Cover image
Try Now
2025-04-04

A Model Context Protocol (MCP) server that provides secure, read-only access to Snowflake databases. Allows LLMs to safely query tables and describe schemas without write permissions. Built with Python and the official Snowflake SDK.

3 years

Works with Finder

0

Github Watches

0

Github Forks

0

Github Stars

MCP Snowflake Reader

English | 한국어

smithery badge

English

A read-only MCP server for Snowflake databases. This server provides secure, read-only access to Snowflake databases through the MCP protocol.

Features

  • Read-only Access: Secure read-only access to Snowflake databases

Setup

Snowflake Connection

The Snowflake connection information should be provided as a JSON string in the following format:

{
  "account": "your-account",
  "user": "your-user",
  "password": "your-password",
  "warehouse": "your-warehouse",
  "database": "your-database",
  "schema": "your-schema",
  "role": "your-role"
}

MCP Client Configuration

Add the following configuration to your MCP client settings file (Cursor AI or Claude):

Docker
{
  "mcpServers": {
    "mcp-snowflake-reader": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "mcp-snowflake-reader",
        "--connection",
        "{\"account\":\"your-account\",\"user\":\"your-user\",\"password\":\"your-password\",\"warehouse\":\"your-warehouse\",\"database\":\"your-database\",\"schema\":\"your-schema\",\"role\":\"your-role\"}"
      ]
    }
  }
}
UVX
{
  "mcpServers": {
    "mcp-snowflake-reader": {
      "command": "uvx",
      "args": [
        "mcp-snowflake-reader",
        "--connection",
        "{\"account\":\"your-account\",\"user\":\"your-user\",\"password\":\"your-password\",\"warehouse\":\"your-warehouse\",\"database\":\"your-database\",\"schema\":\"your-schema\",\"role\":\"your-role\"}"
      ]
    }
  }
}

Installing via Smithery

To install Snowflake Reader for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @fnf-deepHeading/mcp-snowflake-reader --client claude

Limitations

  • Only read-only operations are allowed
  • Table names can only contain alphanumeric characters, underscores, and dots
  • The following SQL keywords are prohibited:
    • INSERT
    • UPDATE
    • DELETE
    • DROP
    • TRUNCATE
    • ALTER
    • CREATE
    • GRANT
    • REVOKE
    • COMMIT
    • ROLLBACK

License

This project is licensed under the MIT License - see the LICENSE file for details.

Korean

Snowflake 데이터베이스의 테이블을 읽어오는 MCP(Microservice Control Protocol) 서버입니다.

주요 기능

  • 읽기 전용 접근: Snowflake 데이터베이스에 대한 안전한 읽기 전용 접근

설정

Snowflake 연결 정보

Snowflake 연결 정보는 다음과 같은 형식으로 JSON 문자열로 제공됩니다:

{
  "account": "your-account",
  "user": "your-user",
  "password": "your-password",
  "warehouse": "your-warehouse",
  "database": "your-database",
  "schema": "your-schema",
  "role": "your-role"
}

MCP 클라이언트 설정

Cursor AI나 Claude와 같은 MCP 클라이언트의 설정 파일에 다음 설정을 추가하세요:

Docker
{
  "mcpServers": {
    "mcp-snowflake-reader": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "mcp-snowflake-reader",
        "--connection",
        "{\"account\":\"your-account\",\"user\":\"your-user\",\"password\":\"your-password\",\"warehouse\":\"your-warehouse\",\"database\":\"your-database\",\"schema\":\"your-schema\",\"role\":\"your-role\"}"
      ]
    }
  }
}
UVX
{
  "mcpServers": {
    "mcp-snowflake-reader": {
      "command": "uvx",
      "args": [
        "mcp-snowflake-reader",
        "--connection",
        "{\"account\":\"your-account\",\"user\":\"your-user\",\"password\":\"your-password\",\"warehouse\":\"your-warehouse\",\"database\":\"your-database\",\"schema\":\"your-schema\",\"role\":\"your-role\"}"
      ]
    }
  }
}

Smithery 사용하여 설치

Smithery를 통해 Claude Desktop에서 Snowflake Reader를 자동으로 설치하려면:

npx -y @smithery/cli install @fnf-deepHeading/mcp-snowflake-reader --client claude

제한사항

  • 읽기 전용 작업만 허용됩니다
  • 테이블 이름은 영숫자, 언더스코어, 점만 허용됩니다
  • 다음 SQL 키워드는 금지됩니다:
    • INSERT
    • UPDATE
    • DELETE
    • DROP
    • TRUNCATE
    • ALTER
    • CREATE
    • GRANT
    • REVOKE
    • COMMIT
    • ROLLBACK

라이선스

이 프로젝트는 MIT 라이선스를 따릅니다. 자세한 내용은 LICENSE 파일을 참조하세요.

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Yasir Eryilmaz
  • AI scriptwriting assistant for short, engaging video content.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • https://zenepic.net
  • Embark on a thrilling diplomatic quest across a galaxy on the brink of war. Navigate complex politics and alien cultures to forge peace and avert catastrophe in this immersive interstellar adventure.

  • Daren White
  • A supportive coach for mastering all Spanish tenses.

  • https://reddgr.com
  • Delivers concise Python code and interprets non-English comments

  • ariofarmani
  • Test repository for GitHub MCP server functionality

  • 1Panel-dev
  • 💬 MaxKB is an open-source AI assistant for enterprise. It seamlessly integrates RAG pipelines, supports robust workflows, and provides MCP tool-use capabilities.

  • ShrimpingIt
  • Micropython I2C-based manipulation of the MCP series GPIO expander, derived from Adafruit_MCP230xx

  • GLips
  • MCP server to provide Figma layout information to AI coding agents like Cursor

  • Mintplex-Labs
  • The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

    Reviews

    4 (1)
    Avatar
    user_OQugg9UM
    2025-04-18

    The mcp-snowflake-reader by fnf-deepHeading is a fantastic tool for integrating Snowflake data with ease. Its intuitive interface and powerful features make data extraction and management seamless. The seamless integration with Snowflake allows for quick and efficient data processing. Truly a must-have for anyone working with Snowflake! Highly recommended.