About Snowflake Cube Server
Snowflake Cube Server is an MCP server for querying data through a Cube semantic layer. It provides data descriptions and returns query results in formats that MCP clients can process.
Key features
- 01Query Cube REST API data
- 02Describe available data
- 03Return results in YAML
- 04Expose results as JSON resources
Use cases
- 01Querying data in a Cube deployment
- 02Formatting or processing query results in an MCP client
MCP support
It exposes the `read_data` and `describe_data` tools, plus data-description and query-result resources, to MCP clients.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMESnowflake Cube Server
MCP Server for Interacting with Cube Semantic Layers
Resources
context://data_description
Contains a description of the data available in the Cube deployment. This is an application controlled version of the describe_data tool.
data://{data_id}
Contains the data returned by a read_data call in JSON format. This resource is meant for MCP clients that wish to format or otherwise process the output of tool calls. See read_data for more.
Tools
read_data
Accepts a query to the Cube REST API and returns the data in YAML along with a unique identifier for the data returned. This identifier can be used to a retrieve a JSON representation of the data from the resource data://{data_id}. See data://{data_id} for more.
describe_data
Describes the data available in the Cube deployment. This is an agentic version of the context://data_description resource.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.