Frequently Asked Questions (FAQ) about the Metabase MCP Server

Q: What is the Model Context Protocol (MCP)?

A: MCP is an open protocol that standardizes how applications provide context to Large Language Models (LLMs). It allows AI models to access and interact with external data sources and tools in a structured way.

Q: What is the Metabase MCP Server?

A: The Metabase MCP Server is a specific implementation of the MCP that allows AI agents to connect to and interact with Metabase, a popular open-source business intelligence tool. It provides access to Metabase resources like databases, tables, and dashboards.

Q: What are the benefits of using the Metabase MCP Server?

A: The Metabase MCP Server enables AI-powered data analysis, automated reporting, intelligent decision support, natural language data exploration, and AI-driven alerting, streamlining workflows and enhancing data-driven insights.

Q: What kind of resources can I access through the Metabase MCP Server?

A: You can access Metabase databases, tables, schemas, collections, cards (questions/models), and dashboards, along with detailed metadata for each.

Q: What tools does the Metabase MCP Server provide?

A: It offers tools for listing, reading, executing, and managing Metabase assets, including listing dashboards/cards/databases, getting database/table details, executing queries (SQL, MBQL), and exporting results.

Q: How do I configure the Metabase MCP Server?

A: You configure the server using environment variables such as METABASE_URL, METABASE_USERNAME, and METABASE_PASSWORD to connect to your Metabase instance.

Q: How do I install the Metabase MCP Server?

A: You can install it via Smithery using the command: npx -y @smithery/cli install @traghav/metabase-server --client claude.

Q: What is UBOS and how does the Metabase MCP Server integrate with it?

A: UBOS is a full-stack AI Agent Development Platform that helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents, and create Multi-Agent Systems. The Metabase MCP Server seamlessly integrates with UBOS, allowing you to leverage Metabase data within your AI agent workflows.

Q: Can I execute SQL queries through the Metabase MCP Server?

A: Yes, you can execute native SQL queries against a specified database using the execute_query tool.

Q: Can I export the results of a query in different formats?

A: Yes, the export_query_results tool supports exporting results in CSV, XLSX, JSON, and JSON_API formats.

Q: Can I create, update, and delete cards and dashboards using the server?

A: Yes, the server provides CRUD (Create, Read, Update, Delete) tools for managing cards and dashboards.