilot_ondemand_price",
"skypilot_spot_price",
"skypilot_instance_dim",
"epochai_models",
"epochai_benchmark_scores",
"epochai_benchmark_runs",
"epochai_ai_companies",
"epochai_ai_companies_revenue_reports",
"epochai_ai_companies_usage_reports",
"epochai_ai_companies_staff_reports",
"epochai_ai_companies_funding_rounds",
"epochai_ai_companies_compute_spend",
"epochai_polling",
"arena_leaderboard",
"litellm_price_history",
"litellm_models_dim",
"computeprices_llm_prices",
"computeprices_llm_price_daily",
"computeprices_llms_dim",
"comtrade_country",
"comtrade_hs_code",
"census_import_export",
"fred_series",
"fred_observations",
"fred_macro_daily",
"polymarket_events",
"polymarket_markets",
"polymarket_outcomes",
"polymarket_trades",
"polymarket_daily",
"polymarket_volume_daily",
"polymarket_holders_daily",
"kalshi_events",
"kalshi_markets",
"kalshi_trades",
"kalshi_daily",
"kalshi_volume_daily",
"mineral_deposit",
"mineral_deposit_commodity",
"mineral_deposit_operator",
"mineral_country_supply",
"mineral_critical_snapshot",
"fiscal_year_config"
],
"type": "string"
}
},
"required": [
"table_name"
],
"type": "object"
},
"name": "get_table_schema",
"outputSchema": null
},
{
"description": "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.\n\nAll 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.`\n\nReturns 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`.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"impact_companies": {
"default": false,
"description": "Include the per-company company_impacts list. Default false.",
"type": "boolean"
},
"keyword": {
"description": "Optional case-insensitive text contained in the theme name or research summary, up to 200 characters.",
"maxLength": 200,
"minLength": 1,
"type": "string"
},
"limit": {
"description": "Results per page. Default 10, max 10.",
"maximum": 10,
"minimum": 1,
"type": "integer"
},
"page": {
"description": "One-based page number. Default 1.",
"minimum": 1,
"type": "integer"
},
"ticker": {
"anyOf": [
{
"maxLength": 16,
"pattern": "^[A-Z0-9]+(?:[.-][A-Z0-9]+)*$",
"type": "string"
},
{
"items": {
"$ref": "#/properties/ticker/anyOf/0"
},
"maxItems": 10,
"minItems": 1,
"type": "array"
}
],
"description": "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."
}
},
"type": "object"
},
"name": "industry_inflections",
"outputSchema": null
},
{
"description": "List alternative-data tables under the given categories. Returns each table's name,\none-line purpose, and column names (call get_table_schema if you need column\ntypes/comments). Batch up to 5 categories in one call; omit categories, or pass [\"all\"], to\nget the category index instead.\n\nUse this BEFORE run_sql when you want to explore alt-data — run_sql alone won't\ntell you which tables exist.\n\nAvailable categories:\n- Energy & Power — US power plants, electricity prices, regional hourly generation/demand\n- Data Centers — facilities, GPU clusters, cooling\n- Semiconductors — AI chip specs, sales, ownership, foundry revenue, customs trade\n- Compute Pricing — GPU rental, cloud VM spot/on-demand, instance specs\n- Model Development — model specs, benchmarks, AI companies, AI polling, LLM arena\n- Inference Economics — LLM API pricing across providers\n- Macro & Trade — UN Comtrade, US Census trade flows, FRED macro series\n- Prediction Markets — Polymarket and Kalshi events, markets, trades, daily aggregates\n- Critical Minerals — USGS mineral deposits, country supply, critical materials",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"categories": {
"description": "Altdata category names (see tool description for the list). Omit, or pass \"all\", for the category index.",
"items": {
"enum": [
"Energy & Power",
"Data Centers",
"Semiconductors",
"Compute Pricing",
"Model Development",
"Inference Economics",
"Macro & Trade",
"Prediction Markets",
"Critical Minerals",
"all"
],
"type": "string"
},
"maxItems": 5,
"type": "array"
}
},
"type": "object"
},
"name": "list_tables",
"outputSchema": null
},
{
"description": "Use for any news, event, development, or statement question about a company,\ntheme, or the market. The `ticker` filter takes exchange-suffixed symbols.\n\nReturns Markdown: a `## Stories` numbered list (each storyline once), then flat\n`## Events` and `## Claims` tables (claims = attributed statements: analyst\nactions, corporate guidance, central-bank remarks). The Events `story` column\nrefers back to the Stories number. `sources` counts corroborating reports;\n`first_reported`/`last_reported` give the reporting span. Lowest-ranked stories\nare dropped to fit length; the meta line flags how many were omitted.\n\nAt least one of query/theme/ticker/since/until is required. Per-parameter detail\nis on the input schema — search_type=claims needs query/ticker/a time window,\nnot theme.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"order_by": {
"description": "Result ordering. relevance (default) | event_time (newest event time first) | create_time (most recently ingested first).",
"enum": [
"relevance",
"event_time",
"create_time"
],
"type": "string"
},
"query": {
"description": "Semantic query (English). One of query/theme/ticker/since/until required.",
"type": "string"
},
"search_type": {
"description": "all (default) | events | claims (opinions/statements only).",
"enum": [
"all",
"events",
"claims"
],
"type": "string"
},
"since": {
"description": "ISO8601; filter time_event >= since.",
"type": "string"
},
"theme": {
"description": "Theme word, resolved to the nearest canonical theme. Not valid with search_type=claims.",
"type": "string"
},
"ticker": {
"anyOf": [
{
"type": "string"
},
{
"items": {
"type": "string"
},
"type": "array"
}
],
"description": "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."
},
"top_k": {
"description": "Story count. Default 10, max 50.",
"maximum": 50,
"minimum": 1,
"type": "integer"
},
"until": {
"description": "ISO8601; filter time_event < until.",
"type": "string"
}
},
"type": "object"
},
"name": "news_search",
"outputSchema": null
},
{
"description": "PostgreSQL SELECT over financial / market / alt-data tables — returns structured rows.\n\nHard rules (query fails otherwise):\n- SELECT only, no CTE (`WITH ... AS`) — use subqueries.\n- Period columns are TEXT, not dates — `period_end` is 'YYYY-MM'. Compare as strings (`period_end >= '2024-01'`); a `::date` cast on it fails.\n- Filter structured tables by ticker (`WHERE ticker IN ('AAPL','MSFT')`; screening: add `ticker NOT LIKE '%-%'` to drop preferred stock).\n\nTables by domain (get_table_schema gives columns + coverage note):\n- Market: price_volume_history (OHLCV history; MUST filter ticker + time_frame), index_price, equity_extended_rt (pre/after/overnight quotes)\n- Fundamentals: financial_statements (GAAP income/balance/cashflow), company_snapshot (ratios, per-share, growth)\n- Earnings: earning_call_summary, earning_call_calendar\n- Analyst: analyst_ratings, analyst_ratings_consensus\n- Ownership: insider_and_institution_activities\n- 8-K events: executive_change, company_deal_events, debt_issuance, securities_offering\n- Executives: executive_profile, executive_compensation\n- Alt-data: macro / industry / trade / AI-supply-chain — call list_tables(categories=[...])",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"sql": {
"description": "PostgreSQL SELECT query",
"type": "string"
}
},
"required": [
"sql"
],
"type": "object"
},
"name": "run_sql",
"outputSchema": null
},
{
"description": "Resolve a company name, brand, or ticker substring to canonical ticker(s).\n\nInput:\n- query (required): company name, brand, or ticker substring, e.g. \"Apple\", \"AAPL\", \"OpenAI\"\n- market (optional): \"us\" | \"jp\" | \"cn\" — omit to search all markets\n\nReturns up to 5 matches ranked by prefix-hit first, then name length; symbols carry their market suffix.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"market": {
"description": "Optional market filter: 'us' | 'jp' | 'cn'. Omit to search all markets.",
"enum": [
"us",
"jp",
"hk",
"cn",
"kr"
],
"type": "string"
},
"query": {
"description": "Company name or ticker substring (case-insensitive). Matches historical names + tickers too.",
"minLength": 1,
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "ticker_lookup",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:32f2a6263dfdb2d34ea8a4f261376a2633c936892da4a68e90ce0b978bfa3282 | sha256sum