How to Use the Metabase (Business Intelligence & Analytics) MCP in Pydantic AI

Q: How do I configure Metabase (Business Intelligence & Analytics) with Pydantic AI?

Install pydantic-ai-slimmcp and initialize MCPToolset with your Vinkius HTTP URL. Pass this toolset into the Agent constructor to give your model immediate access to tools like listdatabases for safe database schema checks.

Q: How are physical database connection details secured in this setup?

When calling listdatabases, physical database integration metadata is retrieved through secure, single-token Vinkius authentication. No raw database credentials or passwords are ever exposed to the AI client or stored inside the MCP Server runtime environment.

Query Metabase BI endpoints with type-safe runtime validation using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

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

Create your Vinkius account to connect Metabase (Business Intelligence & Analytics) to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Metabase (Business Intelligence & Analytics) with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Metabase dashboard layouts in Pydantic AI

The `get_dashboard` tool fetches layout matrices from Metabase and feeds them directly into your Pydantic AI agent. The framework validates this incoming visual structure against strict Pydantic models at runtime, preventing broken Metabase layouts from crashing your application. Before pulling specific dashboard details, your Pydantic AI agent can use `list_dashboards` to get a validated list of all available Metabase reports. If the Metabase API structure changes, Pydantic AI raises a validation error immediately rather than letting your code fail silently.

Type-safe Metabase search across this MCP Server

The `search_content` tool queries your entire Metabase BI setup to find cards, dashboards, and collections. When integrated with Pydantic AI, the search results from this MCP Server are parsed into type-safe models, making it easy to build reliable data-discovery pipelines. Your Pydantic AI agent can safely inspect Metabase folders using `list_collections` to verify user access rights. This guarantees that your automated Pydantic AI workflows only process properly structured Metabase collection metadata.

Parse Metabase visual questions with Pydantic AI validation

The `get_card` tool retrieves the exact mapping logic and query parameters behind your saved Metabase questions. Pydantic AI ensures that every SQL statement or GUI filter returned by this Metabase tool conforms to your expected application schema. If you need to scan multiple metrics, the Pydantic AI agent uses `list_cards` to fetch raw Metabase question definitions. The framework's model-agnostic nature lets you pass these validated Metabase structures to OpenAI, Anthropic, or local models without rewriting your parsing logic.

Setup guide

Set up Metabase (Business Intelligence & Analytics) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "metabase-business-intelligence-analytics-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Metabase (Business Intelligence & Analytics) tools.",
)

result = await agent.run("List recent Metabase (Business Intelligence & Analytics) transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Metabase. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Metabase (Business Intelligence & Analytics) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Metabase (Business Intelligence & Analytics) MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]` and initialize `MCPToolset` with your Vinkius HTTP URL. Pass this toolset into the `Agent` constructor to give your model immediate access to tools like `list_databases` for safe database schema checks.

If Metabase changes its visual question schemas, tools like `get_card` will return unexpected fields. Pydantic AI catches this instantly at runtime and throws a validation error, protecting your analytical pipelines from corrupt data.

Yes, Pydantic AI is completely model-agnostic. You can use local LLMs to run tools like `list_cards` and `search_content` as long as the model supports tool calling.

This setup supports both Streamable HTTP and SSE transports. Since the MCP Server runs externally on Vinkius, your Pydantic AI agent connects via a secure web endpoint.

When calling `list_databases`, physical database integration metadata is retrieved through secure, single-token Vinkius authentication. No raw database credentials or passwords are ever exposed to the AI client or stored inside the MCP Server runtime environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript