read_queryLABSCO SUMMARY
A warehouse you can ask about before you query it.
Schema browsing, the query itself and somewhere to keep the finding all live in one connection — and the destructive half stays absent until you start the server with the flag that adds it.
What it is
A server over a Snowflake connection. Reads are always available; the write and create-table tools exist only when the server was started with --allow-write. Alongside the tools it exposes per-table schema summaries and a running insights memo as MCP resources.
What you get
- read_query runs a SELECT and returns rows as objects
- Schema navigation without SQL: list_databases, list_schemas, list_tables, and describe_table for column names, types, nullability, defaults and comments
- append_insight adds a finding to a memo the server keeps updated at memo://insights, so what you learned outlives the session
- Per-table schema summaries are exposed as resources when prefetch is on, so context arrives without a round trip
- write_query and create_table cover INSERT, UPDATE, DELETE and CREATE TABLE — present only when the server was launched with
--allow-write
Requirements
A Snowflake account and connection details for it. The server is read-only unless you start it with --allow-write, which is the switch that turns on write_query and create_table.
Setup effort
Add the configuration to your client
USE CASES
01
Finding the table you need
Walk databases, schemas and tables, then read the columns with their types and comments.
02
Answering a data question without hand-writing SQL
The SELECT is generated and run in one step, and the rows come back as objects.
03
Keeping what you learned
Findings append to a memo the server exposes as a resource, so the next session starts from them.
04
Making a controlled change
Writes only exist when the server was launched with --allow-write, so a read-only deployment cannot be talked into one.
8 tools
Listed in project docs. Your client may show a different list.
write_querycreate_tablelist_databaseslist_schemaslist_tablesdescribe_tableappend_insightBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
uvx on PATH
Optional
- SNOWFLAKE_ACCOUNT in your environment
- SNOWFLAKE_USER in your environment
- SNOWFLAKE_PASSWORD in your environment
- SNOWFLAKE_PRIVATE_KEY_PATH in your environment
Where it runs
Both documented setups run the server on your machine.
INSTALLATION
Connect your client
MCP Clients
Claude Desktop — TOML connections file
CLAUDE DESKTOP — TOML CONNECTIONS FILE · JSON
{
"mcpServers": {
"snowflake_production": {
"command": "uvx",
"args": [
"--python=3.12",
"mcp_snowflake_server",
"--connections-file",
"<YOUR_PATH_TO_SNOWFLAKE_CONNECTIONS>",
"--connection-name",
"production"
]
}
}
}<YOUR_PATH_TO_SNOWFLAKE_CONNECTIONS> is the path to your Snowflake connections file, and production is a sample; yours is a connection name defined in that file. The connection details come from that file.
The SNOWFLAKE_* environment variables are for the project's local install, where they go in a .env file; neither block here uses them — each passes the connection as arguments.
Claude Desktop — separate connection settings
CLAUDE DESKTOP — SEPARATE CONNECTION SETTINGS · JSON
{
"mcpServers": {
"snowflake_pip": {
"command": "uvx",
"args": [
"--python=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>"
]
}
}
}The SNOWFLAKE_* environment variables are for the project's local install, where they go in a .env file; neither block here uses them — each passes the connection as arguments.
