cube-mcp-server
Verified Safeby cubedevinc
Overview
Provides a Model Context Protocol (MCP) server for real-time analytics and data exploration via chat with Cube's AI agent.
Installation
npx @cube-dev/mcp-serverEnvironment Variables
- CUBE_API_KEY
- CUBE_TENANT_NAME
- CUBE_DEPLOYMENT_ID
- CUBE_AGENT_ID
- USER_ID
Security Notes
The server correctly loads all sensitive credentials (API keys, tenant names, deployment IDs, agent IDs, user IDs) from environment variables, avoiding hardcoding. It uses standard Node.js `fetch` for network requests and `JSON.parse` for streaming data, which are generally safe. There is no usage of 'eval' or other inherently dangerous functions. Security relies on the secure handling of environment variables by the user and the underlying security of the Cube AI platform's APIs and authentication flow.
Similar Servers
mcp-server-elasticsearch
Connects Model Context Protocol (MCP) clients to Elasticsearch, enabling natural language interaction with Elasticsearch indices and data.
tmcp
Build Model Context Protocol (MCP) servers for AI agents to interact with external tools and data sources, enabling LLMs to access context and perform actions.
MCP-Agent
The MCP Agent serves as an AI integration tool capable of discovering, connecting to, and interacting with Model Context Protocol (MCP) servers to utilize their available tools, prompts, and resources autonomously.
atlantis-mcp-server
Provides a local Model Context Protocol (MCP) server for dynamically hosting and managing Python functions and third-party MCP servers, primarily for AI agent interaction, with optional cloud integration.