Snowflake

Snowflake

v1.4.2
databasedata-warehousesqlcortex

Summary

Snowflake Labs' MCP server — query the warehouse, use Cortex search and analyst, and manage objects.

Features

  • Query Snowflake warehouses through Cortex services
  • Object management for databases, schemas, and tables
  • Configurable tool exposure via a service config file

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

  1. Open your agent's MCP configuration file.
  2. Merge the snippet below into it.
  3. Restart the agent — the "Snowflake" tools will be available.
{
  "mcpServers": {
    "snowflake": {
      "command": "uvx",
      "args": [
        "snowflake-labs-mcp",
        "--service-config-file",
        "tools_config.yaml"
      ]
    }
  }
}

Description

Snowflake's MCP server from Snowflake Labs connects an assistant to a Snowflake account, covering both data access and the Cortex AI services layered on top of it.

Capabilities

  • Cortex Analyst for asking questions of a semantic model in natural language and getting governed SQL back
  • Cortex Search for retrieval over unstructured data stored in Snowflake
  • SQL execution against warehouses, with configurable permissions on what statement types are allowed
  • Object management for databases, schemas, tables, warehouses, and stages

Configuration

Tool exposure is driven by a service configuration file, so you decide exactly which Cortex services and SQL operations an assistant can reach. That granularity matters in an environment where the warehouse holds regulated data and query cost is metered.

Runs with uvx snowflake-labs-mcp pointed at your config file, authenticating through standard Snowflake connection parameters or key-pair authentication.

Related MCP Servers

Browse all MCP servers →