Snowflake integration

Databases · 9 actions · Custom auth

Snowflake data warehouse integration for executing SQL queries, managing tables, and performing data operations. Uses the snowflake-connector-python SDK.

Put Snowflake to work View Snowflake integration docs

Overview

The ModuleX Snowflake integration lets a ModuleX agent operate Snowflake on your behalf — running list actions across sql queries, rows and multiple rows — directly from a plain-English request, using your organization's own Snowflake credentials. No pre-built workflow is required: the agent picks the right Snowflake action for the task.

Snowflake is a databases platform. ModuleX adds the agent layer: ask for an outcome and it selects and runs the right Snowflake action — or, when you want a repeatable process, the composer assembles a Snowflake workflow for you, streaming the nodes onto the canvas as it builds.

Ask the assistant

Drive Snowflake in plain English

Type what you want. A ModuleX agent picks the right Snowflake action — or chains several — and runs it. No workflow to build.

Show me the databases that match what I describe
resolves tolist_databases
Execute any SQL statement
resolves toexecute_sql_query
INSERT a single row from a column→value mapping
resolves toinsert_row

Use cases

What you can automate with Snowflake

Run a sql query from a plain-English requestexecute_sql_query
Pull a list of databases for a reportlist_databases
Look up a table sample on demandget_table_sample

At a glance

Snowflake integration at a glance

VendorSnowflake

CategoryDatabases

Actions available9

AuthenticationCustom

Uses your own credentialsYes

Works with the assistantYes

Works in the composerYes

Multi-step / tool-chainingYes

Technical referenceView docs

Integration version1.0.0

Last updatedJun 2026

Reference

All 9 Snowflake actions

SQL Queries1

execute_sql_query

Execute any SQL statement. Use '%s' for parameterized queries (DB-API style).

Rows1

insert_row

INSERT a single row from a column→value mapping

Multiple Rows1

insert_multiple_rows

Batched INSERT for multiple rows (configurable batch_size)

Databases1

list_databases

SHOW DATABASES — all accessible databases

Schemas1

list_schemas

SHOW SCHEMAS IN DATABASE <database>

Tables2

list_tables

SHOW TABLES IN SCHEMA <database>.<schema>

describe_table

DESCRIBE TABLE — column metadata

Warehouses1

list_warehouses

SHOW WAREHOUSES — compute resources

Table Samples1

get_table_sample

SELECT * FROM table LIMIT N — preview data

See full parameters and response schemas in the Snowflake integration docs

Two ways

Two ways to use Snowflake in ModuleX

Ask the assistantType what you want done and a ModuleX agent picks the right Snowflake action and runs it — no workflow to build.

Compose a workflowNeed it to happen every time? Describe the process and the composer wires Snowflake into a repeatable workflow you can run on a schedule, from chat, or as an API.

Security

Connecting Snowflake

CustomSnowflake uses a custom authentication flow. ModuleX encrypts whatever credentials you supply and scopes them to your organization.

Step-by-step setup in the Snowflake docs

Pairs well with Snowflake

Agents often chain Snowflake with these — connect them once and the agent can use all of them in a single task.

PostgreSQL10 actions

MySQL9 actions

Supabase8 actions

Microsoft SQL Server4 actions

FAQ

Snowflake + ModuleX FAQ

A ModuleX agent can run any of Snowflake's 9 actions — across sql queries, rows, multiple rows and databases — from a plain-English request, using your organization's own Snowflake credentials.

No. The agent selects the right Snowflake action from your prompt. A workflow is only needed when you want a repeatable process — and the composer builds that for you from a description.

Through a secure Snowflake connection; your credentials are stored encrypted and scoped to your organization.

9, spanning sql queries, rows, multiple rows and databases.

Snowflake runs on your own credentials, so any Snowflake usage is billed by Snowflake directly. ModuleX meters the agent run — and if you connect your own model keys, there's no ModuleX markup on model usage.

Put Snowflake to work in ModuleX.

Connect Snowflake once with your own credentials and let your agent run all 9 actions on demand.

Put Snowflake to work View technical docs

Last updated: Jun 2026Browse all 175 integrations →