What is metabase-mcp CLAUDE.md?

A project instruction file for a Metabase MCP server, which connects a coding agent to Metabase, a tool for exploring and analyzing data. It describes setup, building, testing, configuration, and server structure.

Use it when installing dependencies, building TypeScript, starting the server, checking types, linting, or running unit and integration tests.

It gives developers one reference for the commands and conventions needed to develop and run the server.

How 1luvc0d3/metabase-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to 1luvc0d3/metabase-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/1luvc0d3/metabase-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/1luvc0d3/metabase-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/1luvc0d3/metabase-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/1luvc0d3/metabase-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/1luvc0d3/metabase-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/1luvc0d3/metabase-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/1luvc0d3/metabase-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/1luvc0d3/metabase-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,534 This file is loaded in full into every session.

When invoked 1,534 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01534	$0.01534
Opus 5.5	$0.00614	$0.00614
Sonnet 5.5	$0.00307	$0.00307
Haiku 4.5	$0.00153	$0.00153

Measured 5d ago against content hash 1e08b1bd5fc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

metabase-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Build and Development Commands

# Install dependencies
npm install

# Build the project (TypeScript to JavaScript)
npm run build

# Watch mode for development
npm run dev

# Start the MCP server
npm start

# Type checking without emitting
npm run type-check

# Linting
npm run lint

Testing Commands

# Run all tests
npm test

# Run only unit tests
npm run test:unit

# Run only integration tests
npm run test:integration

# Run tests in watch mode
npm run test:watch

# Run a single test file
npx vitest run tests/unit/security/sql-guardrails.test.ts

# Run tests matching a pattern
npx vitest run -t "validates SELECT"

Architecture Overview

This is an MCP (Model Context Protocol) server that connects Claude to Metabase for natural language data analysis.

Entry Point and Flow

src/index.ts - Entry point that initializes all components and starts the MCP server
src/config.ts - Zod-validated configuration loading from environment variables
src/tools/index.ts - Tool registration based on server mode (read/write/full)

Authentication

API key authentication via METABASE_API_KEY. The key is passed as X-API-Key header to all Metabase API requests through MetabaseClient.

Core Components

src/client/metabase-client.ts - Metabase REST API wrapper with all CRUD operations
src/client/types.ts - Metabase API types and config interfaces
src/client/llm-service.ts - Anthropic Claude API integration with token budgeting (daily/monthly limits)

Tool Categories (30 total tools)

Category	File	Tools	Description
Read-Only	`src/tools/read-tools.ts`	10	Dashboard, card, database, collection queries
Batch	`src/tools/batch-tools.ts`	1	Parallel execution of multiple read operations
Workflow	`src/tools/workflow-tools.ts`	1	Composable multi-step pipelines with output chaining
DML/Write	`src/tools/write-tools.ts`	10	Create/update/delete cards, dashboards, collections
NLQ	`src/tools/nlq-tools.ts`	4	Natural language to SQL conversion
Insights	`src/tools/insight-tools.ts`	4	Automated data analysis and trends

Read the full file on GitHub · 208 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago Changed · +3 lines · +85 tokens per session 1e08b1bd5fc9
2mo ago First seen · 205 lines · 1,449 tokens per session scan A 77474a87c97c

Subscribe to this mod's changes

metabase-mcp CLAUDE.md is an instructions file published in the GitHub repository 1luvc0d3/metabase-mcp (5 stars, last pushed 6d ago), licensed MIT. It adds 1,534 tokens to every session, about $0.0061 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

anthropic claude data-analysis mcp metabase model-context-protocol

metabase-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
metabase-mcp CLAUDE.md1luvc0d3/metabase-mcp	Instructions file	5	6d ago	MIT	A	1,534	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

metabase-mcp: Instructions file for Claude Code