MCPs
Snowflake MCP Server

Snowflake MCP Server

MCP server enabling secure and structured Snowflake database interaction with AI tools.

View on GitHub

170

Stars

Forks

170

Watchers

Issues

Snowflake MCP Server provides a Model Context Protocol-conformant interface to interact programmatically with Snowflake databases. It exposes SQL execution, schema exploration, and insight aggregation as standardized resources and tools accessible by AI assistants. The server offers read/write capabilities, structured resource summaries, and insight memoization suitable for contextual AI workflows. Integration is supported with popular AI platforms such as Claude Desktop via Smithery or UVX configurations.

Key Features

Standardized MCP interface for Snowflake

Read/write SQL query execution

Dedicated tools for schema exploration

Insight memoization and aggregation resource

Per-table schema summaries as resources

Integration via Smithery and UVX

Customizable configuration with TOML or parameters

Secure authentication options including private key support

Granular tool enable/disable controls

Rich return types for database metadata and results

Use Cases

Enabling AI agents to analyze and query Snowflake data

Automating database schema discovery for contextual AI applications

Structuring data context for model-based reasoning and analytics

Aggregating and surfacing data insights for continuous knowledge enrichment

Facilitating low-code/no-code exploration of enterprise Snowflake assets

Supporting interactive data analysis workflows for power users

Providing secure, auditable data access to AI-driven platforms

Enhancing AI assistant capabilities in business intelligence scenarios

Enabling integration of Snowflake operations into automated pipelines

Delivering resource summaries for efficient context-driven AI processing

README

Snowflake MCP Server

Overview

A Model Context Protocol (MCP) server implementation that provides database interaction with Snowflake. This server enables running SQL queries via tools and exposes data insights and schema context as resources.

Components

Resources

memo://insights
A continuously updated memo aggregating discovered data insights.
Updated automatically when new insights are appended via the append_insight tool.
context://table/{table_name}
(If prefetch enabled) Per-table schema summaries, including columns and comments, exposed as individual resources.

Tools

The server exposes the following tools:

Query Tools

read_query
Execute SELECT queries to read data from the database.
Input:
- query (string): The SELECT SQL query to execute
  Returns: Query results as array of objects
write_query (enabled only with --allow-write)
Execute INSERT, UPDATE, or DELETE queries.
Input:
- query (string): The SQL modification query
  Returns: Number of affected rows or confirmation
create_table (enabled only with --allow-write)
Create new tables in the database.
Input:
- query (string): CREATE TABLE SQL statement
  Returns: Confirmation of table creation

Schema Tools

list_databases
List all databases in the Snowflake instance.
Returns: Array of database names
list_schemas
List all schemas within a specific database.
Input:
- database (string): Name of the database
  Returns: Array of schema names
list_tables
List all tables within a specific database and schema.
Input:
- database (string): Name of the database
- schema (string): Name of the schema
  Returns: Array of table metadata
describe_table
View column information for a specific table.
Input:
- table_name (string): Fully qualified table name (database.schema.table)
  Returns: Array of column definitions with names, types, nullability, defaults, and comments

Analysis Tools

append_insight
Add new data insights to the memo resource.
Input:
- insight (string): Data insight discovered from analysis
  Returns: Confirmation of insight addition
  Effect: Triggers update of memo://insights resource

Usage with Claude Desktop

Installing via Smithery

To install Snowflake Server for Claude Desktop automatically via Smithery:

bash

npx -y @smithery/cli install mcp_snowflake_server --client claude

Installing via UVX

Traditional Configuration (Individual Parameters)

json

"mcpServers": {
  "snowflake_pip": {
    "command": "uvx",
    "args": [
      "--python=3.12",  // Optional: specify Python version <=3.12
      "mcp_snowflake_server",
      "--account", "your_account",
      "--warehouse", "your_warehouse",
      "--user", "your_user",
      "--password", "your_password",
      "--role", "your_role",
      "--database", "your_database",
      "--schema", "your_schema"
      // Optionally: "--private_key_path", "your_private_key_absolute_path"
      // Optionally: "--allow_write"
      // Optionally: "--log_dir", "/absolute/path/to/logs"
      // Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
      // Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
    ]
  }
}

TOML Configuration (Recommended)

json

"mcpServers": {
  "snowflake_production": {
    "command": "uvx",
    "args": [
      "--python=3.12",
      "mcp_snowflake_server",
      "--connections-file", "/path/to/snowflake_connections.toml",
      "--connection-name", "production"
      // Optionally: "--allow_write"
      // Optionally: "--log_dir", "/absolute/path/to/logs"
      // Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
      // Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
    ]
  },
  "snowflake_staging": {
    "command": "uvx",
    "args": [
      "--python=3.12",
      "mcp_snowflake_server",
      "--connections-file", "/path/to/snowflake_connections.toml",
      "--connection-name", "staging"
    ]
  }
}

Installing Locally

Install Claude AI Desktop App
Install uv:

bash

curl -LsSf https://astral.sh/uv/install.sh | sh

Create a .env file with your Snowflake credentials:

bash

SNOWFLAKE_USER="xxx@your_email.com"
SNOWFLAKE_ACCOUNT="xxx"
SNOWFLAKE_ROLE="xxx"
SNOWFLAKE_DATABASE="xxx"
SNOWFLAKE_SCHEMA="xxx"
SNOWFLAKE_WAREHOUSE="xxx"
SNOWFLAKE_PASSWORD="xxx"
SNOWFLAKE_PASSWORD="xxx"
SNOWFLAKE_PRIVATE_KEY_PATH=/absolute/path/key.p8
# Alternatively, use external browser authentication:
# SNOWFLAKE_AUTHENTICATOR="externalbrowser"

[Optional] Modify runtime_config.json to set exclusion patterns for databases, schemas, or tables.
Test locally:

bash

uv --directory /absolute/path/to/mcp_snowflake_server run mcp_snowflake_server

Add the server to your claude_desktop_config.json:

Traditional Configuration (Using Environment Variables)

json

"mcpServers": {
  "snowflake_local": {
    "command": "/absolute/path/to/uv",
    "args": [
      "--python=3.12",  // Optional
      "--directory", "/absolute/path/to/mcp_snowflake_server",
      "run", "mcp_snowflake_server"
      // Optionally: "--allow_write"
      // Optionally: "--log_dir", "/absolute/path/to/logs"
      // Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
      // Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
    ]
  }
}

TOML Configuration (Recommended)

json

"mcpServers": {
  "snowflake_local": {
    "command": "/absolute/path/to/uv",
    "args": [
      "--python=3.12",
      "--directory", "/absolute/path/to/mcp_snowflake_server",
      "run", "mcp_snowflake_server",
      "--connections-file", "/absolute/path/to/snowflake_connections.toml",
      "--connection-name", "development"
      // Optionally: "--allow_write"
      // Optionally: "--log_dir", "/absolute/path/to/logs"
      // Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
      // Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
    ]
  }
}

Notes

By default, write operations are disabled. Enable them explicitly with --allow-write.
The server supports filtering out specific databases, schemas, or tables via exclusion patterns.
The server exposes additional per-table context resources if prefetching is enabled.
The append_insight tool updates the memo://insights resource dynamically.

License

MIT

Star History

Repository Owner

isaacwasserman

User

Repository Details

Language Python

Default Branch main

Size 85 KB

Contributors 10

License GNU General Public License v3.0

MCP Verified Nov 12, 2025

Programming Languages

Python

97.32%

Dockerfile

2.68%

Related MCPs

Discover similar Model Context Protocol servers

Snowflake Cortex AI Model Context Protocol (MCP) Server

Tooling and orchestration for Snowflake Cortex AI via Model Context Protocol.

Provides an MCP server that brings Snowflake Cortex AI, object management, and SQL orchestration to the MCP ecosystem. Enables Cortex Search, Analyst, and Agent services for structured and unstructured data querying, along with automated SQL execution and object management. Designed for integration with MCP clients to streamline AI-powered data workflows and context-sensitive operations within Snowflake environments.

⭐ 176
MCP
Snowflake-Labs/mcp

simple_snowflake_mcp

Production-ready MCP server for seamless Snowflake data integration.

Simple Snowflake MCP server provides advanced integration with Snowflake databases, facilitating database operations, metadata discovery, and resource monitoring with full compliance to the Model Context Protocol (MCP). It features a comprehensive YAML-based configuration system, robust logging options, and support for resource subscriptions and error handling. Designed for use in production environments, the server offers customizable access controls and is optimized for deployment behind corporate proxies.

⭐ 7
MCP
YannBrrd/simple_snowflake_mcp

Multi-Database MCP Server (by Legion AI)

Unified multi-database access and AI interaction server with MCP integration.

Multi-Database MCP Server enables seamless access and querying of diverse databases via a unified API, with native support for the Model Context Protocol (MCP). It supports popular databases such as PostgreSQL, MySQL, SQL Server, and more, and is built for integration with AI assistants and agents. Leveraging the MCP Python SDK, it exposes databases as resources, tools, and prompts for intelligent, context-aware interactions, while delivering zero-configuration schema discovery and secure credential management.

⭐ 76
MCP
TheRaLabs/legion-mcp

SkySQL MCP Server

Serverless MariaDB database management with AI-powered agents via Model Context Protocol.

SkySQL MCP Server implements the Model Context Protocol to provide a robust interface for launching and managing serverless MariaDB and MySQL database instances. It offers capabilities to interact with AI-powered agents for intelligent database operations, execute SQL queries, and manage credentials and security settings. Integration with tools like MCP CLI, Smithery.ai, and Cursor.sh is supported for interactive usage. Designed for efficiency and scalability, it enables streamlined database workflows with advanced AI assistance.

⭐ 2
MCP
skysqlinc/skysql-mcp

MCP AI SOC Sher

AI-driven SOC Text2SQL framework with security threat analysis

MCP AI SOC Sher is an advanced AI-powered platform that converts natural language prompts into optimized SQL queries using a Model Context Protocol-based server setup. It supports Text2SQL translation, real-time query processing, and security threat analysis across multiple database types. The tool offers multiple interfaces including STDIO, SSE, and REST API for flexible integration, and features in-depth SOC (Security Operations Center) monitoring capabilities. Built-in security features include SQL injection detection, sensitive table monitoring, and configurable security levels.

⭐ 5
MCP
akramIOT/MCP_AI_SOC_Sher

Supabase MCP Server

Connect Supabase projects to AI assistants using the Model Context Protocol.

Supabase MCP Server enables direct, secure integration between Supabase projects and AI assistants such as Cursor, Claude, and Windsurf. Leveraging the Model Context Protocol, it provides standardized endpoints for external LLMs to perform tasks like managing tables, fetching configurations, and querying data on Supabase. The server supports OAuth 2.1 Dynamic Client Registration and offers easy setup with feature groups and popular client installers for local, cloud, and self-hosted environments.

⭐ 2,263
MCP
supabase-community/supabase-mcp

View all Alternatives

Didn't find tool you were looking for?

Search AI Tools

Snowflake MCP Server

Key Features

Use Cases

README

Snowflake MCP Server

Overview

Components

Resources

Tools

Query Tools

Schema Tools

Analysis Tools

Usage with Claude Desktop

Installing via Smithery

Installing via UVX

Traditional Configuration (Individual Parameters)

TOML Configuration (Recommended)

Installing Locally

Traditional Configuration (Using Environment Variables)

TOML Configuration (Recommended)

Notes

License

Star History

Repository Owner

Repository Details

Programming Languages

Tags

Related MCPs