NYSgpt Data Library
Server Details
SQL over 52.8B public records: USAspending, OpenAlex, patents, LEHD jobs, SEC, EPA, FERC, Medicare.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- nyd-user-1/nysgpt-data-library
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool has a clearly distinct role in a natural discovery-to-query workflow: list databases, list tables within a database, describe a table's schema, then run SQL. There is no overlap between tools, and the descriptions reinforce the intended call order.
Three tools follow a clean verb_noun snake_case pattern (list_databases, list_tables, describe_table), while 'query' is a bare verb rather than a noun-object name. The deviation is minor and the meaning remains obvious.
Four tools is exactly the right scope for a read-only data library: database listing, table listing, schema inspection, and SQL execution. Each tool earns its place and there is no redundant surface.
The core discovery and query lifecycle is fully covered for a read-only Athena data library. Minor gaps include no cross-database keyword table search or sample-row preview, but agents can work around these using list_tables, describe_table, and query.
Available Tools
4 toolsdescribe_tableDescribe a tableARead-onlyInspect
Return the fields (name, type, description), the table description and the row count of one table. Always call this before writing SQL: many source columns are stored as text and need try_cast.
Inputs: table (required), database (required).
list_databasesList databasesARead-onlyInspect
List the databases in the NYSgpt Data Library. Each database is one subject of public records (for example govblock_awards = federal spending, govblock_patents, govblock_sec = company filings, govblock_scholarly = OpenAlex, govblock_labor, govblock_census, govblock_energy, govblock_health, govblock_courts). Call this first, then list_tables.
Inputs: no named parameters.
list_tablesList tablesARead-onlyInspect
List every table in one database with its row count. Use it to find the table that answers a question before calling describe_table.
Inputs: database (required).
queryRun SQLARead-onlyInspect
Run one read-only SQL statement (SELECT, WITH, SHOW or DESCRIBE) in the Amazon Athena (Trino) dialect and return up to 1,000 rows with column names and bytes scanned. Qualify every table as database.table. Select only the columns you need and filter on year or state columns where they exist, because each query has a scan limit (1 GB without a key, 10 GB with a paid key). Numeric text columns need try_cast(col AS double). When a daily limit is reached the error message gives the address for a paid key.
Inputs: sql (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Citable US facts w/ curated query templates: SEC financials, bank call reports, nonprofits. No key.
Public records as JSON: US permits, grants, OSHA/EPA, recalls, licenses, PACER; EU/UK/AU tenders.
US public-records intelligence for AI agents — companies, SEC, courts, spending, licenses.
US government + SEC data as clean JSON: SAM.gov, USAspending, Grants.gov, Congress, SEC filings.
Related MCP Servers
- AlicenseBqualityDmaintenanceQuery 20 structured datasets from AI agents — healthcare providers (9M NPI records), SEC EDGAR filings, PACER federal courts, USPTO patents and trademarks, OFAC sanctions screening, crypto whale wallets, DeFi liquidation signals, Polymarket smart money, economic indicators (FRED/BLS), federal contracts, NOAA weather, and OTC shell risk scoring. Pay per query, no subscriptions751MIT

DataDawn MCP Serverofficial
AlicenseNot gradedqualityBmaintenanceEnables AI agents to query the IRS 990 nonprofit database and OpenRegs federal regulations database via SQL, providing access to nonprofit filings, grants, lobbying, and congressional data.Creative Commons Zero v1.0 Universal- AlicenseNot gradedqualityCmaintenanceEnables querying, sampling, and exporting datasets from over twenty keyless free public data sources spanning the EU, Switzerland, Germany, the US, and global providers through one uniform set of tools. A single consistent interface lets users list databases and tables, inspect schemas and query guides, run queries, and export results as CSV or JSON without per-API clients.Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables querying EPA drinking-water records — public water-system inventories, historical SDWA violations, enforcement actions, Lead and Copper Rule summaries, and UCMR 5 contaminant measurements — without an API key. Also supports optional read-only SQL analysis over staged dataset partitions via DuckDB canvases.146 npm2Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.