Snowflake MCP Server

What is Snowflake MCP Server about?

A server implementation that exposes Snowflake database operations via Model Context Protocol tools. It lets clients run read‑only SELECT statements, optionally perform write operations, list databases/schemas/tables, describe table structures, and append data insights that appear in a continuously updated memo resource.

How to use Snowflake MCP Server?

1. Install the server (recommended via Smithery or UVX). Example with Smithery:

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

2. Configure connection parameters either through command‑line arguments, a TOML connections file, or environment variables (SNOWFLAKE_USER, SNOWFLAKE_PASSWORD, etc.).
3. Run the server using the chosen runner (e.g., uvx run mcp_snowflake_server or the npx command shown in the serverConfig).
4. Invoke tools from a compatible client (Claude Desktop, custom MCP client) to query data, explore schema, or add insights.

Key Features of Snowflake MCP Server

• Read Query Tool – Execute arbitrary SELECT statements and receive results as JSON objects.
• Write Query & Create Table Tools – Optional write capabilities (--allow-write).
• Schema Exploration – List databases, schemas, tables, and retrieve detailed column metadata.
• Dynamic Insight Memo – append_insight updates memo://insights in real time.
• Prefetch Context Resources – Optional per‑table context resources (context://table/{table_name}).
• Configurable Exclusions – Filter out unwanted databases, schemas, or tables.
• Logging – Adjustable log directory and level.

Use Cases of Snowflake MCP Server

• Data Analyst Assistant – Enable AI assistants to run ad‑hoc queries and retrieve schema information without direct database credentials.
• Automated Insight Collection – Applications can push discovered patterns or metrics to the memo resource for later review.
• Rapid Prototyping – Developers can interactively explore Snowflake structures and test queries within a conversational UI.
• Controlled Write Operations – Enable safe, audited data modifications in a staged environment using the --allow-write flag.

FAQ from Snowflake MCP Server

Q: Are write operations enabled by default?
A: No. Write tools (write_query, create_table) require the --allow-write flag.

Q: How are credentials supplied?
A: Via command‑line arguments, a TOML connections file, or environment variables (SNOWFLAKE_*).

Q: Can I limit which databases are exposed?
A: Yes, exclusion patterns can be set in runtime_config.json or via CLI flags.

Q: What does memo://insights contain?
A: An aggregated list of textual insights added through the append_insight tool.

Q: Is prefetching required for per‑table context resources?
A: Prefetch must be enabled; otherwise only the memo resource is available.

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

Traditional Configuration (Individual Parameters)

"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: "--private_key_path", "your_private_key_absolute_path"
      // 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}"]
    ]
  }
}

TOML Configuration (Recommended)

"mcpServers": {
  "snowflake_production": {
    "command": "uvx",
    "args": [
      "--python=3.12",
      "mcp_snowflake_server",
      "--connections-file", "/path/to/snowflake_connections.toml",
      "--connection-name", "production"
      // 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}"]
    ]
  },
  "snowflake_staging": {
    "command": "uvx",
    "args": [
      "--python=3.12",
      "mcp_snowflake_server",
      "--connections-file", "/path/to/snowflake_connections.toml",
      "--connection-name", "staging"
    ]
  }
}

---

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"
SNOWFLAKE_PASSWORD="xxx"
SNOWFLAKE_PRIVATE_KEY_PATH=/absolute/path/key.p8
# 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:

Traditional Configuration (Using Environment Variables)

"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}"]
    ]
  }
}

TOML Configuration (Recommended)

"mcpServers": {
  "snowflake_local": {
    "command": "/absolute/path/to/uv",
    "args": [
      "--python=3.12",
      "--directory", "/absolute/path/to/mcp_snowflake_server",
      "run", "mcp_snowflake_server",
      "--connections-file", "/absolute/path/to/snowflake_connections.toml",
      "--connection-name", "development"
      // 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