warehouse mcp for Cursor

io.github.kalehdoo/warehouse-mcp

Production MCP server for Postgres, Oracle, Snowflake, BigQuery, Redshift, DuckDB, MotherDuck.

client:Cursor transport:stdio runtime:npm

Install warehouse mcp in Cursor

~/.cursor/mcp.json · windows: %USERPROFILE%\.cursor\mcp.json

MCP_TRANSPORT

WAREHOUSE_TYPE

MCP_API_KEYS

DUCKDB_PATH

MOTHERDUCK_TOKEN

PG_HOST

PG_DATABASE

PG_USER

PG_PASSWORD

ORACLE_USER

ORACLE_PASSWORD

ORACLE_CONNECT_STRING

SNOWFLAKE_ACCOUNT

SNOWFLAKE_USER

SNOWFLAKE_PRIVATE_KEY_PATH

BIGQUERY_PROJECT

GOOGLE_APPLICATION_CREDENTIALS

GUARDRAIL_PII_MASK

MCP_RATE_LIMIT_RPM

Held in this page only — never stored, logged, or sent anywhere but back to your screen.

{
  "mcpServers": {
    "warehouse-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "warehouse-mcp"
      ],
      "env": {
        "MCP_TRANSPORT": "<MCP_TRANSPORT>",
        "WAREHOUSE_TYPE": "<WAREHOUSE_TYPE>",
        "MCP_API_KEYS": "<MCP_API_KEYS>",
        "DUCKDB_PATH": "<DUCKDB_PATH>",
        "MOTHERDUCK_TOKEN": "<MOTHERDUCK_TOKEN>",
        "PG_HOST": "<PG_HOST>",
        "PG_DATABASE": "<PG_DATABASE>",
        "PG_USER": "<PG_USER>",
        "PG_PASSWORD": "<PG_PASSWORD>",
        "ORACLE_USER": "<ORACLE_USER>",
        "ORACLE_PASSWORD": "<ORACLE_PASSWORD>",
        "ORACLE_CONNECT_STRING": "<ORACLE_CONNECT_STRING>",
        "SNOWFLAKE_ACCOUNT": "<SNOWFLAKE_ACCOUNT>",
        "SNOWFLAKE_USER": "<SNOWFLAKE_USER>",
        "SNOWFLAKE_PRIVATE_KEY_PATH": "<SNOWFLAKE_PRIVATE_KEY_PATH>",
        "BIGQUERY_PROJECT": "<BIGQUERY_PROJECT>",
        "GOOGLE_APPLICATION_CREDENTIALS": "<GOOGLE_APPLICATION_CREDENTIALS>",
        "GUARDRAIL_PII_MASK": "<GUARDRAIL_PII_MASK>",
        "MCP_RATE_LIMIT_RPM": "<MCP_RATE_LIMIT_RPM>"
      }
    }
  }
}

Use .cursor/mcp.json in a project root instead to scope it to that project. Cursor merges both. Cursor docs

warehouse mcp in other clients

warehouse mcp MCP server