Loading...

Snowflake MCP server enables data interaction and analysis via SQL queries and schema exploration, with configurable write access and insight aggregation.
Boost this tool
Subscribe to listing upgrades or segmented pushes.
Snowflake MCP server enables data interaction and analysis via SQL queries and schema exploration, with configurable write access and insight aggregation.
The Snowflake MCP server is relatively safe in its default read-only configuration. Enabling write access significantly increases the risk, requiring careful management of permissions and input validation to prevent data corruption or unauthorized modifications. Use of connection files is recommended to avoid hardcoding credentials.
Performance depends on the complexity of the SQL queries and the size of the data being processed. Consider optimizing queries for better performance.
Snowflake charges for compute and storage. Running complex queries or storing large amounts of data can incur significant costs.
npx -y @smithery/cli install mcp_snowflake_server --client claudeSNOWFLAKE_USERSNOWFLAKE_ACCOUNTSNOWFLAKE_ROLESNOWFLAKE_DATABASESNOWFLAKE_SCHEMASNOWFLAKE_WAREHOUSESNOWFLAKE_PASSWORDread_queryExecutes SELECT queries to retrieve data from the Snowflake database.
Read-only operation, no data modification.
write_queryExecutes INSERT, UPDATE, or DELETE queries to modify data in the Snowflake database.
Allows modification and deletion of data.
create_tableCreates new tables within the Snowflake database.
Allows structural changes to the database schema.
list_databasesLists all databases available in the Snowflake instance.
Read-only operation, no data modification.
list_schemasLists all schemas within a specified database.
Read-only operation, no data modification.
list_tablesLists all tables within a specified database and schema.
Read-only operation, no data modification.
describe_tableRetrieves column information for a specified table.
Read-only operation, no data modification.
append_insightAdds a new data insight to the insights memo.
Non-destructive write operation, but could be used to inject misleading information.
Environment Variable
cloud
The Snowflake MCP server is relatively safe in its default read-only configuration. Enabling write access significantly increases the risk, requiring careful management of permissions and input validation to prevent data corruption or unauthorized modifications. Use of connection files is recommended to avoid hardcoding credentials.
Autonomy is limited by the enabled tools and the permissions of the Snowflake user. Write operations should be carefully considered before enabling.
Production Tip
Use a dedicated Snowflake user with restricted permissions for the MCP server to minimize the impact of potential security breaches.
Use the `--allow-write` command-line option when starting the server.
Use a TOML configuration file to store connection parameters and avoid hardcoding credentials in the command line. Consider using private key authentication instead of passwords.
Yes, you can use exclusion patterns in the `runtime_config.json` file to filter out specific databases, schemas, or tables.
Configure logging using the `--log_dir` and `--log_level` options. Review the logs for errors and security events.
Python 3.12 or lower is recommended.
Yes, set the `SNOWFLAKE_AUTHENTICATOR` environment variable to `externalbrowser`.
Use Smithery or UVX as described in the README.