MCP.so
Sign In

Snowflake MCP Service

@davidamom

About Snowflake MCP Service

MCP server implementation for Snowflake integration

Basic information

Category

Databases

License

MIT

Runtime

python

Transports

stdio

Publisher

davidamom

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "snowflake-mcp": {
      "command": "python",
      "args": [
        "server.py"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Snowflake MCP Service?

The Snowflake MCP Service is a Model Context Protocol (MCP) server that provides access to Snowflake databases for any MCP-compatible client. It allows AI applications and tools to execute SQL queries on Snowflake, automatically manage database connections (connect, reconnect on timeout, close), and handle query results and errors safely, using either password or key pair authentication.

How to use Snowflake MCP Service?

Clone the repository, install dependencies with pip install -r requirements.txt, and create a .env file with your Snowflake credentials and authentication method. Then configure your MCP client (e.g., Claude Desktop) with the path to the Python interpreter and the server script, or use the provided Docker setup. The server starts automatically when invoked by the client; for testing you can run python server.py manually.

Key features of Snowflake MCP Service

  • Secure Snowflake database access
  • Automatic connection lifecycle management
  • Password and key pair authentication
  • SQL query execution and result processing
  • Export queries to CSV files
  • Compatible with any MCP-compliant client

Use cases of Snowflake MCP Service

  • Query Snowflake databases directly from an AI assistant like Claude
  • Export SQL query results to CSV files for further analysis
  • Enable natural language data exploration via MCP clients
  • Automate database reporting through conversational interfaces

FAQ from

Comments

More Databases MCP servers