Does this work with self-hosted Metabase instances?

Yes. You just need to provide your full Metabase Base URL (e.g., http://metabase.your-domain.com). Your agent will connect securely to your private instance using your API Key.

Can I see the SQL code behind a specific Metabase card through my agent?

Yes. Use the `get_card` tool with a specific Card ID. Your agent will retrieve the complete mapping logic, exposing the underlying SQL query (if it's a SQL question) or the structural query parameters used to generate the visualization.

Can my agent list all databases currently connected to Metabase?

Absolutely. Use the `list_databases` tool to identify all physical data warehouse integrations. Your agent will report the database names, types (e.g., PostgreSQL, Snowflake), and internal IDs available for querying.

Metabase (Business Intelligence & Analytics) MCP Server for Pydantic AI 7 tools — connect in under 2 minutes

Name: Metabase (Business Intelligence & Analytics)
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 7 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Metabase (Business Intelligence & Analytics) through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Metabase (Business Intelligence & Analytics) "
            "(7 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Metabase (Business Intelligence & Analytics)?"
    )
    print(result.data)

asyncio.run(main())

Metabase (Business Intelligence & Analytics)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Metabase (Business Intelligence & Analytics) MCP Server

Connect your Metabase instance to any AI agent and take full control of your enterprise business intelligence, data visualizations, and reporting through natural conversation.

Pydantic AI validates every Metabase (Business Intelligence & Analytics) tool response against typed schemas, catching data inconsistencies at build time. Connect 7 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Dashboard Orchestration — List all managed reporting panels and retrieve detailed layout matrices, including specific card mappings and filter structures directly from your agent
Question & Card Audit — Access visual 'Cards' to retrieve the underlying SQL logic or visualization definitions driving your key business metrics securely
Global Content Search — Execute cross-platform searches to identify Dashboards, Cards, or Data tables matching specific keywords across your entire Metabase instance
Collection Navigation — Explore hierarchical BI Collections (folders) to understand your reporting taxonomy and organizational data boundaries natively
Database Inventory — Enumerate physical data warehouse connections and raw table mappings available for querying within your Metabase environment
Metadata Inspection — Deep-dive into specific Dashboard or Card IDs to retrieve precise JSON representations and chronological data insights instantly

The Metabase (Business Intelligence & Analytics) MCP Server exposes 7 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Metabase (Business Intelligence & Analytics) to Pydantic AI via MCP

Follow these steps to integrate the Metabase (Business Intelligence & Analytics) MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 7 tools from Metabase (Business Intelligence & Analytics) with type-safe schemas

Why Use Pydantic AI with the Metabase (Business Intelligence & Analytics) MCP Server

Pydantic AI provides unique advantages when paired with Metabase (Business Intelligence & Analytics) through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Metabase (Business Intelligence & Analytics) integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Metabase (Business Intelligence & Analytics) connection logic from agent behavior for testable, maintainable code

Metabase (Business Intelligence & Analytics) + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Metabase (Business Intelligence & Analytics) MCP Server delivers measurable value.

Type-safe data pipelines: query Metabase (Business Intelligence & Analytics) with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Metabase (Business Intelligence & Analytics) tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Metabase (Business Intelligence & Analytics) and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Metabase (Business Intelligence & Analytics) responses and write comprehensive agent tests

Metabase (Business Intelligence & Analytics) MCP Tools for Pydantic AI (7)

These 7 tools become available when you connect Metabase (Business Intelligence & Analytics) to Pydantic AI via MCP:

get_card

Fetch explicit mapping logic behind a specific BI Card

get_dashboard

Get comprehensive Metabase Dashboard layout matrices

list_cards

Returns heavy lists. List raw questions (cards) parsed inside Metabase

list_collections

List structural BI Collections (folders)

list_dashboards

List dashboards mapped in the Metabase BI platform

list_databases

List physical Database integrations parsed by Metabase

search_content

Search global reporting entities across Metabase

Example Prompts for Metabase (Business Intelligence & Analytics) in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Metabase (Business Intelligence & Analytics) immediately.

"List the last 5 dashboards created in my Metabase instance"

"Search for any Metabase content related to 'Revenue'"

"Show me the configuration for card ID '654'"

Troubleshooting Metabase (Business Intelligence & Analytics) MCP Server with Pydantic AI

Common issues when connecting Metabase (Business Intelligence & Analytics) to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Metabase (Business Intelligence & Analytics) + Pydantic AI FAQ

Common questions about integrating Metabase (Business Intelligence & Analytics) MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Metabase (Business Intelligence & Analytics) MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.