Snowflake

What is mcp-snowflake-server?

mcp-snowflake-server is an MCP (Model Context Protocol) server implementation designed to facilitate interaction between Language Models (LLMs) and Snowflake databases. It allows LLMs to perform secure and controlled data operations by exposing Snowflake functionalities through a set of tools and resources.

How to use mcp-snowflake-server?

mcp-snowflake-server can be installed and used with Claude Desktop via Smithery or UVX, or by installing it locally. Installation typically involves configuring Snowflake credentials and adding the server to your Claude Desktop configuration. The server exposes various tools that can be called by LLMs to interact with the Snowflake database.

Key Features of mcp-snowflake-server

• Database Interaction: Enables LLMs to execute SQL queries (SELECT, INSERT, UPDATE, DELETE, CREATE TABLE) on Snowflake databases.
• Schema Exploration: Provides tools to list databases, schemas, tables, and describe table structures (columns, types, comments).
• Data Insights: Features a memo://insights resource that aggregates discovered data insights, updated automatically via an append_insight tool.
• Contextual Resources: Exposes per-table schema summaries as individual resources (context://table/{table_name}) when prefetch is enabled.
• Security: Write operations are disabled by default and require explicit --allow-write flag for activation.
• Configurability: Supports exclusion patterns for databases, schemas, or tables to control access.

Use Cases of mcp-snowflake-server

• Automated Data Retrieval: LLMs can retrieve specific data from Snowflake tables by executing SELECT queries.
• Data Analysis and Reporting: LLMs can leverage the append_insight tool to record and aggregate data insights, aiding in automated analysis and report generation.
• Database Management: With write operations enabled, LLMs can perform basic database management tasks like creating tables or modifying data.
• Schema Discovery: LLMs can dynamically explore the Snowflake database schema to understand data structures and relationships.

FAQ about mcp-snowflake-server

• Are write operations enabled by default? No, write operations are disabled by default for security reasons. They can be enabled explicitly with the --allow-write flag.
• Can I exclude certain databases or tables from being accessed? Yes, the server supports filtering out specific databases, schemas, or tables via exclusion patterns.
• What is the memo://insights resource? It is a continuously updated memo that aggregates discovered data insights. It gets updated automatically when new insights are appended via the append_insight tool.
• How can I install mcp-snowflake-server? You can install it via Smithery, UVX, or by following the local installation instructions provided in the documentation, which involves setting up a .env file with Snowflake credentials and configuring your Claude Desktop application.

Snowflake MCP Server

---

Overview

A Model Context Protocol (MCP) server implementation that provides database interaction with Snowflake. This server enables running SQL queries via tools and exposes data insights and schema context as resources.

---

Components

Resources

• memo://insights
  A continuously updated memo aggregating discovered data insights.
  Updated automatically when new insights are appended via the append_insight tool.

• context://table/{table_name}
  (If prefetch enabled) Per-table schema summaries, including columns and comments, exposed as individual resources.

---

Tools

The server exposes the following tools:

Query Tools

• read_query
  Execute SELECT queries to read data from the database.
  Input:

  • query (string): The SELECT SQL query to execute
    Returns: Query results as array of objects

• write_query (enabled only with --allow-write)
  Execute INSERT, UPDATE, or DELETE queries.
  Input:

  • query (string): The SQL modification query
    Returns: Number of affected rows or confirmation

• create_table (enabled only with --allow-write)
  Create new tables in the database.
  Input:

  • query (string): CREATE TABLE SQL statement
    Returns: Confirmation of table creation

Schema Tools

• list_databases
  List all databases in the Snowflake instance.
  Returns: Array of database names

• list_schemas
  List all schemas within a specific database.
  Input:

  • database (string): Name of the database
    Returns: Array of schema names

• list_tables
  List all tables within a specific database and schema.
  Input:

  • database (string): Name of the database
  • schema (string): Name of the schema
    Returns: Array of table metadata

• describe_table
  View column information for a specific table.
  Input:

  • table_name (string): Fully qualified table name (database.schema.table)
    Returns: Array of column definitions with names, types, nullability, defaults, and comments

Analysis Tools

• append_insight
  Add new data insights to the memo resource.
  Input:
  • insight (string): Data insight discovered from analysis
    Returns: Confirmation of insight addition
    Effect: Triggers update of memo://insights resource

---

Usage with Claude Desktop

Installing via Smithery

To install Snowflake Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install mcp_snowflake_server --client claude

---

Installing via UVX

"mcpServers": {
  "snowflake_pip": {
    "command": "uvx",
    "args": [
      "--python=3.12",  // Optional: specify Python version <=3.12
      "mcp_snowflake_server",
      "--account", "your_account",
      "--warehouse", "your_warehouse",
      "--user", "your_user",
      "--password", "your_password",
      "--role", "your_role",
      "--database", "your_database",
      "--schema", "your_schema"
      // Optionally: "--allow_write"
      // Optionally: "--log_dir", "/absolute/path/to/logs"
      // Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
      // Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
    ]
  }
}

---

Installing Locally

1. Install Claude AI Desktop App

2. Install uv:

curl -LsSf https://astral.sh/uv/install.sh | sh

3. Create a .env file with your Snowflake credentials:

SNOWFLAKE_USER="xxx@your_email.com"
SNOWFLAKE_ACCOUNT="xxx"
SNOWFLAKE_ROLE="xxx"
SNOWFLAKE_DATABASE="xxx"
SNOWFLAKE_SCHEMA="xxx"
SNOWFLAKE_WAREHOUSE="xxx"
SNOWFLAKE_PASSWORD="xxx"
# Alternatively, use external browser authentication:
# SNOWFLAKE_AUTHENTICATOR="externalbrowser"

4. [Optional] Modify runtime_config.json to set exclusion patterns for databases, schemas, or tables.

5. Test locally:

uv --directory /absolute/path/to/mcp_snowflake_server run mcp_snowflake_server

6. Add the server to your claude_desktop_config.json:

"mcpServers": {
  "snowflake_local": {
    "command": "/absolute/path/to/uv",
    "args": [
      "--python=3.12",  // Optional
      "--directory", "/absolute/path/to/mcp_snowflake_server",
      "run", "mcp_snowflake_server"
      // Optionally: "--allow_write"
      // Optionally: "--log_dir", "/absolute/path/to/logs"
      // Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
      // Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
    ]
  }
}

---

Notes

• By default, write operations are disabled. Enable them explicitly with --allow-write.
• The server supports filtering out specific databases, schemas, or tables via exclusion patterns.
• The server exposes additional per-table context resources if prefetching is enabled.
• The append_insight tool updates the memo://insights resource dynamically.

---

License

MIT