MCP Snowflake Server NSP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SNOWFLAKE_ROLE | No | Role to assume | |
| SNOWFLAKE_USER | No | Snowflake username | |
| SNOWFLAKE_TOKEN | No | OAuth bearer token (for token auth) | |
| SNOWFLAKE_SCHEMA | No | Default schema (required) | |
| SNOWFLAKE_ACCOUNT | No | Snowflake account identifier | |
| SNOWFLAKE_DATABASE | No | Default database (required) | |
| SNOWFLAKE_PASSWORD | No | Password for password authentication | |
| SNOWFLAKE_WAREHOUSE | No | Virtual warehouse to use | |
| SNOWFLAKE_OAUTH_SCOPE | No | OAuth scope (optional, for client credentials flow) | |
| SNOWFLAKE_AUTHENTICATOR | No | Authentication method: 'snowflake', 'snowflake_jwt', 'externalbrowser', 'oauth_client_credentials', 'oauth' | |
| SNOWFLAKE_OAUTH_CLIENT_ID | No | OAuth client ID (for client credentials flow) | |
| SNOWFLAKE_PRIVATE_KEY_FILE | No | Absolute path to .p8 private key file (for key-pair auth) | |
| SNOWFLAKE_OAUTH_CLIENT_SECRET | No | OAuth client secret (for client credentials flow) | |
| SNOWFLAKE_PRIVATE_KEY_FILE_PWD | No | Passphrase for encrypted private key | |
| SNOWFLAKE_OAUTH_TOKEN_REQUEST_URL | No | OAuth token request URL (for client credentials flow) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_databasesA | List all available databases in Snowflake |
| list_schemasB | List all schemas in a database |
| list_tablesB | List all tables in a specific database and schema |
| describe_tableA | Get the schema information for a specific table |
| read_queryB | Execute a SELECT query. |
| append_insightB | Add a data insight to the memo |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Data Insights Memo | A living document of discovered data insights |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose: listing databases, schemas, tables, describing a table's schema, executing queries, and appending a text insight. There is no ambiguity or overlap between them.
All tool names follow the consistent verb_noun pattern with lowercase and underscores (e.g., list_databases, describe_table, append_insight). The naming is uniform and predictable.
With 6 tools, the set is well-scoped for a Snowflake exploration and insight server. It covers basic metadata discovery, querying, and an insight-add feature without being bloated or insufficient.
The tool set covers read operations and metadata listing well, but lacks write capabilities beyond appending insights (no INSERT/UPDATE/DELETE queries, no DDL operations like creating tables). This creates a notable gap for many database workflows.