Snowflake logo

Snowflake

By Simtheory Data science

Query your Snowflake data warehouse — execute SQL, explore warehouses, databases, schemas and tables, and use Cortex AI for natural-language analytics and search.

Description

Connect to Snowflake for powerful cloud data warehouse analytics.

• 🔍 Warehouse & Schema Exploration: Discover warehouses, databases, schemas, tables and columns
• ⚡ SQL Execution: Run read-only queries via the Snowflake SQL REST API with automatic async polling and multi-partition result handling
• 🧠 Cortex Analyst: Ask natural-language questions against semantic models and get generated SQL
• 🔎 Cortex Search: Low-latency semantic search over unstructured text
• 🔒 Secure: Programmatic Access Token (PAT) authentication, per-connection credentials
• 🛡️ Read-Only by Design: Write operations (INSERT, UPDATE, DELETE, DDL) are always blocked, and results are capped at 10,000 rows

Perfect for data analysis, reporting, and exploring your Snowflake data cloud.

Available tools

Cortex Analyst (Natural Language to SQL)

Asks Snowflake Cortex Analyst a natural-language question against a semantic model or semantic view. Returns content blocks (text, sql, suggestions). Exactly one of semantic_model_file or semantic_view must be provided. Review the returned SQL, then run it with execute_query.

Cortex Search

Queries a Snowflake Cortex Search service for low-latency semantic search over unstructured text. Returns matching results with the requested columns.

Describe Table

Describes the columns of a table via DESCRIBE TABLE. Returns name, type, kind, null?, default, primary key, and unique key for each column.

Execute Query (Read-Only)

Executes a read-only SQL query (SELECT, SHOW, DESCRIBE). Write operations (INSERT, UPDATE, DELETE, DDL) are always rejected — this integration is read-only by design. Returns columns, rows (values as strings), row_count, and a truncation warning if results exceed 10,000 rows.

List Databases

Lists all databases visible to the connection via SHOW DATABASES. Returns name, origin, owner, comment, and creation time.

List Schemas

Lists all schemas in a database via SHOW SCHEMAS. Returns name, database_name, owner, comment, and creation time.

List Tables

Lists all tables in a schema via SHOW TABLES. Returns name, database_name, schema_name, kind, rows (row count), bytes, and comment.

List Warehouses

Lists all warehouses visible to the connection via SHOW WAREHOUSES. Returns name, state (STARTED/SUSPENDED), type, size, and other warehouse metadata.

How it works

1. Install

One-click install from the Simtheory store.

2. Connect

Authorize access to your Snowflake account.

3. Use

Your AI can now interact with Snowflake.

Install

Log in if you already have an account.

Details

Version 1.0.0
Updated Aug 19, 2026
Category Data science
Publisher Simtheory

Features

Cloud hosted — no setup required
Secure authentication
Automatic updates
Works with all AI models

Ready to use Snowflake?

Sign up for Simtheory and install this MCP directly into your workspace.

Get Started