# Metabase MCP Server — 60+ Metabase Tools

> Connect AI assistants to Metabase via MCP with an `npx` runnable server; configure METABASE_URL/API_KEY and optionally limit tools with TOOL_MODE.

## Install

Merge the JSON below into your `.mcp.json`:

## Quick Use

```bash
export METABASE_URL=https://your-metabase-instance.com
export METABASE_API_KEY=your_metabase_api_key
npx @easecloudio/mcp-metabase-server
```

## Intro

Use this MCP server to let an assistant query and manage Metabase analytics with explicit tool filtering and environment-based auth.

Connect AI assistants to Metabase via MCP with an `npx` runnable server; configure METABASE_URL/API_KEY and optionally limit tools with TOOL_MODE.

**Best for:** data teams using Metabase who want an MCP interface for dashboards/cards/databases with optional read-only modes

**Works with:** Node.js + npx, METABASE_URL and METABASE_API_KEY env vars, MCP-capable clients

**Setup time:** ~6–15 minutes (API key + first run)

### Key facts (verified)

- GitHub: 75 stars · 20 forks · pushed 2026-05-14.
- License: MIT · owner avatar + repo URL verified via GitHub API.
- Entrypoint (README-backed): `npx @easecloudio/mcp-metabase-server`.

## Main

- Start with `TOOL_MODE=read` or `essential` to minimize destructive operations while you validate the integration.
- Use a dedicated Metabase API key and rotate it; avoid reusing human admin sessions for automation.
- Log tool calls (dashboard/card/db mutations) so you can audit and roll back unintended changes.

### README excerpt (source)

```text
# Metabase MCP Server

[![npm version](https://img.shields.io/npm/v/@easecloudio/mcp-metabase-server)](https://www.npmjs.com/package/@easecloudio/mcp-metabase-server)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![TypeScript](https://img.shields.io/badge/TypeScript-007ACC?style=flat&logo=typescript&logoColor=white)](https://www.typescriptlang.org/)
[![GitHub](https://img.shields.io/badge/GitHub-easecloudio%2Fmcp--metabase--server-blue)](https://github.com/easecloudio/mcp-metabase-server)

A **Model Context Protocol (MCP) server for Metabase** that gives AI assistants full access to your analytics platform — dashboards, cards, databases, tables, collections, and more.

**Developed and maintained by [EaseCloud](https://easecloud.io)** — cloud-native, AI-driven, and data infrastructure solutions.

## Quick Start

```bash
export METABASE_URL=https://your-metabase-instance.com
export METABASE_API_KEY=your_metabase_api_key
npx @easecloudio/mcp-metabase-server
```

## 64 Tools Available

| Domain | Tools |
|---|---|
| Dashboard Management | 16 |
| Card / Question Management | 14 |
| Database Management | 12 |
```

### FAQ

**Q: How many tools does it expose?**
A: The README lists tool counts by domain and supports filtering via TOOL_MODE.

**Q: Can I run it without global install?**
A: Yes—the README recommends `npx @easecloudio/mcp-metabase-server`.

**Q: How do I keep it safe?**
A: Prefer read-only modes first and use least-privilege API keys for automation.

## Source & Thanks

> Source: https://github.com/easecloudio/mcp-metabase-server
> License: MIT
> GitHub: 75 stars · 20 forks · pushed 2026-05-14


---

<!-- ZH -->

## 快速使用

```bash
export METABASE_URL=https://your-metabase-instance.com
export METABASE_API_KEY=your_metabase_api_key
npx @easecloudio/mcp-metabase-server
```

## 简介

用该 MCP Server 让助手调用 Metabase 分析能力，并通过工具过滤与环境变量鉴权来降低误操作。

用 MCP 把 AI 助手接入 Metabase：可用 `npx` 直接启动服务，配置 `METABASE_URL` 与 `METABASE_API_KEY`，并用 `TOOL_MODE` 控制只读/精简工具面，降低误操作风险。

**适合谁：** 使用 Metabase 的数据团队，希望用 MCP 暴露仪表盘/卡片/数据库等能力，并可选只读模式

**可搭配：** Node.js + npx，环境变量 `METABASE_URL` / `METABASE_API_KEY`，支持 MCP 的客户端

**上手时间：** 约 6–15 分钟（创建 API key + 首次运行）

### 关键事实（已验证）

- GitHub：75 stars · 20 forks · 最近更新 2026-05-14。
- 许可证：MIT（GitHub API 已验证仓库 URL / 头像等基础信息）。
- 入口命令（基于 README）：`npx @easecloudio/mcp-metabase-server`。

## 主要内容

- 建议先用 `TOOL_MODE=read` 或 `essential`，把破坏性操作降到最低，再逐步放开。
- 使用专用的 Metabase API key 并定期轮换，避免复用个人管理员会话做自动化。
- 对工具调用做日志留痕（尤其是变更类操作），方便审计与回滚误修改。

### README 摘录（来源）

```text
# Metabase MCP Server

[![npm version](https://img.shields.io/npm/v/@easecloudio/mcp-metabase-server)](https://www.npmjs.com/package/@easecloudio/mcp-metabase-server)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![TypeScript](https://img.shields.io/badge/TypeScript-007ACC?style=flat&logo=typescript&logoColor=white)](https://www.typescriptlang.org/)
[![GitHub](https://img.shields.io/badge/GitHub-easecloudio%2Fmcp--metabase--server-blue)](https://github.com/easecloudio/mcp-metabase-server)

A **Model Context Protocol (MCP) server for Metabase** that gives AI assistants full access to your analytics platform — dashboards, cards, databases, tables, collections, and more.

**Developed and maintained by [EaseCloud](https://easecloud.io)** — cloud-native, AI-driven, and data infrastructure solutions.

## Quick Start

```bash
export METABASE_URL=https://your-metabase-instance.com
export METABASE_API_KEY=your_metabase_api_key
npx @easecloudio/mcp-metabase-server
```

## 64 Tools Available

| Domain | Tools |
|---|---|
| Dashboard Management | 16 |
| Card / Question Management | 14 |
| Database Management | 12 |
```

### FAQ

**Q: 它会暴露多少工具？**
A: README 按领域列出了工具数量，并支持用 TOOL_MODE 进行过滤。

**Q: 需要全局安装吗？**
A: 不需要；README 推荐直接 `npx @easecloudio/mcp-metabase-server`。

**Q: 如何更安全？**
A: 优先只读模式 + 最小权限 API key，并对变更类调用做审计记录。

## 来源与感谢

> 来源：https://github.com/easecloudio/mcp-metabase-server
> 许可证：MIT
> GitHub：75 stars · 20 forks · 最近更新 2026-05-14



---
Source: https://tokrepo.com/en/workflows/metabase-mcp-server-60-metabase-tools
Author: MCP Hub