Snowflake MCP Server
A read-only server for interacting with Snowflake databases, allowing SELECT queries and access to schema context.
Snowflake MCP Server
Slightly altered from https://github.com/isaacwasserman/mcp-snowflake-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. Does not include the ability to execute write operations, and includes a system prompt.
Components
Resources
-
memo://insights
A continuously updated memo aggregating discovered data insights.
Updated automatically when new insights are appended via theappend_insighttool. -
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
ExecuteSELECTqueries to read data from the database.
Input:query(string): TheSELECTSQL query to execute
Returns: Query results as array of objects
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 databaseschema(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 ofmemo://insightsresource
Usage with Claude Desktop
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: "--log_dir", "/absolute/path/to/logs"
// Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
// Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
]
}
}
Installing Locally
-
Install Claude AI Desktop App
-
Install
uv:
curl -LsSf https://astral.sh/uv/install.sh | sh
- Create a
.envfile 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"
-
[Optional] Modify
runtime_config.jsonto set exclusion patterns for databases, schemas, or tables. -
Test locally:
uv --directory /absolute/path/to/mcp_snowflake_server run mcp_snowflake_server
- 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: "--log_dir", "/absolute/path/to/logs"
// Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
// Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
]
}
}
Notes
- 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_insighttool updates thememo://insightsresource dynamically.
License
MIT
Máy chủ liên quan
Trino MCP Server
A Go implementation of a Model Context Protocol (MCP) server for Trino, enabling LLM models to query distributed SQL databases through standardized tools.
AlibabaCloud DMS MCP Server
An AI-powered gateway for managing over 40 data sources like Alibaba Cloud and mainstream databases, featuring NL2SQL, code generation, and data migration.
Bitable
Interact with Lark Bitable tables and data using the Model Context Protocol.
Seatable
A comprehensive Model Context Protocol (MCP) server for SeaTable that exposes end‑to‑end database capabilities (schema introspection, CRUD, querying, linking, select option management, and file attachment stubs) through 18+ rigorously defined tools.
Adobe Commerce MCP Server by CData
A read-only MCP server for Adobe Commerce, enabling LLMs to query live data using the CData JDBC driver.
MCP Alchemy
Explore, query, and analyze SQLAlchemy-compatible databases directly from your desktop.
Flexpa FHIR
An MCP server for interacting with FHIR (Fast Healthcare Interoperability Resources) servers, enabling access and search of healthcare data.
Exasol MCP
Exasol MCP server. Provides knowledge about the Exasol database to an LLM through the Model Context Protocol.
MySQL MCP Tools
Provides tools for querying and managing a MySQL database.
MCP-MySQL-Ops
You are working with the MCP MySQL Operations Server, a powerful tool that provides comprehensive MySQL database monitoring and analysis capabilities through natural language queries. This server offers 19 specialized tools for database administration, performance monitoring, and system analysis.