Advertise
MCP.so
Sign In

MCP Snowflake Service

@datawiz168

Repository

Basic information

Category

Databases

License

MIT

Transports

stdio

Author

datawiz168

About MCP Snowflake Service

MCP server implementation for Snowflake integration

MCP Snowflake Service config

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

{
  "mcpServers": {
    "mcp-snowflake-service": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@datawiz168/mcp-service-snowflake",
        "--client",
        "claude"
      ]
    }
  }
}

MCP Snowflake Service tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Mcp Snowflake Service?

Mcp Snowflake Service is a Model Context Protocol (MCP) server that provides Claude with secure access to Snowflake databases. It automatically manages the database connection lifecycle—connecting, reconnecting on timeout, and closing—and handles query execution, result processing, and error reporting.

How to use Mcp Snowflake Service?

Install via Smithery (npx -y @smithery/cli install @datawiz168/mcp-service-snowflake --client claude) or manually by cloning the repository and installing dependencies with pip install -r requirements.txt. Configure Snowflake credentials in a .env file and add the server to claude_desktop_config.json with the path to your Python interpreter and the server script. The server starts automatically with Claude Desktop; for development testing, run python server.py manually.

Key features of Mcp Snowflake Service

  • Execute SQL queries on Snowflake databases
  • Automatic connection lifecycle management (connect, reconnect, close)
  • Robust error handling and result processing
  • Secure database access via Snowflake user credentials
  • Supports both read-only and write operations based on database user permissions

Use cases of Mcp Snowflake Service

  • Query Snowflake data through Claude’s natural language interface
  • Automate database reporting and analysis tasks
  • Perform safe database operations with controlled permissions (e.g., assigning a read-only user for read queries)

Frequently asked questions

1

How do I install Mcp Snowflake Service?

You can install it automatically via Smithery or manually by cloning the repository, running `pip install -r requirements.txt`, and configuring the server in `claude_desktop_config.json`.

2

What configuration is required for Snowflake?

Create a `.env` file in the project root with `SNOWFLAKE_USER`, `SNOWFLAKE_PASSWORD`, `SNOWFLAKE_ACCOUNT`, `SNOWFLAKE_DATABASE`, and `SNOWFLAKE_WAREHOUSE`.

3

How does connection management work?

The server automatically initializes a connection on the first query, monitors connection state, handles timeouts, reconnects if lost, and properly closes connections when the server stops.

4

Can I restrict database access to read-only?

Yes. By assigning a Snowflake user with read‑only permissions, the server will only be able to execute read queries, ensuring precise access control.

5

What are the runtime dependencies?

Python is required. All dependencies are listed in `requirements.txt` and installed via `pip install -r requirements.txt`. The server communicates with Claude via the MCP protocol.

6

Is Mcp Snowflake Service open source? What license does it use?

Yes, it is licensed under the MIT License.

Comments

More Databases MCP servers

MongoDB MCP Server

mongodb-js

A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.

1.1K

Local YDB MCP

astandrik

Safety-first stdio MCP server with 38 tools for operating Docker-based local-ydb environments locally or over SSH.

4

MCP Alchemy

runekaagaard

A MCP (model context protocol) server that gives the LLM access to and knowledge about relational databases like SQLite, Postgresql, MySQL & MariaDB, Oracle, and MS-SQL.

412

Sail MCP Server for Spark SQL

lakehq

Drop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.

3.1K

Database Gateway

centralmind

Universal MCP-Server for your Databases optimized for LLMs and AI-Agents.

531
Advertise