NY Benchmark

- “What is Syracuse’s fund balance as a percentage of expenditures?”
- “Compare police spending per capita across Buffalo, Rochester, and Yonkers”
- “Which cities have the highest debt service burden?”
- “Show me NYC’s revenue sources over the last 10 years”
- “Rank all towns by per capita spending”
- “Which villages spend the most on public safety?”
- “What are the 10 most populated towns in New York?”
- “Which school districts spend the most per pupil?”
- “What cities are late filing with the State Comptroller?”

- 30 years of city financial data(62 cities, 1995-present) — revenue, expenditures, fund balances, debt service
- Town and village finances(933 towns, 558 villages, 1997-present) — the same OSC financial data, now queryable and rankable
- School district finances(689 districts, 2012-present) — per-pupil spending, state aid, fund balances
- County finances(57 counties, 1995-present)
- Census demographics(population, income, poverty, housing, education)
- Fiscal stress scores(OSC FSMS, 2012-present) — fiscal and environmental indicators
- Computed metrics— Fund Balance %, Debt Service %, Per-Capita Spending, available without manual calculation
- Rankings— rank any entity type by any metric, cross-type rankings (e.g. all cities, towns, and villages together), top/bottom N

Most government data APIs return raw numbers and leave interpretation to the user. Our MCP server includesdomain-aware caveatsthat travel with the data:

- Comparability notesflag cities with unique reporting structures. NYC isn’t inside any county — it encompasses five boroughs that are themselves counties, and its $109B consolidated budget includes functions (like the $34B Department of Education) that are separate entities elsewhere. Plattsburgh runs its own municipal electric utility, putting debt service in enterprise funds that a naive analysis would miss. The server flags these automatically so the AI doesn’t produce misleading comparisons.
- Filing statusidentifies cities that haven’t filed recent reports, so the AI doesn’t silently present stale data as current
- Data quality rulesexclude custodial pass-throughs and interfund transfers that inflate apparent spending
- Anti-hallucination directivesprevent the AI from fabricating benchmark thresholds or interpolating missing data

This approach follows progressive disclosure: session-level instructions set the ground rules, and response-level notes provide entity-specific context on demand.

Tested and supported.Add this to your Claude Desktop config file, then restart Claude Desktop:

- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:%APPDATA%\Claude\claude_desktop_config.json

MCP is an open standard and our endpoint (https://mcp.benchmarkusa.org/mcp) should work with any MCP-compatible client that supports remote servers. We haven’t tested these, but they may work:

The server provides five tools in a sequential workflow:
- discover_data— overview of available data sources, entity types, and year ranges
- find_entities— search for cities, counties, school districts, towns, or villages by name, kind, or filing status
- find_metrics— explore available metrics by category (revenue, expenditure, balance sheet) or search by keyword
- get_data— retrieve time-series data for specific entities and metrics
- rank_entities— rank entities by any metric (top/bottom N, cross-type rankings like all cities + towns + villages together)

Domain rules are applied automatically. You don’t need to know about T-fund exclusions, interfund transfer adjustments, or GASB 54 fund balance classifications — the server handles them and attaches explanatory notes to responses when relevant.

All data comes from official government sources:

Access Chinese stock market data, including historical prices, real-time quotes, news, and financial statements.

Interact with the Aptos blockchain, supporting both testnet and mainnet for AI applications.

Provides A-share stock market data, including basic info, historical K-lines, financial indicators, and macroeconomic data using Baostock.

AudioAlpha turns 100+ daily finance and crypto podcasts into structured intelligence — α-sentiment scores, narrative signals, asset mentions, transcripts, and market snapshots with 40+ custom metrics. Built for AI-driven research and trading workflows.

Access live U.S. congressional data from the Congress.gov API.

Access Binance cryptocurrency market data, including prices, candlestick charts, and order books.

Access BrianKnows' extensive blockchain knowledge base.

A read-only MCP server for querying live Avalara AvaTax data. Powered by the CData JDBC Driver.