Snowflake IntegrationSAFE
MCP server implementation for Snowflake integration
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol (MCP) server that provides Claude access to Snowflake databases. / 一个为 Claude 提供 Snowflake 数据库访问能力的 MCP (模型上下文协议) 服务器。
[](https://smithery.ai/server/@datawiz168/mcp-service-snowflake)
This server implements the Model Context Protocol to allow Claude to:
- Execute SQL queries on Snowflake databases
- Automatically handle database connection lifecycle (connect, reconnect on timeout, close)
- Handle query results and errors
- Perform database operations safely
此服务器实现了模型上下文协议,使 Claude 能够:
- 在 Snowflake 数据库上执行 SQL 查询
- 自动管理数据库连接生命周期(连接创建、超时重连、连接关闭)
- 处理查询结果和错误
- 安全地执行数据库操作
Installation / 安装
Installing via Smithery
To install mcp-service-snowflake for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @datawiz168/mcp-service-snowflake --client claude
Manual Installation
- Clone this repository / 克隆此仓库
git clone https://github.com/datawiz168/mcp-snowflake-service.git
- Install dependencies / 安装依赖
pip install -r requirements.txt
Configuration / 配置说明
MCP Client Configuration Example / MCP 客户端配置示例
Add the following configuration to claude_desktop_config.json / 在 claude_desktop_config.json 中添加配置:
{
"mcpServers": {
"snowflake": {
"command": "C:\\Users\\K\\anaconda3\\envs\\regular310\\python.exe",
"args": ["D:\\tools\\mcp-snowflake\\server.py"]
}
}
}Configuration parameters / 配置参数说明:
command: Full path to your Python interpreter. Please modify this according to your Python installation location. / Python 解释器的完整路径,请根据您的 Python 安装位置进行修改。args: Full path to the server script. Please modify this according to where you cloned the repository. / 服务器脚本的完整路径,请根据您克隆仓库的位置进行修改。
Example paths
78871327a196OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server-snowflake --env SNOWFLAKE_PASSWORD=${SNOWFLAKE_PASSWORD} -- uvx mcp-server-snowflake{
"mcpServers": {
"mcp-server-snowflake": {
"command": "uvx",
"args": [
"mcp-server-snowflake"
],
"env": {
"SNOWFLAKE_PASSWORD": "${SNOWFLAKE_PASSWORD}"
}
}
}
}Exposed tools (1)
0 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
execute_query | write | Execute a SQL query on Snowflake |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
logger.info(f"Initialized with config (excluding password): {json.dumps({k:v for k,v in self.config.items() if k != 'password'})}").env.template
snowflake-connector-python, python-dotenv, mcp
Gates applied: no_behavioural_pass.
78871327a196full audit observations/trust-audit/mcp-server/datawiz168__snowflake-integration-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 78871327a196 | SAFE | B | 89 | first audit |
Questions
What is the Snowflake Integration MCP server?
MCP server implementation for Snowflake integration
What tools does Snowflake Integration expose?
1 in total: 0 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Snowflake Integration safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Snowflake Integration need?
It reads SNOWFLAKE_PASSWORD from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Snowflake Integration run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as mcp-server-snowflake.
How current is this page?
The grade is for one exact copy of the source (78871327a196), read on 2026-10-08. The repository is watched and re-audited when it changes.