MCP Server for Snowflake

Created By
dynamikea year ago
MCP Server for connecting to Snowflake with read-only questions
Overview

What is MCP Server for Snowflake?

MCP Server for Snowflake is a Model Context Protocol (MCP) server designed for performing read-only operations against Snowflake databases, allowing secure querying of data without modifying any information.

How to use MCP Server for Snowflake?

To use the MCP Server, clone the repository, install the package, and configure your Snowflake credentials in a .env file. You can then run the server and connect it to Claude Desktop or any compatible MCP client.

Key features of MCP Server for Snowflake?

  • Flexible authentication methods (service account with private key or external browser)
  • Connection pooling with automatic refresh
  • Support for multiple SQL statement types (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH)
  • Read-only operations with security checks
  • Integration with Claude Desktop for easy querying

Use cases of MCP Server for Snowflake?

  1. Listing all databases and views in a Snowflake account.
  2. Describing the structure of specific views.
  3. Executing custom read-only SQL queries.
  4. Comparing data from different views across databases.

FAQ from MCP Server for Snowflake?

  • Can I modify data using this server?

No, the server enforces read-only operations to ensure data integrity.

  • What authentication methods are supported?

The server supports both private key authentication and external browser authentication.

  • Is there a limit on the number of queries I can run?

There is no explicit limit, but the server automatically adds LIMIT clauses to prevent large result sets.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
dynamike
Star
4
Language
Python
License
MIT license

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
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)

a day ago