Snowflake Cube Server

Created By
isaacwassermana year ago
MCP Server for Interacting with Cube Semantic Layers
Overview

what is Snowflake Cube Server?

Snowflake Cube Server is an MCP server designed for interacting with Cube semantic layers, allowing users to access and manipulate data in a structured format.

how to use Snowflake Cube Server?

To use the Snowflake Cube Server, you can send queries to the Cube REST API using the provided tools, such as read_data and describe_data, to retrieve and describe data from the Cube deployment.

key features of Snowflake Cube Server?

  • Interacts with Cube semantic layers for data manipulation
  • Provides tools for reading and describing data
  • Returns data in JSON and YAML formats for easy processing

use cases of Snowflake Cube Server?

  1. Accessing structured data from Cube deployments for analysis.
  2. Integrating with other applications that require data from Cube layers.
  3. Facilitating data exploration and visualization through API calls.

FAQ from Snowflake Cube Server?

  • What types of data can I access with Snowflake Cube Server?

You can access any data available in the Cube deployment that is structured and defined within the semantic layers.

  • Is there a limit to the number of queries I can send?

There may be rate limits depending on your Cube deployment configuration, but generally, you can send multiple queries as needed.

  • Can I use Snowflake Cube Server for real-time data access?

Yes, Snowflake Cube Server is designed to provide timely access to data, depending on the underlying Cube deployment.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
isaacwasserman
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago