SQL over 52.8B public records: USAspending, OpenAlex, patents, LEHD jobs, SEC, EPA, FERC, Medicare.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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.
Table name from list_tables, for example openalex_works.
Database name, for example govblock_scholarly.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http data-library https://data.nysgpt.com/mcp
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.
| Argument | Type | Description |
|---|---|---|
| table* | string | Table name from list_tables, for example openalex_works. |
| database* | string | Database name, for example govblock_scholarly. |
{
"type": "object",
"required": [
"database",
"table"
],
"properties": {
"table": {
"type": "string",
"description": "Table name from list_tables, for example openalex_works."
},
"database": {
"type": "string",
"description": "Database name, for example govblock_scholarly."
}
},
"additionalProperties": false
}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.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}List every table in one database with its row count. Use it to find the table that answers a question before calling describe_table.
| Argument | Type | Description |
|---|---|---|
| database* | string | A database name from list_databases, for example govblock_awards. |
{
"type": "object",
"required": [
"database"
],
"properties": {
"database": {
"type": "string",
"description": "A database name from list_databases, for example govblock_awards."
}
},
"additionalProperties": false
}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.
| Argument | Type | Description |
|---|---|---|
| sql* | string | One SQL statement, for example: SELECT publication_year, count(*) FROM govblock_scholarly.openalex_works GROUP BY 1 ORDER BY 1 |
{
"type": "object",
"required": [
"sql"
],
"properties": {
"sql": {
"type": "string",
"description": "One SQL statement, for example: SELECT publication_year, count(*) FROM govblock_scholarly.openalex_works GROUP BY 1 ORDER BY 1"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 17, 2026.