Snowflake MCP 服务器 | PlugMCP
跳到正文 MCP Server for Snowflake
A Model Context Protocol (MCP) server for performing read-only operations against Snowflake databases. This tool enables Claude to securely query Snowflake data without modifying any information.
Features
Flexible authentication to Snowflake using either:
Service account authentication with private key
MCP Server for connecting to Snowflake with read-only questions
把任意工具接入任意智能体。面向非开发者的 MCP 服务器目录;网关承载流量,n8n 承载应用。
产品
目录
开发者
公司
External browser authentication for interactive sessions
Connection pooling with automatic background refresh to maintain persistent connections
Support for querying multiple views and databases in a single session
Support for multiple SQL statement types (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH)
MCP-compatible handlers for querying Snowflake data
Read-only operations with security checks to prevent data modification
Support for Python 3.12+
Stdio-based MCP server for easy integration with Claude Desktop
Available Tools The server provides the following tools for querying Snowflake:
list_databases : List all accessible Snowflake databases
list_views : List all views in a specified database and schema
describe_view : Get detailed information about a specific view including columns and SQL definition
query_view : Query data from a view with an optional row limit
execute_query : Execute custom read-only SQL queries (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH) with results formatted as markdown tables
Installation
Prerequisites
Python 3.12 or higher
A Snowflake account with either:
A configured service account (username + private key), or
A regular user account for browser-based authentication
uv package manager (recommended)
Steps
Clone this repository:
git clone https://github.com/yourusername/snowflake-mcp-server.git
cd snowflake-mcp-server
Install the package:
uv pip install -e .
Create a .env file with your Snowflake credentials:
Choose one of the provided example files based on your preferred authentication method:
For private key authentication :
cp .env.private_key.example .env
Then edit the .env file to set your Snowflake account details and path to your private key.
For external browser authentication :
cp .env.browser.example .env
Then edit the .env file to set your Snowflake account details.
Usage
Running with uv After installing the package, you can run the server directly with:
uv run snowflake-mcp
# Or you can be explicit about using stdio transport
uv run snowflake-mcp-stdio
This will start the stdio-based MCP server, which can be connected to Claude Desktop or any MCP client that supports stdio communication.
When using external browser authentication, a browser window will automatically open prompting you to log in to your Snowflake account.
Claude Desktop Integration
In Claude Desktop, go to Settings → MCP Servers
Add a new server with the full path to your uv executable:
"snowflake-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/<path-to-code>/snowflake-mcp-server",
"run",
"snowflake-mcp"
]
}
Or explicitly specify the stdio transport:
"snowflake-mcp-server": {
"command": "uv",
"args": [
"--directory",
"/<path-to-code>/snowflake-mcp-server",
"run",
"snowflake-mcp-stdio"
]
}
You can find your uv path by running which uv in your terminal
Save the server configuration
Example Queries When using with Claude, you can ask questions like:
"Can you list all the databases in my Snowflake account?"
"List all views in the MARKETING database"
"Describe the structure of the CUSTOMER_ANALYTICS view in the SALES database"
"Show me sample data from the REVENUE_BY_REGION view in the FINANCE database"
"Run this SQL query: SELECT customer_id, SUM(order_total) as total_spend FROM SALES.ORDERS GROUP BY customer_id ORDER BY total_spend DESC LIMIT 10"
"Query the MARKETING database to find the top 5 performing campaigns by conversion rate"
"Compare data from views in different databases by querying SALES.CUSTOMER_METRICS and MARKETING.CAMPAIGN_RESULTS"
Configuration Connection pooling behavior can be configured through environment variables:
SNOWFLAKE_CONN_REFRESH_HOURS: Time interval in hours between connection refreshes (default: 8)
Example .env configuration:
# Set connection to refresh every 4 hours
SNOWFLAKE_CONN_REFRESH_HOURS=4
Authentication Methods
Private Key Authentication This method uses a service account and private key for non-interactive authentication, ideal for automated processes.
Create a key pair for your Snowflake user following Snowflake documentation
Set SNOWFLAKE_AUTH_TYPE=private_key in your .env file
Provide the path to your private key in SNOWFLAKE_PRIVATE_KEY_PATH
External Browser Authentication This method opens a browser window for interactive authentication.
Set SNOWFLAKE_AUTH_TYPE=external_browser in your .env file
When you start the server, a browser window will open asking you to log in
After authentication, the session will remain active for the duration specified by your Snowflake account settings
Security Considerations
Enforces read-only operations (only SELECT, SHOW, DESCRIBE, EXPLAIN, and WITH statements are allowed)
Automatically adds LIMIT clauses to prevent large result sets
Uses secure authentication methods for connections to Snowflake
Validates inputs to prevent SQL injection
⚠️ Important : Keep your .env file secure and never commit it to version control. The .gitignore file is configured to exclude it.
Development
Static Type Checking mypy mcp_server_snowflake/
Linting
Formatting
Running Tests
Contributing Contributions are welcome! Please feel free to submit a Pull Request.
Technical Details Graphify Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, e Private Gpt Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server. Scientific Agent Skills Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biolog Open Code Review Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, Codebase Memory Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection. Orm The Prisma ORM: write your application in TypeScript with human-readable queries instead of SQL. Host your database on Prisma Postgres and your app on Prisma Compute. OpenViking Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. Context Mode Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OMP, OpenCode, Gemin Dbx 25 MB lightweight cross-platform database client for 100+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Dock Xerj AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory a Wasp The batteries-included full-stack framework for the AI era. Develop JS/TS web apps (React, Node.js, and Prisma) using declarative code that abstracts away complex full-stack features like auth, backgr WrenAI GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data s Databases MCP 服务器 最佳 Databases MCP 服务器
暂无工具列表。远程服务器在首次健康检查后会获得工具列表。
如何安装 Snowflake? 在本页复制适用于 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 配置。它使用发布者的安装方式,而不是 PlugMCP 代理。
Snowflake 需要 API 密钥吗? 此记录未列出必需的环境变量。
Snowflake 使用哪种传输方式? Snowflake 通过 stdio 在本地运行。
Snowflake 上次检查是什么时候? 上次检查时间:2026-10-28。 MCP Server for connecting to Snowflake with read-only questions
工具
0 / 10