Provides comprehensive database interaction capabilities including SQL query execution, schema exploration, table management, and data analysis tools for Snowflake data warehouses.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Snowflake MCP Server show me the top 10 customers by total sales this month"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
Related MCP server: Snowflake MCP Server
memo://insights
A continuously updated memo aggregating discovered data insights.
Updated automatically when new insights are appended via the append_insight tool.
context://table/{table_name}
(If prefetch enabled) Per-table schema summaries, including columns and comments, exposed as individual resources.
The server exposes the following tools:
read_query
Execute SELECT queries to read data from the database.
Input:
query (string): The SELECT SQL query to execute
Returns: Query results as array of objects
write_query (enabled only with --allow-write)
Execute INSERT, UPDATE, or DELETE queries.
Input:
query (string): The SQL modification query
Returns: Number of affected rows or confirmation
create_table (enabled only with --allow-write)
Create new tables in the database.
Input:
query (string): CREATE TABLE SQL statement
Returns: Confirmation of table creation
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 database
schema (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
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 of memo://insights resource
To install Snowflake Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install mcp_snowflake_server --client claude"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: "--allow_write"
// Optionally: "--log_dir", "/absolute/path/to/logs"
// Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
// Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
]
}
}Install Claude AI Desktop App
Install uv:
curl -LsSf https://astral.sh/uv/install.sh | shCreate a .env file 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.json to set exclusion patterns for databases, schemas, or tables.
Test locally:
uv --directory /absolute/path/to/mcp_snowflake_server run mcp_snowflake_serverAdd 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: "--allow_write"
// Optionally: "--log_dir", "/absolute/path/to/logs"
// Optionally: "--log_level", "DEBUG"/"INFO"/"WARNING"/"ERROR"/"CRITICAL"
// Optionally: "--exclude_tools", "{tool_name}", ["{other_tool_name}"]
]
}
}By default, write operations are disabled. Enable them explicitly with --allow-write.
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_insight tool updates the memo://insights resource dynamically.
MIT
Add a data insight to the memo
| Name | Required | Description | Default |
|---|---|---|---|
| insight | Yes | Data insight discovered from analysis |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral traits but only states the action. It does not disclose side effects (e.g., whether the memo is modified permanently), permissions needed, or return behavior beyond 'add'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no unnecessary words. It is front-loaded and concise for a simple tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity, the description is mostly adequate. It identifies the action and parameter, though it could be more explicit about which memo (e.g., current context) and whether it appends or replaces.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'insight' has a description in the schema ('Data insight discovered from analysis'), and schema description coverage is 100%. The tool description adds no further meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Add') and the resource ('data insight to the memo'), with a specific verb and resource that distinguishes it from sibling tools (e.g., describe_table, read_query).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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, nor any context about prerequisites or exclusions. The description only states the function without usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the schema information for a specific table
| Name | Required | Description | Default |
|---|---|---|---|
| table_name | Yes | Fully qualified table name in the format 'database.schema.table' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates a safe read operation. However, with no annotations, it lacks details on potential limitations, permissions, or the exact content of the schema returned (e.g., columns, types).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words. It is appropriately sized for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter and no output schema, the description is mostly complete. However, it could specify what 'schema information' includes (e.g., columns, types) for better agent understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%; the parameter 'table_name' is fully described in the schema. The description adds no additional semantic meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Get the schema information for a specific table' clearly specifies the verb and resource. It distinguishes from sibling tools like list_tables which only list table names.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly indicates usage for retrieving schema of a specific table. While no explicit when-not-to-use is provided, sibling names provide context, making it clear that this tool is for detailed schema rather than listing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch video media for specific violation events. Returns simple list with DEVICE_EVENT_UUID and Region.
| Name | Required | Description | Default |
|---|---|---|---|
| violation_ids | Yes | List of violation IDs to get video media for |
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 mentions the return format ('simple list with DEVICE_EVENT_UUID and Region'), which adds some behavioral context. However, it lacks details on permissions, rate limits, error handling, or data freshness, which are critical for a fetch operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences that directly state the purpose and return format. It's front-loaded and wastes no words, though it could be slightly more structured for clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description provides basic purpose and return format but lacks details on behavioral traits, error cases, or usage context. It's minimally adequate for a simple fetch tool but has clear gaps in completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 the 'violation_ids' parameter fully. The description doesn't add any meaning beyond what the schema provides, such as format examples or constraints. Baseline 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Fetch video media for specific violation events.' It specifies the verb ('fetch'), resource ('video media'), and target ('violation events'). However, it doesn't distinguish from siblings like 'append_insight' or 'read_query' which serve different functions, so it's not a perfect 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. The description doesn't mention prerequisites, context, or exclusions. It's a basic statement of function with no usage instructions, leaving the agent to infer applicability.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all available databases in Snowflake
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. The description only states it lists databases, but does not disclose behavioral details such as permissions required, whether it returns names only, or any limitations. For a read-only tool, minimal disclosure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence of 6 words, no redundancy, front-loaded. Every word is necessary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with no parameters and no output schema, the description is minimally adequate. It could mention return format or whether it requires any permissions, but overall meets basic needs.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters in schema, so description doesn't need to add parameter semantics. Baseline for 0 parameters is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all available databases in Snowflake, with a specific verb ('List') and resource ('databases'). It distinguishes itself from sibling tools like 'list_schemas' and 'describe_table'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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_schemas' or 'list_tables'. No when-not-to-use or explicit context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all schemas in a database
| Name | Required | Description | Default |
|---|---|---|---|
| database | Yes | Database name to list schemas from |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided; description only states the action without disclosing any behavioral traits like authentication, side effects, or return format.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded and concise without wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool, the description and schema together provide adequate information, though no output schema exists to explain return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and parameter description in schema is clear; description adds no extra semantic value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'List' and resource 'schemas', clearly distinguishing from siblings like list_databases and list_tables.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives; no context about prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all tables in a specific database and schema
| Name | Required | Description | Default |
|---|---|---|---|
| database | Yes | Database name | |
| schema | Yes | Schema name |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Only states 'list', implying read-only, but no details on permissions, performance, or whether metadata is included. Insufficient for a tool with zero annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with no wasted words. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with full schema coverage and no output schema, the description is adequate. Lacks context about output format but sufficient for basic usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with clear parameter descriptions. Description adds no extra meaning beyond what schema already provides; baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'List all tables in a specific database and schema' with a specific verb and resource. It distinguishes from sibling tools like list_databases and list_schemas which cover different resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives like list_databases, list_schemas, or describe_table. No mention of prerequisites (e.g., need to select database first) or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute a SELECT query.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | SELECT SQL query to execute |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but only says 'Execute a SELECT query.' This implies a read-only operation, but it does not explicitly state that no side effects occur, no data is modified, or what happens on invalid queries. The behavioral profile is insufficiently disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise at 4 words, front-loading the core purpose. While it could be slightly more structured by adding a sentence about return value or constraints, it is not verbose and wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and a single parameter, the description is minimally adequate: it states what the tool does. However, it lacks mention of the return format (e.g., result rows), potential limits (e.g., max rows), or error behavior. It is complete enough for a simple tool but could be more informative.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with the query parameter description 'SELECT SQL query to execute'. The tool description adds no extra meaning beyond this. Per guidelines, baseline is 3 when coverage is high, and there is no additional value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Execute' and the resource 'SELECT query', making the tool's function obvious. It is distinct from sibling tools like describe_table or list_tables, which are metadata operations, and append_insight, which is likely a write operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 does not mention that it is for ad-hoc data retrieval and not for exploring schema or modifying data, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0append_insightdescribe_tablefetch_violation_videoslist_databaseslist_schemaslist_tablesread_queryScored across 7 tools
Each tool has a clearly distinct purpose with no overlap: append_insight handles data insights, describe_table provides schema details, fetch_violation_videos retrieves video media, list_databases/schemas/tables enumerate database objects, and read_query executes queries. The tools are well-separated by function and target resources.
All tools follow a consistent verb_noun naming pattern (e.g., append_insight, describe_table, fetch_violation_videos, list_databases, list_schemas, list_tables, read_query). The naming is uniform, predictable, and uses snake_case throughout without any deviations.
With 7 tools, the server is well-scoped for Snowflake database operations. The count is appropriate, covering core functions like listing databases/schemas/tables, describing tables, executing queries, and adding insights, without being too sparse or bloated.
The toolset provides good coverage for Snowflake database interactions, including listing, describing, and querying. However, there are minor gaps such as lacking tools for creating or modifying database objects (e.g., create_table, update_table) or handling transactions, which agents might need to work around.
Ask data questions in natural language. Get SQL, insights, and charts from your databases.
Query BigQuery, Snowflake, Redshift & Azure Synapse with natural language
Your Databricks Lakehouse in natural language: run SQL on your SQL warehouses, track long-running qu
Query 40 databases from Claude, ChatGPT, or Cursor — on any device. Read-only, encrypted, audited.
