mcp-snowflake-server

Snowflake MCP Server

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

Tools

Query Tools

• read_query
  Execute SELECT queries to read data from the database.
• write_query
  Execute INSERT, UPDATE, or DELETE queries.
• create_table
  Create new tables in the database.

Schema Tools

• list_databases
  List all databases in the Snowflake instance.
• list_schemas
  List all schemas within a specific database.
• list_tables
  List all tables within a specific database and schema.
• describe_table
  View column information for a specific table.

Analysis Tools

• append_insight
  Add new data insights to the memo resource.

Usage with Claude Desktop

Installing via Smithery

To install Snowflake Server for Claude Desktop automatically via Smithery:

Installing via UVX

• Add to your configuration.

Installing Locally

1. Install Claude AI Desktop App.
2. Install uv.
3. Create a .env file with your Snowflake credentials.
4. Modify runtime_config.json if necessary.
5. Test locally.
6. Add to your configuration.

Notes

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