Snowflake MCP Server By Cdata

@CDataSoftware

Basic information

About Snowflake MCP Server By Cdata

This read-only MCP Server allows you to connect to Snowflake data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at

#snowflake #mcp-server #cdata

Snowflake MCP Server By Cdata config

No standard config provided

This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.

Repository

Snowflake MCP Server By Cdata 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.

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-server-by-cdata?

snowflake-mcp-server-by-cdata is a read-only MCP (Model Context Protocol) server that allows LLMs like Claude Desktop to query live data in Snowflake using natural language. It wraps the CData JDBC Driver for Snowflake and exposes Snowflake tables as relational SQL models through a simple MCP interface.

How to use snowflake-mcp-server-by-cdata?

Clone the repository, build it with mvn clean install, then download and license the CData JDBC Driver for Snowflake. Create a .prp file with your JDBC connection string, driver path, and settings. Configure Claude Desktop by adding the server to its claude_desktop_config.json with the path to Java and the JAR and .prp file. The server uses stdio transport and must run on the same machine as the client.

Key features of snowflake-mcp-server-by-cdata

Read‑only querying of Snowflake data via natural language.
Built on the CData JDBC Driver for Snowflake.
Exposes Snowflake tables as relational SQL models.
Provides tools: get_tables, get_columns, and run_query (SQL SELECT).
Works with Claude Desktop and other MCP clients using stdio.
MIT licensed and open source.

Use cases of snowflake-mcp-server-by-cdata

Ask an LLM to analyze Snowflake data without writing SQL.
Let Claude Desktop answer questions about live Snowflake tables.
Quickly explore Snowflake schemas and run SELECT queries from a chatbot.
Integrate Snowflake data into AI workflows for reporting or analytics.

Frequently asked questions

What does snowflake-mcp-server-by-cdata do?

It lets LLMs like Claude Desktop query live Snowflake data by asking natural-language questions, without needing to write SQL. It is a read‑only server based on the CData JDBC Driver for Snowflake.

What dependencies are required?

You need Java, Maven to build, and the CData JDBC Driver for Snowflake (requires installation and licensing). The server runs on any OS with Java.

Is snowflake-mcp-server-by-cdata read‑only?

Yes, this MCP server is read‑only. For full CRUD and action capabilities, CData offers a separate beta MCP Server for Snowflake with a simplified setup.

What transport does it use?

The server uses `stdio` transport, so it must run on the same machine as the MCP client (e.g., Claude Desktop).

Where is the data stored?

Data remains in Snowflake; the server only queries live data. No local persistence is used.

Comments

More Databases MCP servers

Neon MCP Server

neondatabase-labs

MCP server for interacting with Neon Management API and databases

617

golfdata.online - Verified Golf Clubs

golfdata.online

Verified golf club data for AI agents: holes, par, address, phone, booking links, facilities, visitor rules and green fees for golf clubs in Spain (Canary Islands and mainland), expanding across Europe. Every fact comes

mcp-server-qdrant: A Qdrant MCP server

qdrant

An official Qdrant Model Context Protocol (MCP) server implementation

637

Redis MCP Server

redis

The official Redis MCP Server is a natural language interface designed for agentic applications to manage and search data in Redis efficiently

539

Fund Momentum MCP Server

schneidavie

Fund Momentum MCP Server — VC intelligence for AI assistants. 1000+ active VC funds, live investor signals, AI-powered startup matching.