mcp server
Cabrini Market Data
US equity data for AI agents — 23 years intraday + daily, SEC filings. x402 USDC payments.
Description as published by the maintainer. Source
- version 1.1.0
- active
active — Most recent push to the repository was 2026-07-26.
What this server can do
15 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.
get_bars(end, date, start, ticker, adjusted, interval)- Resampled intraday bars at custom timeframes (3, 6, 9, 12, 15, 30, 60, 240 min) for one ticker. Every bar carries absolute open/high/low/close plus fractional change from the daily open, whatever the interval, and volume and transactions. $0.015 USDC per day. Required: ticker, interval.
get_brief(date, ticker, lookback_days)- Full research brief: price, fundamentals, insiders, splits for one ticker. $0.25 USDC. Required: ticker.
get_company(ticker)- Company profile: name, CIK, industry, exchange, fiscal year. $0.005 USDC. Required: ticker.
get_filings(types, ticker, to_date, sections, accession, from_date)- SEC filing index (10-K, 10-Q, 8-K, proxies) for a ticker. $0.01 USDC; add sections=[risk_factors, mdna] to extract full section text from the latest 10-K/10-Q for $0.05. Required: ticker.
get_fundamentals(ticker, metrics, to_date, from_date)- Quarterly fundamentals from SEC EDGAR (revenue, EPS, margins, etc). $0.02 USDC. Required: ticker.
get_insiders(ticker, to_date, from_date)- Insider transactions (Form 4) from SEC EDGAR. $0.02 USDC. Required: ticker.
get_pricing- Pricing and data coverage information. Free.
get_sample- FREE, no payment: real intraday OHLCV bars for AAPL on 2024-01-02, identical in shape to a paid query. Call this first to verify data quality before spending. Takes no arguments — fixed ticker and date.
get_stats- Platform statistics. Free.
list_tickers(date)- List all tickers that traded on a given date. $0.005 USDC. Required: date.
query_batch(date, tickers)- Multiple tickers for one date. Every bar carries absolute open/high/low/close plus fractional change from that ticker's own daily open. $0.02/ticker, no limit. Required: tickers, date.
query_daily(end, start, ticker)- Daily OHLCV bars plus VWAP, range_pct and true_range_pct for one ticker over a date range. range_pct = (high - low) / open is a ready-made volatility read; true_range_pct also captures the overnight gap. Day-level aggregates — the cheapest way to cover long histories. $0.001/year. Required: ticker, start, end.
query_minute_bars(date, ticker, interval)- Full trading day of intraday bars for one US stock (interval 3-240 min, default 3m). Every bar carries absolute open/high/low/close plus pct_open/pct_high/pct_low/pct_close (fractional change from that day's open), volume and transactions. $0.025 USDC. Required: ticker, date.
query_range(end, start, ticker, interval)- Multi-day intraday bars for one ticker (interval 3-240 min, default 3m). Every bar carries absolute open/high/low/close plus fractional change from that day's own open — percentages reset daily, not cumulative. $0.01/day, no day limit. Required: ticker, start, end.
scan_market(date, limit, gap_up_pct, volume_min, gap_down_pct, range_pct_min, change_pct_max, change_pct_min, volume_ratio_min)- Scan all US stocks on a date for custom criteria (gaps, volume, change). Returns pct_change, range_pct, pct_gap, true_range_pct, volume and volume_ratio per match — criteria in percent (5 = 5%), outputs fractional (0.05 = 5%). $0.10 USDC. Required: date.
Last successful function declaration observed on . Source: https://cabrini.ai/mcp. We list what the server declared; we do not call any of these functions.
Endpoint status observed on . Source: https://cabrini.ai/mcp.
Signals
These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.
| Signal | Value | What it measures | Window | Observed | Source |
|---|---|---|---|---|---|
| GitHub stars | 1 | Number of GitHub accounts that bookmarked this repository since it was created. It is a bookmark count, not installs, not active users and not quality. | cumulative, all time | GitHub | |
| Last commit | 2026-07-26 | Date of the most recent push to any branch. This is the strongest cheap indicator of whether the project is still maintained. | point in time | GitHub | |
| Open issues | 0 | Open issues plus open pull requests, as GitHub counts them together. A high number can mean an active project or an abandoned one. | as of fetch | GitHub | |
| Latest published version | 1.1.0 | Latest version string the maintainer published to the registry. | as of fetch | Model Context Protocol | |
| Registry record last updated | 2026-07-29 | When the registry record was last updated by its maintainer. | point in time | Model Context Protocol | |
| License | MIT | Licence GitHub detected in the repository. Detection can be wrong; the LICENSE file is authoritative. | as of fetch | GitHub | |
| First listed in the MCP Registry | 2026-07-29 | Date this server was first published to the official MCP Registry. Not a usage or quality measure. | point in time | Model Context Protocol | |
| repository status | active | The repository exists on GitHub and is not archived. This says nothing about how recently it was worked on. | as of fetch | GitHub | |
| mcp tools declared | 15 tools | Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. | as of probe | cabrini.ai | |
| mcp endpoint status | ok | The server listed 15 functions when asked. | as of probe | cabrini.ai |
Where to get it
This record as data
Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.
GET /api/v1/entries/mcp_server.json