snowflake-mcp-server-by-cdata

Created By
CDataSoftwarea year ago
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
Overview

What is Snowflake MCP Server by CData?

The Snowflake MCP Server by CData is a read-only Model Context Protocol (MCP) server that allows users to connect to Snowflake data from Claude Desktop using CData JDBC Drivers. It enables LLMs to query live data without needing to write SQL queries.

How to use Snowflake MCP Server?

To use the Snowflake MCP Server, clone the repository, build the server, install the CData JDBC Driver for Snowflake, configure your connection, and create a configuration file for Claude Desktop. Once set up, you can run the server and interact with it through natural language queries.

Key features of Snowflake MCP Server?

  • Read-only access to Snowflake data through a simple MCP interface.
  • No SQL required for querying data; users can ask natural language questions.
  • Supports various data sources and provides tools for data retrieval.

Use cases of Snowflake MCP Server?

  1. Querying live data from Snowflake using natural language.
  2. Integrating Snowflake data with AI applications like Claude Desktop.
  3. Simplifying data access for users without SQL knowledge.

FAQ from Snowflake MCP Server?

  • Can I write data to Snowflake using this server?

No, this server is read-only. For write capabilities, consider the full CData MCP Server for Snowflake.

  • Is there a cost to use the Snowflake MCP Server?

The server is currently in beta and is free to use.

  • What kind of queries can I run?

You can ask natural language questions about your data, such as retrieving specific information or summarizing data.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
CDataSoftware
Star
0
Language
Java
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

2 days ago