Metabase
Metabase includes a built-in Model Context Protocol (MCP) server that lets AI clients connect directly to a Metabase instance. It uses the Streamable HTTP transport and builds on Metabase's Agent API to expose tools for searching, exploring, querying, and visualizing data — all scoped to the connecting user's permissions.
README
Metabase
Metabase is the easy, open-source way for everyone in your company to ask questions and learn from data.

Get started
The easiest way to get started with Metabase is to sign up for a free trial of Metabase Cloud.
You get expert support, backups, upgrades, an SMTP server, SSL certificate, SoC2 Type 2 security auditing, and more (plus your money goes toward improving a major open-source project). Check out our quick overview of cloud vs self-hosting. If you need to, you can always switch to self-hosting Metabase at any time (or vice versa).
Key Features
- Set up in five minutes (we're not kidding), or have us host Metabase for you so you don't even need to think about it.
- Let anyone on your team ask questions without knowing SQL.
- Use the SQL editor for more complex queries.
- Ask AI: Metabot gives you answers you can trust, helps you write queries, and more. Or build your own AI agent to query your data.
- Build handsome, interactive dashboards with filters, auto-refresh, fullscreen, custom click behavior, and more.
- Use documents for long-form data analysis, and invite people to comment.
- Transform raw data into analytics-ready tables, track down broken dependencies, and define canonical metrics in Metabase's Data Studio.
- Set up alerts on your data, or schedule dashboard subscriptions to email, Slack, or even a webhook.
- Curate content in a Library, and version your work with Git.
- Embed Metabase in your app, with components for charts, dashboards, data browser, AI chat, and more. You can even put an entire Metabase in your app.
- Set granular permissions that work for both internal teams and embedded analytics, whether you co-locate your customer data, or give each customer their own database.
- Dark mode, content translations, and way more stuff than we can list here.
Take a tour of Metabase.
Supported databases
Installation
Metabase can be run just about anywhere. Check out our Installation Guides.
Documentation
The Metabase handbook.
Contributing
To contribute to Metabase, see our Developer docs.
Extending Metabase
Hit our API to integrate analytics. Check out our guide, Working with the Metabase API.
Internationalization
We want Metabase to be available in as many languages as possible. See which translations are available and help contribute to internationalization using our project over at Crowdin. You can also check out our policies on translations.
Security Disclosure
See SECURITY.md for details.
License
This repository contains the source code for both the Open Source edition of Metabase, released under the AGPL, as well as the commercial editions of Metabase, which are released under the Metabase Commercial Software License.
See LICENSE.txt for details.
Unless otherwise noted, all files © 2026 Metabase, Inc.
Community
Metabase Experts
If you’d like more technical resources to set up your data stack with Metabase, connect with a Metabase Expert.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.