Snowflake MCP Server

A Visual Studio Code extension that provides a Model Context Protocol (MCP) server for Snowflake data warehouses. This extension enables AI assistants like Claude to interact with your Snowflake databases through natural language queries.

Features

🚀 Easy Server Management: Start, stop, and restart the MCP server with simple commands
🔐 Secure Configuration: Store Snowflake credentials securely in VS Code settings
📊 Real-time Logging: Monitor server activity through the dedicated output channel
🔄 Auto-start Option: Automatically start the server when VS Code launches
🧪 Connection Testing: Verify your Snowflake configuration before use
🛠️ Rich Tool Set: Access to multiple Snowflake operations including:
- Database and schema exploration
- Table and column discovery
- Query execution and analysis
- Performance monitoring
- Data quality checks
- And more!

Requirements

Before using this extension, ensure you have:

Python 3.8+ installed on your system

Required Python packages:

pip install mcp snowflake-connector-python python-dotenv pandas

Snowflake Account with appropriate credentials and permissions
Snowflake Account Identifier (e.g., xy12345.us-east-1)

Installation

From VS Code Marketplace

Open VS Code
Go to Extensions (Ctrl+Shift+X / Cmd+Shift+X)
Search for "Snowflake MCP Server"
Click Install

From VSIX File

Download the .vsix file
Open VS Code
Go to Extensions (Ctrl+Shift+X / Cmd+Shift+X)
Click the "..." menu > "Install from VSIX..."
Select the downloaded file

Configuration

After installation, configure your Snowflake connection:

Open VS Code Settings (File > Preferences > Settings)
Search for "Snowflake MCP"
Configure the following settings:

Required Settings

Account: Your Snowflake account identifier (e.g., xy12345.us-east-1)
Username: Your Snowflake username
Password: Your Snowflake password

Optional Settings

Database: Default database to use
Schema: Default schema to use
Warehouse: Snowflake warehouse to use for queries
Role: Snowflake role to assume
Python Path: Path to Python executable (default: python)
Auto Start: Automatically start server on VS Code startup (default: false)

Example Configuration (settings.json)

{
  "snowflakeMCP.account": "xy12345.us-east-1",
  "snowflakeMCP.username": "your_username",
  "snowflakeMCP.password": "your_password",
  "snowflakeMCP.database": "MY_DATABASE",
  "snowflakeMCP.schema": "PUBLIC",
  "snowflakeMCP.warehouse": "COMPUTE_WH",
  "snowflakeMCP.role": "ANALYST",
  "snowflakeMCP.autoStart": true
}

Security Note: For production use, consider storing sensitive credentials in environment variables rather than VS Code settings:

SNOWFLAKE_ACCOUNT
SNOWFLAKE_USER
SNOWFLAKE_PASSWORD
SNOWFLAKE_DATABASE
SNOWFLAKE_SCHEMA
SNOWFLAKE_WAREHOUSE
SNOWFLAKE_ROLE

Usage

Starting the Server

Open the Command Palette (Ctrl+Shift+P / Cmd+Shift+P) and run:

Snowflake MCP: Start Server

Or use the keyboard shortcut (if configured).

Available Commands

All commands are accessible via the Command Palette:

Command	Description
`Snowflake MCP: Start Server`	Start the MCP server
`Snowflake MCP: Stop Server`	Stop the running server
`Snowflake MCP: Restart Server`	Restart the server
`Snowflake MCP: Show Server Status`	Display current server status
`Snowflake MCP: Test Connection`	Verify Snowflake connection settings

Monitoring

The extension provides a dedicated output channel for monitoring:

View > Output (Ctrl+Shift+U / Cmd+Shift+U)
Select "Snowflake MCP Server" from the dropdown

This shows:

Server start/stop events
Connection status
Query execution logs
Error messages

Available MCP Tools

Once the server is running, the following tools are available through MCP-compatible AI assistants:

ListDatabases: List all accessible databases
ListSchemas: List schemas in a database
ListTables: List tables in a schema
DescribeTable: Get detailed table structure
SearchTables: Search for tables by name pattern
SearchColumns: Find columns across tables
InspectSchema: Get comprehensive schema information
GetTableSampleData: Retrieve sample rows from a table
GetColumnStats: Get statistical information about columns
AnalyzePerformance: Analyze query performance
CheckDataQuality: Perform data quality checks
GetWarehouseInfo: Get warehouse status and information
CreateStoredProcedure: Create Snowflake stored procedures
ProcessRequest: Execute custom SQL queries

Troubleshooting

Server Won't Start

Check Python Installation:
```
python --version
```
Should show Python 3.8 or higher

Verify Python Packages:

pip list | grep -E "mcp|snowflake|dotenv|pandas"

Check Output Channel: Look for error messages in "Snowflake MCP Server" output
Verify Python Path: Ensure snowflakeMCP.pythonPath is correctly set in settings

Connection Errors

Test Your Credentials: Use Snowflake MCP: Test Connection command
Verify Account Identifier: Ensure it includes the region (e.g., xy12345.us-east-1)
Check Firewall: Ensure your network allows connections to Snowflake
Verify Permissions: Ensure your Snowflake user has necessary permissions

Common Issues

"Module not found" errors: Install missing Python packages
"Permission denied": Check Snowflake user permissions
"Connection refused": Verify account identifier and network connectivity
"Process exited with code 1": Check output channel for specific error

Development

To contribute or modify this extension:

# Clone the repository
git clone https://github.com/yourusername/snowflake-mcp-server.git
cd snowflake-mcp-server

# Install dependencies
npm install

# Open in VS Code
code .

# Press F5 to run in debug mode

Release Notes

0.0.1

Initial release
Basic MCP server integration
Snowflake connection management
14 MCP tools for database operations
Server lifecycle commands
Configuration settings

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch
Make your changes
Submit a pull request

License

This extension is licensed under the MIT License. See LICENSE file for details.

Support

Issues: GitHub Issues
Documentation: GitHub Wiki

Acknowledgments

This extension uses:

Enjoy using Snowflake MCP Server! 🎉

Following extension guidelines

Ensure that you've read through the extensions guidelines and follow the best practices for creating your extension.

Extension Guidelines

Working with Markdown

You can author your README using Visual Studio Code. Here are some useful editor keyboard shortcuts:

Split the editor (Cmd+\ on macOS or Ctrl+\ on Windows and Linux).
Toggle preview (Shift+Cmd+V on macOS or Shift+Ctrl+V on Windows and Linux).
Press Ctrl+Space (Windows, Linux, macOS) to see a list of Markdown snippets.

For more information

Enjoy!

Snowflake MCP Server

Hithesh Patel

Snowflake MCP Server

Features

Requirements

Installation

From VS Code Marketplace

From VSIX File

Configuration

Required Settings

Optional Settings

Example Configuration (settings.json)

Usage

Starting the Server

Available Commands

Monitoring

Available MCP Tools

Troubleshooting

Server Won't Start

Connection Errors

Common Issues

Development

Release Notes

0.0.1

Contributing

License

Support

Acknowledgments

Following extension guidelines

Working with Markdown

For more information