# Snowflake

> Use this tool when you need to integrate AI assistants with Snowflake data warehouses to execute SELECT queries, explore database schemas, and retrieve table metadata. It solves problems related to data exploration, report generation, and schema discovery, accepting SQL queries as input and providing query results, schema information, and metadata as output. It is ideal for data analysts and business users who require AI-assisted data analysis within their Snowflake environments.

Canonical page: https://skillsregistry.net/skills/patrickfreyer-snowflake  
JSON: https://api.skillsregistry.net/v1/skills/patrickfreyer-snowflake

## Description

This Snowflake MCP server by Patrick Freyer provides direct integration with Snowflake data warehouses, enabling AI assistants to execute SELECT queries, explore database schemas, and retrieve table metadata through the Snowflake SDK. Built with TypeScript and featuring comprehensive authentication support through environment variables or MCP configuration, it offers five core tools including read-only query execution with SQL injection protection, database/schema/table listing, and detailed table schema inspection. The implementation includes robust error handling, connection management with automatic reconnection, and flexible configuration options supporting warehouse, database, schema, and role specifications, making it valuable for data analysts and business users who need AI-assisted data exploration, report generation, and schema discovery within their Snowflake environments.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/patrickfreyer-snowflake)
- **Repository:** <https://github.com/patrickfreyer/mcp-server-snowflake>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "patrickfreyer-snowflake"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/patrickfreyer-snowflake` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/patrickfreyer-snowflake/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt