Natural language to SQL for Snowflake

Connect Snowflake and ask your first question

Install the package, register the connection once, build the knowledge base, and query. Leave out --password and it is prompted for without echoing, then stored in your OS keychain rather than the connectors file. Only where no keychain is available does it go into the stored connection URL, with a warning.

$ pip install "nlqueries-core[snowflake]"
$ nlqueries connect snowflake --account myorg.us-east-1 --database ANALYTICS --schema PUBLIC --warehouse COMPUTE_WH --user alice --alias snow-prod
$ nlqueries process-history snow-prod --annotate
$ nlqueries export-kb snow-prod
$ nlqueries query snow-prod "how many orders were placed last month by first-time customers?"

How NL2SQL works on Snowflake

Most text-to-SQL tools hand the LLM a schema dump and hope. NLQueries builds a YAML knowledge base from your Snowflake schema and from real query history, in this case SNOWFLAKE.ACCOUNT_USAGE.QUERY_HISTORY, so it learns which joins your team actually uses and what your columns mean. That knowledge base is what the model sees when it writes SQL.

Every generated statement is parsed with sqlglot and refused unless it is a single read-only query, and its columns are checked against the schema in the knowledge base. It then runs read-only where the engine allows it, with a statement timeout; what each connector enforces has the details per engine. Use nlqueries ask to see the SQL without running it, or nlqueries query to run it. A semantic cache answers repeated questions without another LLM call, and runs the stored SQL again so the rows are current.

Snowflake-specific details

Reading ACCOUNT_USAGE.QUERY_HISTORY needs IMPORTED PRIVILEGES on the SNOWFLAKE database. Without it, the connector falls back to the INFORMATION_SCHEMA.QUERY_HISTORY() table function, which covers the last 7 days only. If neither can be read, process-history stops with an error. Within those limits --days N is honoured.

Snowflake has no read-only transaction to ask for. The connector runs each query between BEGIN and ROLLBACK, which undoes DML, but DDL is not transactional on Snowflake, so a CREATE or DROP that ran stays. Use a role with SELECT only; the database hardening guide has the grant.

Point the connector at the warehouse you want to pay for: every generated query runs on the warehouse named in --warehouse. The statement timeout is sent as Snowflake statement parameters, split between time queued and time running.

Full connector notes are in the connectors guide, and the read-only role to create is in database hardening. This connector covers Snowflake Data Cloud on AWS, Azure or GCP.

Use it from Claude, Cursor or any MCP client

Run nlqueries mcp-server start and point Claude Desktop, Cursor, or any Model Context Protocol client at it. Its query tool generates SQL through the same pipeline, runs it read-only and returns the rows. Over stdio, the transport desktop clients use, there is nothing to configure. A network transport will not start without authentication, by OIDC or a pre-shared token, and grants per agent and action decide who may run SQL. See MCP authentication.