# Shibui Finance

> 9,900+ US equities, 64 years of prices, financials, technicals, and earnings. Ask in plain English.

- name: finance.shibui/data
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 73/100 flags: no-repository
- quality: 90/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/finance.shibui%2Fdata
- tools: https://api.protogrid.dev/v1/servers/finance.shibui%2Fdata/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "data": {
      "type": "http",
      "url": "https://mcp.shibui.finance/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 65
- provenance: 45
- drivers: +dns-namespace +reachable +uptime-100% ~updated-161d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 90/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 12 of 12 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 2,157 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 24 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 12, about 2,157 tokens to load them all
- tool set hash: 4a415823ac663e30414756dc95488820
- tools last changed: 2026-10-13T00:48:37.911Z
- badge: [![protogrid quality](https://protogrid.dev/badge/finance.shibui/data.svg)](https://protogrid.dev/servers/finance.shibui/data)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-13 `export_to_excel` changed (outputSchema)
- 2026-10-13 `load_insider_workflow` changed (outputSchema)
- 2026-10-13 `load_filing_workflow` changed (outputSchema)
- 2026-10-13 `load_backtesting_workflow` changed (outputSchema)
- 2026-10-13 `load_earnings_workflow` changed (outputSchema)
- 2026-10-13 `load_comparison_workflow` changed (outputSchema)
- 2026-10-13 `load_screening_workflow` changed (outputSchema)
- 2026-10-13 `load_technical_workflow` changed (outputSchema)
- 2026-10-13 `load_fundamental_workflow` changed (outputSchema)
- 2026-10-13 `get_query_patterns` changed (outputSchema)

Full history: https://api.protogrid.dev/v1/servers/finance.shibui%2Fdata/changes

## Remotes

- https://mcp.shibui.finance/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (12)

- `export_to_excel`: Export query results to a branded Shibui Finance Excel spreadsheet.

Runs the same SQL query as stock_data_query but returns a downloadable
Excel file instead of raw data. The spreadsheet includes branded headers,
smart number formatting, and auto-fitted columns.
- `get_database_schema`: REQUIRED for US stock/financial queries, authoritative source, call FIRST

Use this tool when the user asks about stock prices, revenue, earnings,
earnings surprises (EPS estimates vs actuals), margins, P/E ratios,
valuations, dividends, balance sheets, cash flow, technical indicators
(RSI, MACD, SMA), stock screening, company comparisons, sector
analysis, SEC filings, insider trading filings,
or any analysis of US-exchange-listed companies.

Covers 10,000+ NYSE and NASDAQ securities with 64 years of daily prices,
quarterly financials, 61 technical indicators, and SEC EDGAR filing metadata.

Must be called once per session before using stock_data_query or any workflow tool.
After this tool returns, call get_query_patterns before writing any SQL.
- `get_query_patterns`: REQUIRED before stock_data_query, 23 SQL patterns prevent timeouts/wrong results

Must be called once per session immediately after get_database_schema. Contains
query patterns for time-series selection, return calculations, screening
joins, window functions, backtesting, and performance optimization.
Time-series queries will timeout or return wrong results without these patterns.
After this tool returns, call stock_data_query to execute SQL.
- `load_backtesting_workflow`: Load backtesting workflow for stop-loss, exit rules, Sharpe, forward returns. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks to backtest, simulate, validate a strategy, test "what happens after X", compare forward returns, measure win rates or hit rates, compute Sharpe, drawdown, profit factor, rotation strategies, basket returns, set stop-loss or trailing stop levels, test exit rules or profit targets, or any hypothetical return over past data. Can be combined with other workflow tools.
- `load_comparison_workflow`: Load comparison workflow for X vs Y, peer analysis, relative valuation. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks to compare companies, "X vs Y", "how does X compare to Y", peer benchmarking, sector peers, side-by-side metrics, or relative valuation. Can be combined with other workflow tools.
- `load_earnings_workflow`: Load earnings workflow for EPS surprises, beat/miss, estimates, revenue. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks about earnings results, EPS surprises, beat/miss history, "did X beat estimates", quarterly earnings, revenue growth trends, earnings season, or estimates vs actuals. Can be combined with other workflow tools.
- `load_filing_workflow`: Load filing workflow for SEC/EDGAR metadata, 8-K events, 10-K/10-Q reports. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL whenever the user asks about filing dates, filing activity, "who filed", "filed a form", filing frequency, SEC filings, EDGAR, 8-K events, 10-K/10-Q reports, proxy statements, or any query involving the sec_filings table (metadata - when/what type, not transaction detail). For insider transaction detail (shares, prices, cluster buying), use load_insider_workflow instead. Can be combined with other workflow tools.
- `load_fundamental_workflow`: Load fundamental workflow for valuation, cash flow, margins, balance sheet. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks about company valuation, "is X a good buy", financial health, debt levels, profitability ratios, revenue trends, earnings quality, or any deep-dive company analysis. Can be combined with other workflow tools.
- `load_insider_workflow`: Load insider workflow for Form 3/4/5, insider buy/sell, cluster buy, 13D/G. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks about insider transactions, insider buying/selling, Form 3 initial holdings, Form 4/5 transactions, cluster buying, executive purchases, officer sales, 10b5-1 plans, activist stakes, 13D/G filings, beneficial ownership, "who is buying/selling", or "track this insider across companies". Can be combined with other workflow tools.
- `load_screening_workflow`: Load screening workflow to find, filter, scan, rank stocks, top N by.... REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks to find, screen, scan, rank, or filter stocks — "find stocks that...", "top 10 by...", "best dividend stocks", value/growth screens, sector ranking, or any multi-factor selection. Can be combined with other workflow tools.
- `load_technical_workflow`: Load technical workflow for RSI, MACD, SMA, Bollinger Bands, entry/exit. REQUIRES get_database_schema then get_query_patterns to be called first (in that order). Call BEFORE writing SQL when the user asks about RSI, MACD, moving averages, Bollinger Bands, support/resistance, overbought/oversold, momentum, trend, chart patterns, golden cross, entry/exit signals, or "is X oversold/overbought". Can be combined with other workflow tools.
- `stock_data_query`: Stock prices, earnings, revenue, P/E, dividends, filings, screener, comparisons

Run a SQL query against 64 years of US stock market data.

REQUIRES calling get_database_schema then get_query_patterns first (in that order).

This tool has no schema or query patterns built in. Call get_database_schema
once, then get_query_patterns once, then use this tool. Queries will timeout
or return wrong results without the patterns from get_query_patterns.