This Snowflake MCP server provides tooling for Snowflake Cortex AI, object management, and SQL orchestration, bringing these capabilities to the MCP ecosystem. When connected to an MCP Client (e.g. Claude for Desktop, fast-agent, Agentic Orchestration Framework), users can leverage these features.

The MCP server currently supports the below capabilities:

• Cortex Search: Query unstructured data in Snowflake as commonly used in Retrieval Augmented Generation (RAG) applications.
• Cortex Analyst: Query structured data in Snowflake via rich semantic modeling.
• Cortex Agent: Agentic orchestrator across structured and unstructured data retrieval
• Object Management: Perform basic operations against Snowflake's most common objects such as creation, dropping, updating, and more.
• SQL Execution: Run LLM-generated SQL managed by user-configured permissions.
• Semantic View Querying: Discover and query Snowflake Semantic Views

A simple configuration file is used to drive all tooling. An example can be seen at services/configuration.yaml and a template is below. The path to this configuration file will be passed to the server and the contents used to create MCP server tools at startup.

Cortex Services

Many Cortex Agent, Search, and Analyst services can be added. Ideal descriptions are both highly descriptive and mutually exclusive. Only the explicitly listed Cortex services will be available as tools in the MCP client.

Other Services

Other services include tooling for object management, query execution, and semantic view usage. These groups of tools can be enabled by setting them to True in the other_services section of the configuration file.

SQL Statement Permissions

The sql_statement_permissions section ensures that only approved statements are executed across any tools with access to change Snowflake objects. The list contains SQL expression types. Those marked with True are permitted while those marked with False are not permitted. Please see SQL Execution for examples of each expression type.

agent_services: # List all Cortex Agent services
  - service_name: <service_name>
    description: > # Describe contents of the agent service
      <Agent service that ...>
    database_name: <database_name>
    schema_name: <schema_name>
  - service_name: <service_name>
    description: > # Describe contents of the agent service
      <Agent service that ...>
    database_name: <database_name>
    schema_name: <schema_name>
search_services: # List all Cortex Search services
  - service_name: <service_name>
    description: > # Describe contents of the search service
      <Search services that ...>
    database_name: <database_name>
    schema_name: <schema_name>
  - service_name: <service_name>
    description: > # Describe contents of the search service
      <Search services that ...>
    database_name: <database_name>
    schema_name: <schema_name>
analyst_services: # List all Cortex Analyst semantic models/views
  - service_name: <service_name> # Create descriptive name for the service
    semantic_model: <semantic_yaml_or_view> # Fully-qualify semantic YAML model or Semantic View
    description: > # Describe contents of the analyst service
      <Analyst service that ...>
  - service_name: <service_name> # Create descriptive name for the service
    semantic_model: <semantic_yaml_or_view> # Fully-qualify semantic YAML model or Semantic View
    description: > # Describe contents of the analyst service
      <Analyst service that ...>
other_services: # Set desired tool groups to True to enable tools for that group
  object_manager: True # Perform basic operations against Snowflake's most common objects such as creation, dropping, updating, and more.
  query_manager: True # Run LLM-generated SQL managed by user-configured permissions.
  semantic_manager: True # Discover and query Snowflake Semantic Views and their components.
sql_statement_permissions: # List SQL statements to explicitly allow (True) or disallow (False).
  # - All: True # To allow everything, uncomment and set All: True.
  - Alter: True
  - Command: True
  - Comment: True
  - Commit: True
  - Create: True
  - Delete: True
  - Describe: True
  - Drop: True
  - Insert: True
  - Merge: True
  - Rollback: True
  - Select: True
  - Transaction: True
  - TruncateTable: True
  - Unknown: False # To allow unknown or unmapped statement types, set Unknown: True.
  - Update: True
  - Use: True

The MCP server uses the Snowflake Python Connector for all authentication and connection methods. Please refer to the official Snowflake documentation for comprehensive authentication options and best practices.

The MCP server honors the RBAC permissions assigned to the specified role (as passed in the connection parameters) or default role of the user (if no role is passed to connect).

Connection parameters can be passed as CLI arguments and/or environment variables. The server supports all authentication methods available in the Snowflake Python Connector, including:

• Username/password authentication
• Key pair authentication
• OAuth authentication
• Single Sign-On (SSO)
• Multi-factor authentication (MFA)

Connection parameters can be passed as CLI arguments and/or environment variables:

The MCP server supports multiple transport mechanisms. For detailed information about MCP transports, see FastMCP Transport Protocols.

# Default stdio transport
uvx snowflake-labs-mcp --service-config-file config.yaml

# HTTP transport with custom endpoint
uvx snowflake-labs-mcp --service-config-file config.yaml --transport streamable-http --endpoint /my-endpoint

# For containers (uses streamable-http on port 9000)
uvx snowflake-labs-mcp --service-config-file config.yaml --transport streamable-http --endpoint /snowflake-mcp

The below server customizations are available when running with sse and streamable-http transports.

Example:

export SNOWFLAKE_MCP_ENDPOINT="/my-mcp"
uvx snowflake-labs-mcp --service-config-file config.yaml --transport streamable-http

The MCP server is client-agnostic and will work with most MCP Clients that support basic functionality for MCP tools and (optionally) resources. Below are examples for local installation. For connecting to containerized deployments, see Connecting MCP Clients to Containers.

To integrate this server with Claude Desktop as the MCP Client, add the following to your app's server configuration. By default, this is located at:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Set the path to the service configuration file and configure your connection method:

{
  "mcpServers": {
    "mcp-server-snowflake": {
      "command": "uvx",
      "args": [
        "snowflake-labs-mcp",
        "--service-config-file",
        "<path_to_file>/tools_config.yaml",
        "--connection-name",
        "default"
      ]
    }
  }
}

Register the MCP server in Cursor by opening Cursor and navigating to Settings -> Cursor Settings -> MCP. Add the below:

{
  "mcpServers": {
    "mcp-server-snowflake": {
      "command": "uvx",
      "args": [
        "snowflake-labs-mcp",
        "--service-config-file",
        "<path_to_file>/tools_config.yaml",
        "--connection-name",
        "default"
      ]
    }
  }
}

Add the MCP server as context in the chat.

For troubleshooting Cursor server issues, view the logs by opening the Output panel and selecting Cursor MCP from the dropdown menu.

Update the fastagent.config.yaml mcp server section with the configuration file path and connection name:

# MCP Servers
mcp:
    servers:
        mcp-server-snowflake:
            command: "uvx"
            args: ["snowflake-labs-mcp", "--service-config-file", "<path_to_file>/tools_config.yaml", "--connection-name", "default"]

For prerequisites, environment setup, step-by-step guide and instructions, please refer to this blog.

Register the MCP server in codex by adding the following to ~/.codex/config.toml

[mcp_servers.mcp-server-snowflake]
command = "uvx"
args = [
    "snowflake-labs-mcp",
    "--service-config-file",
    "<path_to_file>/tools_config.yaml",
    "--connection-name",
    "default"
]

After editing, the snowflake mcp should appear in the output of codex mcp list run from the terminal.

Deploy the MCP server as a container for remote access or production environments. This guide provides step-by-step instructions for both Docker and Docker Compose deployments.

Follow these steps to deploy the MCP server using Docker:

Create a directory for MCP configuration and copy the template:

mkdir -p ${HOME}/.mcp/
cp services/configuration.yaml ${HOME}/.mcp/tools_config.yaml

Edit the configuration file to match your environment:

# Edit the configuration file as needed
# Update service names, database/schema references, and enable desired features
nano ${HOME}/.mcp/tools_config.yaml

Build the Docker image from the provided Dockerfile:

docker build -f docker/server/Dockerfile -t mcp-server-snowflake .

Configure your Snowflake connection parameters. Choose one of the following authentication methods:

Username/Password Authentication:

export SNOWFLAKE_ACCOUNT=<your_account>
export SNOWFLAKE_USER=<your_username>
export SNOWFLAKE_PASSWORD=<your_password>

Key Pair Authentication:

export SNOWFLAKE_ACCOUNT=<your_account>
export SNOWFLAKE_USER=<your_username>
export SNOWFLAKE_PRIVATE_KEY="$(cat <path_to_private_key.p8>)"
export SNOWFLAKE_PRIVATE_KEY_FILE_PWD=<your_key_password>

Start the container with your configuration and environment variables:

For Username/Password Authentication:

docker run -d \
  --name mcp-server-snowflake \
  -p 9000:9000 \
  -e SNOWFLAKE_ACCOUNT=${SNOWFLAKE_ACCOUNT} \
  -e SNOWFLAKE_USER=${SNOWFLAKE_USER} \
  -e SNOWFLAKE_PASSWORD=${SNOWFLAKE_PASSWORD} \
  -v ${HOME}/.mcp/tools_config.yaml:/app/services/tools_config.yaml:ro \
  mcp-server-snowflake

For Key Pair Authentication:

docker run -d \
  --name mcp-server-snowflake \
  -p 9000:9000 \
  -e SNOWFLAKE_ACCOUNT=${SNOWFLAKE_ACCOUNT} \
  -e SNOWFLAKE_USER=${SNOWFLAKE_USER} \
  -e SNOWFLAKE_PRIVATE_KEY="${SNOWFLAKE_PRIVATE_KEY}" \
  -e SNOWFLAKE_PRIVATE_KEY_FILE_PWD=${SNOWFLAKE_PRIVATE_KEY_FILE_PWD} \
  -v ${HOME}/.mcp/tools_config.yaml:/app/services/tools_config.yaml:ro \
  mcp-server-snowflake

Check that the container is running and accessible:

# Check container status
docker ps

# Check container logs
docker logs mcp-server-snowflake

# Test endpoint (should return MCP server info)
curl http://localhost:9000/snowflake-mcp

Follow these steps for a simplified deployment using Docker Compose:

Create the configuration directory and copy the template:

mkdir -p ${HOME}/.mcp/
cp services/configuration.yaml ${HOME}/.mcp/tools_config.yaml

Edit the configuration file to match your environment:

# Update service configurations as needed
nano ${HOME}/.mcp/tools_config.yaml

Configure your Snowflake connection parameters:

export SNOWFLAKE_ACCOUNT=<your_account>
export SNOWFLAKE_USER=<your_username>
# For username/password auth:
export SNOWFLAKE_PASSWORD=<your_password>
# For key pair auth, also set:
# export SNOWFLAKE_PRIVATE_KEY="$(cat <path_to_private_key.p8>)"
# export SNOWFLAKE_PRIVATE_KEY_FILE_PWD=<your_key_password>

Launch the container using Docker Compose:

docker-compose up -d

Check that the services are running:

# Check service status
docker-compose ps

# View logs
docker-compose logs

# Test endpoint
curl http://localhost:9000/snowflake-mcp

Once your MCP server is running in a container, you can connect various MCP clients to it. The connection configuration is the same across all clients - only the configuration format differs.

Connection URL Format:

• Local deployment: http://localhost:9000/snowflake-mcp
• Remote deployment: http://<hostname>:<port>/snowflake-mcp

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-server-snowflake": {
      "url": "http://localhost:9000/snowflake-mcp"
    }
  }
}

Add this to your MCP settings in Cursor (Settings -> Cursor Settings -> MCP):

{
  "mcpServers": {
    "mcp-server-snowflake": {
      "url": "http://localhost:9000/snowflake-mcp"
    }
  }
}

Add this to your fastagent.config.yaml:

# MCP Servers
mcp:
    servers:
        mcp-server-snowflake:
            url: "http://localhost:9000/snowflake-mcp"

Notes:

• For remote deployments, replace localhost:9000 with your server's hostname and port
• Ensure your firewall allows connections on port 9000 (or your configured port)
• For production deployments, consider using HTTPS and proper authentication

Instances of Cortex Agent (in agent_services section), Cortex Search (in search_services section), and Cortex Analyst (in analyst_services section) of the configuration file will be served as tools. Leave these sections blank to omit such tools.

Only Cortex Agent objects are supported in the MCP server. That is, only Cortex Agent objects pre-configured in Snowflake can be leveraged as tools. See Cortex Agent Run API for more details.

Ensure all services have accurate context names for service name, database, schema, etc. Ideal descriptions are both highly descriptive and mutually exclusive.

The semantic_model value in analyst services should be a fully-qualified semantic view OR semantic YAML file in a Snowflake stage:

• For a semantic view: MY_DATABASE.MY_SCHEMA.MY_SEMANTIC_VIEW
• For a semantic YAML file: @MY_DATABASE.MY_SCHEMA.MY_STAGE/my_semantic_file.yaml (Note the @.)

The MCP server includes dozens of tools narrowly scoped to fulfill basic operation management. It is recommended to use Snowsight directly for advanced object management.

The MCP server currently supports creating, dropping, creating or altering, describing, and listing the below object types. To enable these tools, set object_manager to True in the configuration file under other_services.

- Database
- Schema
- Table
- View
- Warehouse
- Compute Pool
- Role
- Stage
- User
- Image Repository

Please note that these tools are also governed by permissions captured in the configuration file under sql_statement_permissions. Object management tools to create and create or alter objects are governed by the Create permission. Object dropping is governed by the Drop permission.

It is likely that more actions and objects will be included in future releases.

The general SQL tool will provide a way to execute generic SQL statements generated by the MCP client. Users have full control over the types of SQL statement that are approved in the configuration file.

Listed in the configuration file under sql_statement_permissions are sqlglot expression types. Those marked as False will be stopped before execution. Those marked with True will be executed (or prompt the user for execution based on the MCP client settings).

To enable the SQL execution tool, set query_manager to True in the configuration file under other_services. To allow all SQL expressions to pass the additional validation, set All to True.

Not all Snowflake SQL commands are mapped in sqlglot and you may find some obscure commands have yet to be captured in the configuration file. Setting Unknown to True will allow these uncaptured commands to pass the additional validation. You may also add new expression types directly to honor specific ones.

Below are some examples of sqlglot expression types with accompanying Snowflake SQL command examples:

Several tools support the discovery and querying of Snowflake Semantic Views and their components. Semantic Views can be listed and described. In addition, you can list their metrics and dimensions. Lastly, you can query Semantic Views directly.

To enable these tools, set semantic_manager to True in the configuration file under other_services.

The MCP Inspector is a powerful debugging tool that provides a web interface to interact with your MCP server directly. It's essential for troubleshooting configuration issues, testing tools, and validating your setup.

Launch the inspector with your MCP server configuration:

npx @modelcontextprotocol/inspector uvx snowflake-labs-mcp --service-config-file <path_to_file>/tools_config.yaml --connection-name "default"

Once launched, the inspector will open a web interface where you can:

1. View Available Tools: See all MCP tools loaded from your configuration file
2. Test Tool Execution: Call tools directly with custom parameters to verify they work
3. Inspect Resources: View any resources exposed by the server
4. Debug Connection Issues: See detailed error messages if connection fails
5. Validate Configuration: Ensure your service configurations are properly loaded

Configuration File Issues:

• If tools don't appear, check your tools_config.yaml syntax
• Verify that service names and database/schema references are correct
• Ensure other_services are set to True for the tool groups you want

Connection Problems:

• Verify your Snowflake connection parameters are correct
• Check that your role has the necessary permissions for the services you've configured
• For key pair authentication, ensure your private key is properly formatted

Tool Execution Errors:

• Use the inspector to test individual tools with known-good parameters
• Check the server logs for detailed error messages
• Verify that the underlying Snowflake objects (databases, schemas, services) exist

Using Cursor MCP Logs:

• Open Output panel in Cursor
• Select "Cursor MCP" from the dropdown
• View real-time logs as you interact with the MCP server

Command Line Debugging: Add verbose logging to see detailed connection and execution information:

uvx snowflake-labs-mcp --service-config-file <path_to_file>/tools_config.yaml --connection-name "default" --verbose

• The MCP server supports all connection methods supported by the Snowflake Python Connector. See Connecting to Snowflake with the Python Connector for more information.

• While LLMs' support for more tools will likely grow, you can hide tool groups by setting them to False in the configuration file. Only listed Cortex services will be made into tools as well.

• Yes. Pass it to the CLI flag --password or set as environment variable SNOWFLAKE_PASSWORD.

• The MCP server is intended to be used as one part of the MCP ecosystem. Think of it as a collection of tools. You'll need an MCP Client to act as an orchestrator. See the MCP Introduction for more information.

• All tools in this MCP server are managed services, accessible via REST API. No separate remote service deployment is necessary. Instead, the current version of the server is intended to be started by the MCP client, such as Claude Desktop, Cursor, fast-agent, etc. By configuring these MCP client with the server, the application will spin up the server service for you. Future versions of the MCP server may be deployed as a remote service in the future.

• If using a Programmatic Access Tokens, note that they do not evaluate secondary roles. When creating them, please select a single role that has access to all services and their underlying objects OR select any role. A new PAT will need to be created to alter this property.

• You may add multiple instances of both services. The MCP Client will determine the appropriate one(s) to use based on the user's prompt.

• If your account name contains underscores, try using the dashed version of the URL.
  • Account identifier with underscores: acme-marketing_test_account
  • Account identifier with dashes: acme-marketing-test-account

• Deploy using Docker or Docker Compose as shown in the Container Deployment section. The containerized server runs on HTTP and can handle multiple concurrent MCP client connections. Configure your environment variables for authentication and mount your configuration file as a read-only volume.

• Verify that your configuration file syntax is correct (use MCP Inspector to validate)
• Ensure the service names, database names, and schema names match exactly what exists in Snowflake
• Check that your role has access to the specified databases and schemas
• Confirm that the Cortex services actually exist in the specified locations

• Yes. You can set environment variables differently for each deployment, use different connection names in your connections.toml file, or pass different CLI arguments. The server supports all Snowflake Python Connector authentication methods including username/password, key pairs, OAuth, and SSO.

• Use the sql_statement_permissions section in your configuration file. Set specific statement types to True (allow) or False (deny). For maximum security, only enable the statement types you actually need. Set Unknown to False to block unrecognized statement types.

• Initial startup can take a few seconds as the server connects to Snowflake and validates your configuration. Subsequent tool calls should be much faster. If startup takes more than 30 seconds, check your network connection to Snowflake and verify your authentication credentials.

Please add issues to the GitHub repository.