Snowflake Database
🐍 ☁️ - Snowflake integration implementing read and (optional) write operations as well as insight tracking
What is Snowflake Database?
Snowflake Database is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐍 ☁️ - snowflake integration implementing read and (optional) write operations as well as insight tracking
🐍 ☁️ - Snowflake integration implementing read and (optional) write operations as well as insight tracking
This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🐍 ☁️ - Snowflake integration implementing read and (optional
Use Cases
Maintainer
Works with
Installation
NPM
npx -y mcp_snowflake_serverManual Installation
npx -y mcp_snowflake_serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Snowflake Database
mcp-snowflake-server is a Python MCP server that gives AI clients direct read and optional write access to a Snowflake data warehouse, along with schema discovery tools and a persistent insight memo resource. It exposes tools for executing SELECT queries, listing databases, schemas, and tables, describing table columns, and optionally running INSERT/UPDATE/DELETE statements and creating tables. Data analysts, data engineers, and AI developers use it to query Snowflake warehouses in natural language through Claude without writing SQL by hand, while the memo resource accumulates discovered insights across a session.
Prerequisites
- Python 3.12 or lower recommended (Snowflake connector has known issues with Python 3.13+)
- uv or uvx package runner installed (curl -LsSf https://astral.sh/uv/install.sh | sh)
- A Snowflake account with a warehouse, database, schema, role, and user configured
- Snowflake user credentials: account identifier, username, password or private key path
- An MCP-compatible client such as Claude Desktop
Gather your Snowflake connection details
You will need your Snowflake account identifier (format: orgname-accountname or legacy accountname.region), username, password (or path to a private key .p8 file), role, warehouse, database, and schema.
Install mcp_snowflake_server via uvx
The recommended installation is via uvx, which isolates the package and its dependencies automatically. Specify Python 3.12 to avoid compatibility issues.
uvx --python=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(Alternative) Use a TOML connections file
For multiple environments, store credentials in a Snowflake connections TOML file and reference named connections. This avoids putting credentials directly in the MCP config.
# snowflake_connections.toml
[connections.production]
user = "your_user"
password = "your_password"
account = "your_account"
warehouse = "your_warehouse"
role = "your_role"
database = "your_database"
schema = "your_schema"Add the server to your MCP client configuration
Edit claude_desktop_config.json to register mcp_snowflake_server, passing your Snowflake credentials as arguments. Add --allow_write only if you need INSERT/UPDATE/DELETE/CREATE TABLE support.
Restart Claude Desktop and verify
Restart Claude Desktop and ask Claude to list the databases in your Snowflake instance. A successful response confirms the connection is working.
Snowflake Database Examples
Client configuration
Register mcp_snowflake_server in Claude Desktop using uvx with individual credential parameters. Add --allow_write to enable write operations.
{
"mcpServers": {
"snowflake": {
"command": "uvx",
"args": [
"--python=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"
]
}
}
}Prompts to try
Example prompts for querying and exploring your Snowflake data warehouse through Claude.
- "List all databases in my Snowflake account"
- "Show me all tables in the ANALYTICS schema of the PRODUCTION database"
- "Describe the columns in PRODUCTION.ANALYTICS.ORDERS"
- "Query the top 10 customers by total order value in the last 30 days"
- "Find any tables that contain a column named 'user_id' across all schemas"
- "Add the insight that the ORDERS table has a significant spike in NULLs for the shipped_at column after 2024-06-01"Troubleshooting Snowflake Database
Authentication error: Incorrect username or password
Double-check the --account value. Snowflake account identifiers are case-insensitive but format matters: use orgname-accountname for newer accounts or legacy accountname.region.cloud format. Verify by logging into app.snowflake.com and checking the account URL.
Module not found or import errors on Python 3.13+
The Snowflake Python connector has compatibility issues with Python 3.13. Explicitly pin Python 3.12 by passing --python=3.12 to uvx: `uvx --python=3.12 mcp_snowflake_server ...`.
write_query or create_table tool is not available
Write tools are disabled by default to prevent accidental data modification. Add --allow_write to the args array in your MCP client configuration and restart the client.
Frequently Asked Questions about Snowflake Database
What is Snowflake Database?
Snowflake Database is a Model Context Protocol (MCP) server that 🐍 ☁️ - snowflake integration implementing read and (optional) write operations as well as insight tracking It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Snowflake Database?
Install via npm with the command: npx -y mcp_snowflake_server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Snowflake Database?
Snowflake Database works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Snowflake Database free to use?
Yes, Snowflake Database is open source and available under the GPL 3.0 license. You can use it freely in both personal and commercial projects.
Snowflake Database Alternatives — Similar Databases Servers
Looking for alternatives to Snowflake Database? Here are other popular databases servers you can use with Claude, Cursor, and VS Code.
Excelize
★ 20.6kGo language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets
MCP Toolbox for Databases
★ 15.3kOpen source MCP server specializing in easy, fast, and secure tools for Databases.
DBHub
★ 2.8kA universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.
Tabularis
★ 2.1kA lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
Postgres AI Guide
★ 1.7kMCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
Anyquery
★ 1.7k🏎️ 🏠 ☁️ - Query more than 40 apps with one binary using SQL. It can also connect to your PostgreSQL, MySQL, or SQLite compatible database. Local-first and private by design.
Browse More Databases MCP Servers
Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Snowflake Database in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Snowflake Database?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.