Skip to main content
Glama
YannBrrd

Simple Snowflake MCP

by YannBrrd
OverviewSchemaRelated ServersScoreDiscussions
Python
Remote

Simple Snowflake MCP server

Enhanced Snowflake MCP Server with comprehensive configuration system and full MCP protocol compliance.

A production-ready MCP server that provides seamless Snowflake integration with advanced features including configurable logging, resource subscriptions, and comprehensive error handling. Designed to work seamlessly behind corporate proxies.

For release details, see CHANGELOG.md.

Tools

The server exposes the following MCP tools to interact with Snowflake:

Database Operations:

  • execute-snowflake-sql: Executes a SQL query on Snowflake and returns the result. Supports json (default), markdown, and csv output via the format argument.

  • execute-query: Executes a SQL query with server-enforced read-only protection. In read-only mode (the default) only SELECT, SHOW, DESCRIBE, EXPLAIN, and WITH statements (without DML) are allowed. Read-only mode is governed solely by server configuration and cannot be relaxed by the caller. Supports a limit, an offset for paging, and markdown (default)/json/csv output via format. When a result is truncated the response includes the offset for the next page.

Discovery and Metadata:

  • get-connection-info: Returns current Snowflake connection information and server status.

  • list-snowflake-warehouses: Lists available Data Warehouses (DWH) on Snowflake. Pass include_details: false for names only.

  • list-databases: Lists all accessible Snowflake databases. Supports a pattern filter (wildcards) and include_details.

  • list-schemas: Lists schemas in a database. Supports a pattern filter (wildcards) and include_details.

  • list-tables: Lists tables in a database/schema. Supports a pattern filter (wildcards) and include_details.

  • list-views: Lists views in a database/schema. Supports a pattern filter (wildcards) and include_details.

  • describe-table: Returns the columns and types of a database/schema/table (works for views too). Supports json (default)/markdown/csv via format.

  • query-view: Reads rows from a database/schema/view (or table) by name, with the same server-enforced read-only protection and row limiting as execute-query. Supports a limit, an offset for paging, and markdown (default)/json/csv via format.

  • export-schema: Exports hierarchical schema metadata (databases → schemas → tables/views → columns). Supports json (default), yaml, and sql via format, an optional database filter, and opt-in include_data_samples (table rows only, max 3 rows per table).

Notes (in-memory session state):

  • add-note: Adds or updates a note (name, content) kept in server memory for the session.

  • delete-note: Deletes an existing note by name.

  • list-notes: Lists current note names in sorted order.

  • get-note: Returns the note payload (name, content) for a given note name.

Prompts

The server also exposes MCP prompts that bundle server context into ready-to-use messages:

  • summarize-notes: Summarizes the stored notes. Arguments: style (brief/detailed/executive), format (text/markdown/json).

  • analyze-snowflake-schema: Produces a schema-analysis prompt. Arguments: database (optional focus), focus (tables/views/functions/all).

  • generate-sql-query: Helps draft a SQL query from a natural-language goal. Arguments: intent (required), complexity (simple/intermediate/advanced).

  • troubleshoot-connection: Builds a connection-troubleshooting prompt. Arguments: error_message (optional).

🔒 Security Model

This server executes client-supplied SQL against Snowflake using a single set of credentials. Treat the MCP client as untrusted (an LLM can be prompt-injected) and deploy accordingly.

The real security boundary is a least-privilege Snowflake role, not the server's keyword filter. The built-in read-only check is defense-in-depth only. Always connect with a role scoped to exactly what you need.

Required deployment posture:

  1. Use a least-privilege, read-only Snowflake role. For read-only deployments, grant only USAGE/SELECT (and the relevant SHOW/DESCRIBE visibility) — no INSERT/UPDATE/DELETE/DDL/GRANT. If the role cannot write, no bypass of the keyword filter can cause damage.

  2. Keep read_only: true (the default). Read-only mode is governed solely by server configuration / the MCP_READ_ONLY environment variable. It is not client-controllable — there is no read_only tool argument.

  3. Set a statement timeout and rate limit (see config.yaml) to bound runaway or abusive queries and warehouse-credit consumption.

What the server enforces:

  • Read-only mode applies to every SQL-executing tool through a single guard; comments are stripped, multi-statement input and CTE-fronted DML (e.g. WITH ... DELETE) are rejected.

  • pattern / database arguments are validated against a strict allow-list before being placed into LIKE clauses; limit is coerced to a bounded integer and applied at the driver, never concatenated into SQL.

  • Row-producing reads without an explicit LIMIT are capped at default_query_limit rows (applied at the driver). When a result is capped the response includes an explicit "results were truncated" notice — rows are never dropped silently. Pass a larger limit (up to max_query_limit) or add your own LIMIT clause to retrieve more.

  • Snowflake errors are not returned verbatim to the client; a generic message with a reference id is returned and full detail is logged server-side.

  • Query text is not logged at INFO (only a length + hash); full SQL is DEBUG-only.

Related MCP server: mcp-server-motherduck

🆕 Configuration System

The server now includes a comprehensive YAML-based configuration system that allows you to customize all aspects of the server behavior.

Configuration File Structure

Create a config.yaml file in your project root:

# Logging Configuration
logging:
  level: INFO  # DEBUG, INFO, WARNING, ERROR, CRITICAL (overridable via LOG_LEVEL)
  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
  file_logging:
    enabled: false        # Set to true to enable file logging
    filename: "logs/server.log"  # Must resolve under repository ./logs/
    max_bytes: 10485760   # Rotate after 10 MB
    backup_count: 5

# Server Configuration
server:
  name: "simple_snowflake_mcp"
  version: "0.4.0"
  description: "Enhanced Snowflake MCP Server with full protocol compliance"
  connection:
    test_on_startup: true
    timeout: 30

# Snowflake Configuration
snowflake:
  # Read-only mode is read from here (and the MCP_READ_ONLY env var), NOT from
  # the server block. Set to false to allow write operations.
  read_only: true
  default_query_limit: 1000
  max_query_limit: 50000
  statement_timeout_seconds: 300
  connection_reuse: true

# Security controls
security:
  rate_limit:
    enabled: true
    max_calls: 60
    window_seconds: 60
  notes:
    max_count: 100
    max_content_length: 10000

# MCP Protocol Settings
mcp:
  experimental_features:
    resource_subscriptions: true  # Enable resource change notifications
    completion_support: false    # Set to true when MCP version supports it
  
  notifications:
    resources_changed: true
    tools_changed: true
    prompts_changed: true

Using Custom Configuration

You can specify a custom configuration file using the CONFIG_FILE environment variable:

Windows:

set CONFIG_FILE=config_debug.yaml
python -m simple_snowflake_mcp

Linux/macOS:

CONFIG_FILE=config_production.yaml python -m simple_snowflake_mcp

Configuration Override Priority

Configuration values are resolved in this order (highest to lowest priority):

  1. Environment variables (e.g., LOG_LEVEL, MCP_READ_ONLY)

  2. Custom configuration file (via CONFIG_FILE)

  3. Default config.yaml file

  4. Built-in defaults

🚀 Quick Install

Method 1: Install with uvx (Recommended)

# Install and run directly
uvx simple-snowflake-mcp

Method 2: Install from source

# Clone the repo
git clone https://github.com/YannBrrd/simple_snowflake_mcp
cd simple_snowflake_mcp

# Install with uv (creates a venv automatically)
uv sync

# Run
uv run simple-snowflake-mcp

Method 3: Development

# Install with development dependencies
uv sync --all-extras

# Run the tests
uv run pytest

# Lint with ruff
uv run ruff check .
uv run ruff format .

Configuration Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json

On Windows: %APPDATA%/Claude/claude_desktop_config.json

"mcpServers": {
  "simple_snowflake_mcp": {
    "command": "uv",
    "args": [
      "--directory",
      ".", 
      "run",
      "simple_snowflake_mcp"
    ]
  }
}
"mcpServers": {
  "simple_snowflake_mcp": {
    "command": "uvx",
    "args": [
      "simple_snowflake_mcp"
    ]
  }
}

Docker Setup

Prerequisites

  • Docker and Docker Compose installed on your system

  • Your Snowflake credentials

Quick Start with Docker

  1. Clone the repository

    git clone <your-repo>
cd simple_snowflake_mcp

  2. Set up environment variables

    cp .env.example .env
# Edit .env with your Snowflake credentials

  3. Build and run with Docker Compose

    # Build the Docker image
docker-compose build

# Start the service
docker-compose up -d

# View logs
docker-compose logs -f

Docker Commands

Using Docker Compose directly:

# Build the image
docker-compose build

# Start in production mode
docker-compose up -d

# Start in development mode (with volume mounts for live code changes)
docker-compose --profile dev up simple-snowflake-mcp-dev -d

# View logs
docker-compose logs -f

# Stop the service
docker-compose down

# Clean up (remove containers, images, and volumes)
docker-compose down --rmi all --volumes --remove-orphans

Using the provided Makefile (Windows users can use make with WSL or install make for Windows):

# See all available commands
make help

# Build and start
make build
make up

# Development mode
make dev-up

# View logs
make logs

# Clean up
make clean

Docker Configuration

The Docker setup includes:

  • Dockerfile: Multi-stage build with Python 3.11 slim base image

  • docker-compose.yml: Service definition with environment variable support

  • .dockerignore: Optimized build context

  • Makefile: Convenient commands for Docker operations

Environment Variables

All Snowflake configuration can be set via environment variables:

Required:

  • SNOWFLAKE_USER: Your Snowflake username

  • SNOWFLAKE_PASSWORD: Your Snowflake password

  • SNOWFLAKE_ACCOUNT: Your Snowflake account identifier

Optional:

  • SNOWFLAKE_WAREHOUSE: Warehouse name

  • SNOWFLAKE_DATABASE: Default database

  • SNOWFLAKE_SCHEMA: Default schema

  • MCP_READ_ONLY: Set to "TRUE" for read-only mode (default: TRUE)

Configuration System (v0.2.0):

  • CONFIG_FILE: Path to custom configuration file (default: config.yaml)

  • LOG_LEVEL: Override logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL)

Development Mode

For development, use the development profile which mounts your source code:

docker-compose --profile dev up simple-snowflake-mcp-dev -d

This allows you to make changes to the code without rebuilding the Docker image.

Development

Installing dependencies

# Sync all dependencies (prod + dev)
uv sync --all-extras

# Update dependencies
uv lock --upgrade

# Add a new dependency
uv add <package-name>

# Add a dev dependency
uv add --dev <package-name>

Build and Publish

# Build
uv build

# Publish to PyPI
uv publish --token $UV_PUBLISH_TOKEN

CI

GitHub Actions CI runs on pushes to main and on pull requests via .github/workflows/ci.yml:

uv run ruff check .
uv run ruff format --check .
uv run pytest

Debugging with MCP Inspector

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv run simple-snowflake-mcp

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

New Feature: Snowflake SQL Execution

The server exposes an MCP tool execute-snowflake-sql to execute a SQL query on Snowflake and return the result.

Usage

Call the MCP tool execute-snowflake-sql with a sql argument containing the SQL query to execute. The result will be returned as a list of dictionaries (one per row).

Example:

{
  "name": "execute-snowflake-sql",
  "arguments": { "sql": "SELECT CURRENT_TIMESTAMP;" }
}

The result will be returned in the MCP response.

Installation and configuration in VS Code

  1. Clone the project and install dependencies

    git clone https://github.com/YannBrrd/simple_snowflake_mcp
cd simple_snowflake_mcp

# Install with uv (creates a venv automatically)
uv sync --all-extras

  2. Configure Snowflake access

    • Copy .env.example to .env and fill in your credentials:

      SNOWFLAKE_USER=...
SNOWFLAKE_PASSWORD=...
SNOWFLAKE_ACCOUNT=...
# SNOWFLAKE_WAREHOUSE   Optional: Snowflake warehouse name
# SNOWFLAKE_DATABASE    Optional: default database name
# SNOWFLAKE_SCHEMA      Optional: default schema name
# MCP_READ_ONLY=true|false   Optional: true/false to force read-only mode

  3. Configure the server (v0.2.0)

    • If no config.yaml is present, the server uses its built-in defaults (no file is created automatically)

    • Customize logging, limits, and MCP features by editing config.yaml (an example is provided in the repository)

    • Use CONFIG_FILE=custom_config.yaml to specify a different file (resolved within the repository only, to prevent path traversal)

  4. Configure VS Code for MCP debugging

    • The .vscode/mcp.json file is already present:

      {
  "servers": {
    "simple-snowflake-mcp": {
      "type": "stdio",
      "command": "uv",
      "args": ["run", "simple-snowflake-mcp"]
    }
  }
}

    • Open the command palette (Ctrl+Shift+P), type MCP: Start Server, and select simple-snowflake-mcp.

  5. Usage

Enhanced MCP Features (v0.2.0)

Advanced MCP Protocol Support

This server now implements comprehensive MCP protocol features:

🔔 Resource Subscriptions

  • Real-time notifications when Snowflake resources change

  • Automatic updates for database schema changes

  • Tool availability notifications

📋 Enhanced Resource Management

  • Dynamic resource discovery and listing

  • Detailed resource metadata and descriptions

  • Resource templates for browsing the object hierarchy by URI (snowflake://database/{database}/schemas, snowflake://database/{database}/schema/{schema}/tables, snowflake://table/{database}/{schema}/{table})

  • Argument completion for prompts and resource templates (live database/ schema/table name suggestions)

  • Client-controlled log verbosity via the MCP logging/setLevel request

⚡ Performance & Reliability

  • Configurable query limits and a server-side statement timeout

  • Comprehensive error handling with generic client messages and a server-side reference id

  • Single-connection reuse with automatic reconnect on a stale connection

🔧 Development Features

  • Multiple output formats (JSON, Markdown, CSV)

  • In-process rate limiting across all tool calls

  • Comprehensive logging with configurable levels (and an explicit truncation notice on capped results)

MCP Capabilities Advertised

The server advertises these MCP capabilities:

  • ✅ Tools: Full tool execution with comprehensive schemas

  • ✅ Resources: Dynamic resource discovery, subscriptions, and templates

  • ✅ Prompts: Enhanced prompts with resource integration

  • ✅ Notifications: Real-time change notifications

  • ✅ Completion: Argument completion for prompts and resource templates

  • ✅ Logging: Client-controlled log level via logging/setLevel

Supported MCP Functions

The server exposes the following MCP tools (see the Tools section above for full argument details):

Database Operations:

  • execute-snowflake-sql: Executes a SQL query and returns results as JSON, markdown, or CSV

  • execute-query: Query execution with read-only protection, row limit, and multiple output formats

Discovery and Metadata:

  • get-connection-info: Current connection information and server status

  • list-snowflake-warehouses: Lists available Data Warehouses with status

  • list-databases: Lists all accessible databases, with optional pattern filtering

  • export-schema: Exports hierarchical schema metadata in JSON, YAML, or SQL format (with optional capped table samples)

Session Notes:

  • add-note / delete-note / list-notes / get-note: Manage in-memory notes for the session

The server also implements MCP resources (Snowflake objects with subscription support) and prompts. For parameter schemas, inspect handle_list_tools in src/simple_snowflake_mcp/server.py.

🚀 Getting Started Examples

Basic Usage

# Execute a simple query
{
  "name": "execute-query",
  "arguments": {
    "sql": "SELECT CURRENT_TIMESTAMP;",
    "format": "markdown"
  }
}

# List all databases
{
  "name": "list-databases",
  "arguments": {}
}

Advanced Configuration

# config_production.yaml
logging:
  level: WARNING
  file_logging:
    enabled: true
    filename: "logs/mcp_server.log"

snowflake:
  # Keep true unless the connecting Snowflake role is itself read-only.
  read_only: true
  default_query_limit: 5000
  max_query_limit: 100000
  statement_timeout_seconds: 120
  connection_reuse: true

security:
  rate_limit:
    enabled: true
    max_calls: 60
    window_seconds: 60
  notes:
    max_count: 100
    max_content_length: 10000

mcp:
  experimental_features:
    resource_subscriptions: true

Debugging and Troubleshooting

Enable Debug Logging:

# Method 1: Environment variable
export LOG_LEVEL=DEBUG
python -m simple_snowflake_mcp

# Method 2: Custom config file
export CONFIG_FILE=config_debug.yaml
python -m simple_snowflake_mcp

Common Issues:

  • Connection errors: Check your Snowflake credentials and network connectivity

  • Permission errors: Ensure your user has appropriate Snowflake privileges

  • Query limits: Adjust default_query_limit in config.yaml for large result sets

  • MCP compatibility: Update to latest MCP client version for full feature support

Available Tools

7 tools
describe-viewC

Get details of a view (columns, SQL).

ParametersJSON Schema
NameRequiredDescriptionDefault
databaseYes
schemaYes
viewYes

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It states this is a read operation ('Get details'), implying it's non-destructive, but doesn't disclose behavioral traits like authentication needs, rate limits, error conditions, or what happens if the view doesn't exist. For a tool with 3 required parameters and no annotation coverage, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose ('Get details of a view') and adds specific details ('columns, SQL') without waste. Every word earns its place, making it appropriately sized for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 required parameters, no annotations, no output schema), the description is incomplete. It doesn't explain the return values (e.g., structure of details), error handling, or parameter semantics. The agent lacks sufficient context to use this tool effectively beyond its basic purpose.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema provides no parameter descriptions. The tool description adds no information about the parameters (database, schema, view), such as their formats, examples, or relationships. With 3 undocumented parameters, the description fails to compensate for the schema's lack of documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get details') and resource ('a view'), specifying what details are retrieved (columns, SQL). It distinguishes from siblings like 'list-views' (which lists views) and 'query-view' (which queries view data). However, it doesn't explicitly contrast with 'execute-query' or 'execute-snowflake-sql', which are more general query tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites like needing an existing view, nor does it contrast with 'list-views' (for listing views) or 'query-view' (for querying view data). The agent must infer usage from the tool name and description alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

execute-queryB

Execute a SQL query in read-only mode (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH) or not (if 'read_only' is false), result in markdown format.

ParametersJSON Schema
NameRequiredDescriptionDefault
read_onlyNoAllow only read-only queries
sqlYesSQL query to execute

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It discloses key behavioral traits: read-only mode by default, allowed query types, and result format. However, it doesn't mention important aspects like error handling, execution time limits, authentication requirements, or whether queries are logged/audited. For a SQL execution tool with zero annotation coverage, this leaves significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately concise with two main clauses that convey essential information. However, it could be more front-loaded by starting with the core purpose before detailing the read_only parameter behavior. The parenthetical about query types interrupts the flow slightly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a SQL execution tool with no annotations and no output schema, the description provides basic context about allowed operations and output format. However, it doesn't address critical aspects like what happens with non-SELECT queries when read_only=true, how results are structured beyond 'markdown format', or error conditions. Given the complexity of SQL execution, more completeness would be expected.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description adds minimal value beyond the schema - it mentions the 'read_only' parameter's effect on query types but doesn't provide additional semantic context about parameter interactions or usage patterns. Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'execute' and resource 'SQL query', specifying the types of queries allowed (SELECT, SHOW, DESCRIBE, EXPLAIN, WITH) and the output format. However, it doesn't explicitly differentiate from sibling tools like 'execute-snowflake-sql' or 'query-view', which appear to be similar query execution tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context by mentioning 'read-only mode' and listing allowed query types, but doesn't provide explicit guidance on when to use this tool versus alternatives like 'execute-snowflake-sql' or 'query-view'. It mentions the 'read_only' parameter behavior but doesn't clarify when to set it to false versus using other tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

execute-snowflake-sqlC

Execute a SQL query on Snowflake and return the result.

ParametersJSON Schema
NameRequiredDescriptionDefault
sqlYesSQL query to execute

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. While 'Execute a SQL query' implies a write operation could occur, the description doesn't specify whether this tool supports read-only queries, requires specific permissions, has transaction implications, or includes any rate limits. It provides minimal behavioral context beyond the basic action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise - a single sentence that directly states the tool's function. There's zero wasted language, and it's front-loaded with the essential information. Every word earns its place in this minimal description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a SQL execution tool with no annotations and no output schema, the description is inadequate. It doesn't explain what 'return the result' means - whether it's a data table, success/failure status, or something else. Given the complexity of database operations and the lack of structured metadata, the description should provide more complete context about behavior and outputs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 100%, with the single parameter 'sql' clearly documented as 'SQL query to execute'. The description adds no additional parameter semantics beyond what the schema already provides, so the baseline score of 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Execute a SQL query') and target resource ('on Snowflake'), providing a specific verb+resource combination. However, it doesn't differentiate this tool from sibling tools like 'execute-query' or 'query-view', which appear to have similar functions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance about when to use this tool versus alternatives like 'execute-query' or 'query-view'. There's no mention of prerequisites, limitations, or appropriate contexts for selecting this specific SQL execution tool over others in the sibling set.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list-databasesB

List all accessible Snowflake databases.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.2/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'accessible' databases, hinting at permission-based filtering, but lacks details on output format, pagination, error handling, or any constraints like rate limits or authentication needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core functionality ('List all accessible Snowflake databases'). There is no wasted verbiage or redundancy, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no output schema, no annotations), the description is adequate but has gaps. It lacks details on behavioral aspects like output format or error conditions, which are important for a list operation even without complex inputs.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters, and schema description coverage is 100%, so there are no parameters to document. The description appropriately doesn't add unnecessary param details, earning a baseline score of 4 for zero-parameter tools.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List') and resource ('all accessible Snowflake databases'), making the tool's purpose immediately understandable. It doesn't differentiate from sibling tools like 'list-views' or 'list-snowflake-warehouses', but the scope is well-defined.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'list-views' or 'list-snowflake-warehouses'. The description only states what it does without indicating context or prerequisites for usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list-snowflake-warehousesB

List available Data Warehouses (DWH) on Snowflake.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'available' warehouses but doesn't clarify what 'available' means (e.g., accessible to current user, currently running), nor does it describe output format, pagination, permissions required, or error conditions. This leaves significant gaps for a tool that presumably returns a list.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's function without any fluff or redundant information. It's appropriately sized for a zero-parameter list operation and front-loads the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a list operation with no annotations and no output schema, the description is insufficient. It doesn't explain what information is returned about warehouses (e.g., names, statuses, sizes), how results are structured, or any limitations (e.g., max results). The lack of behavioral context makes it incomplete for effective agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters with 100% schema description coverage, so the schema already fully documents the input structure. The description appropriately doesn't add parameter information since none exist, maintaining focus on the tool's purpose without unnecessary detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('available Data Warehouses (DWH) on Snowflake'), making the purpose unambiguous. It doesn't explicitly differentiate from sibling tools like 'list-databases' or 'list-views', but the resource specificity provides implicit distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'list-databases' or 'list-views', nor does it mention any prerequisites or context for usage. It simply states what the tool does without addressing when it's appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list-viewsC

List all views in a database and schema.

ParametersJSON Schema
NameRequiredDescriptionDefault
databaseYes
schemaYes

TDQS

C2.7/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action but doesn't mention whether this is a read-only operation, if it requires specific permissions, what the output format looks like, or any rate limits. This leaves significant gaps for a tool that presumably queries system metadata.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without any unnecessary words. It is appropriately sized and front-loaded, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a tool that lists database views, the lack of annotations, no output schema, and 0% schema description coverage, the description is insufficient. It doesn't explain what information is returned, how results are structured, or any behavioral traits, leaving the agent with inadequate context for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 0%, meaning the input schema provides no descriptions for the two required parameters. The description adds no semantic information about what 'database' and 'schema' represent, their expected formats, or examples, failing to compensate for the schema's lack of documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('all views in a database and schema'), making the purpose immediately understandable. However, it doesn't differentiate from sibling tools like 'list-databases' or 'describe-view' beyond the resource type, which prevents a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'list-databases', 'describe-view', or 'query-view'. It lacks context about prerequisites, such as whether the database and schema must exist or be accessible, or any exclusions for usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

query-viewC

Query a view with an optional row limit (markdown result).

ParametersJSON Schema
NameRequiredDescriptionDefault
databaseYes
limitNo
schemaYes
viewYes

TDQS

C2.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool returns 'markdown result' which gives some context about output format, but fails to describe important behavioral aspects like whether this is a read-only operation, what permissions are required, how errors are handled, or any rate limits. The description is minimal and leaves critical behavioral traits unspecified.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at just 10 words in a single sentence. It's front-loaded with the core purpose ('Query a view') and efficiently mentions both the optional parameter and output format. While perhaps too brief for adequate completeness, it wastes no words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a database query tool with 4 parameters, no annotations, and no output schema, the description is insufficiently complete. It doesn't explain what the tool actually does beyond 'query', doesn't describe the expected input formats for parameters, and provides minimal context about the operation's behavior or results. The mention of 'markdown result' is helpful but inadequate for the tool's complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage and 4 parameters (3 required), the description provides minimal parameter information. It only mentions 'optional row limit' which corresponds to the 'limit' parameter, leaving the other 3 parameters (database, schema, view) completely unexplained. The description doesn't compensate for the schema's lack of descriptions, resulting in poor parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool 'Query a view' which indicates a read operation on a database view, but it's vague about what constitutes a 'query' versus just retrieving data. It mentions 'markdown result' which adds some specificity about output format, but doesn't clearly distinguish this from sibling tools like 'execute-query' or 'describe-view'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'execute-query' or 'describe-view'. It mentions an 'optional row limit' which implies usage for limiting results, but offers no context about appropriate scenarios, prerequisites, or exclusions compared to sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

C2.8/5.0
Disambiguation2/5

There is significant overlap between tools, particularly 'execute-query' and 'execute-snowflake-sql' which appear to serve nearly identical purposes, both executing SQL queries on Snowflake. Additionally, 'describe-view' and 'query-view' both target views but with different outputs, which could cause confusion about when to use each. This ambiguity makes it difficult for an agent to reliably select the correct tool without careful examination of descriptions.

Naming Consistency3/5

The naming is mixed with some consistency issues. Most tools use a verb-noun pattern (e.g., 'list-databases', 'describe-view'), but there are deviations like 'execute-snowflake-sql' which includes the platform name, unlike the simpler 'execute-query'. The use of hyphens is consistent, but the verb choices and specificity vary, leading to a readable but not fully predictable naming scheme.

Tool Count4/5

With 7 tools, the count is reasonable for a Snowflake database interaction server, covering key operations like listing resources, executing queries, and managing views. It is slightly on the lower side but still well-scoped for basic database tasks, with each tool having a clear role except for the overlapping execution tools.

Completeness3/5

The tool set covers core read and list operations for Snowflake, including databases, warehouses, and views, but has notable gaps. There is no support for write operations (e.g., INSERT, UPDATE, DELETE) or schema modifications, which limits the server to querying and describing existing data. While agents can perform basic exploration, the lack of data manipulation tools makes the surface incomplete for full database management.

Maintenance

ActivityStale
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/YannBrrd/simple_snowflake_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server