metabase

Query Metabase databases with native SQL and retrieve JSON results.

3|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/PIGzyj233/metabase-cli --skill metabase
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: metabase
Source: https://github.com/PIGzyj233/metabase-cli/tree/main
Command: npx skills add https://github.com/PIGzyj233/metabase-cli --skill metabase

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Query Metabase data from the terminal, enabling AI agents to run native SQL, view saved cards/reports, and explore database structures without leaving the AI workflow.

Core Features & Use Cases

  • Discover databases, schemas, and tables to understand available data sources.
  • Execute native SQL queries against Metabase and retrieve results in JSON for AI agents.
  • View, filter, and run saved cards/reports (questions) with optional parameter/template tag resolution.
  • Explore database metadata across databases, schemas, tables, and fields to build a data understanding.

Quick Start

Authenticate to Metabase and start running native SQL queries from the CLI.

Frequently Asked Questions about metabase

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query Metabase from the CLI for an AI agent?

Query Metabase from the CLI by using a lightweight API client to execute native SQL and retrieve JSON output. This enables AI agents to access data, run saved cards, and browse metadata directly from the terminal workflow.

Can AI agents run native SQL queries and view saved cards in Metabase?

Yes, AI agents can run native SQL queries and view saved cards in Metabase. The CLI executes queries and runs saved questions with optional parameter resolution, returning results formatted as JSON optimized for agent parsing.

How do I browse database metadata and schemas in Metabase for AI workflows?

Browse database metadata in Metabase by discovering databases, schemas, tables, and fields. This structural exploration helps AI agents understand available data sources and build a data understanding without leaving the terminal.

What is the best way to manage Metabase API tokens for CLI data analytics?

Manage Metabase API tokens for CLI data analytics using YAML-based config and token management. This lightweight setup authenticates the agent to Metabase, enabling seamless query execution and metadata retrieval.

Does querying Metabase from the terminal support pagination for large datasets?

Yes, querying Metabase from the terminal supports pagination for large datasets. The CLI implementation includes pagination metadata on stderr, ensuring the JSON output remains clean and optimized for AI agent parsing.

Are there limitations to executing Metabase SQL queries via CLI for AI agents?

Executing Metabase SQL queries via CLI requires handling pagination metadata output on stderr rather than stdout. This design ensures the primary JSON results remain optimized for agent parsing without structural interference.