How to Use the Metabase (Business Intelligence & Analytics) MCP in OpenAI Agents SDK

Q: How do I connect Metabase (Business Intelligence & Analytics) to OpenAI Agents SDK?

Install the openai-agents package and configure MCPServerStreamableHttp with your Vinkius endpoint. Pass this MCP Server instance inside the mcpservers list when initializing your agent. The agent auto-discovers all seven tools like listdashboards instantly.

Q: Can OpenAI Agents SDK handle caching for Metabase (Business Intelligence & Analytics) queries?

Yes, you should set cacheToolsList=True in your server parameters to keep performance high. This prevents the agent from making repeated schema requests to Metabase when running frequent analytical loops.

Q: How does the agent handle complex SQL queries inside Metabase (Business Intelligence & Analytics) using OpenAI Agents SDK?

The agent calls getcard to pull the raw SQL query mapped to a card. The OpenAI Agents SDK then processes this query text or passes it to a specialized SQL analyst agent for deep inspection.

Q: What happens if an agent requests a dashboard that does not exist?

The getdashboard tool returns a clear API error which your agent catches. You can configure handoffs in your Python code to redirect the agent to searchcontent to find a similar dashboard.

Get raw Metabase BI data directly into your OpenAI Agents SDK production flows without manual SQL scripting.

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 OpenAI Agents SDK

Create your Vinkius account to connect Metabase (Business Intelligence & Analytics) to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Metabase dashboards inside OpenAI Agents SDK

The `list_dashboards` tool exposes your entire Metabase dashboard inventory directly to your OpenAI Agents SDK workflow. This lets your OpenAI Agents SDK agent inspect Metabase layouts and map out where specific business metrics live before executing deeper analytical steps. Once the agent locates the right Metabase dashboard, it uses `get_dashboard` to pull down the exact layout matrix. You get clean, structured Metabase visual data for your OpenAI Agents SDK production agents to parse, avoiding the typical mess of scraped visual charts or broken image exports.

Inspect Metabase visual cards via OpenAI Agents SDK guardrails

The `get_card` tool retrieves the explicit SQL logic and visual question definitions powering your Metabase charts. Your OpenAI Agents SDK workflow uses this to let specialized agents inspect raw Metabase analytical queries before presenting final numbers to users. By combining this with `list_cards`, your OpenAI Agents SDK agent can scan through thousands of saved Metabase questions. The built-in safety guardrails in OpenAI's framework ensure the agent only reads allowed Metabase questions without executing arbitrary, unverified database queries.

Search Metabase folders with this MCP Server

The `search_content` tool runs global queries across all your Metabase collections, cards, and dashboards. Your OpenAI Agents SDK system uses this MCP Server to locate specific Metabase reports on the fly when users ask vague questions about revenue or churn. To keep things organized, the OpenAI Agents SDK agent calls `list_collections` and `list_databases` to map out the underlying Metabase data sources. This gives your OpenAI Agents SDK multi-agent system a clear map of your Metabase collections, allowing safe handoffs between data-discovery agents.

Setup guide

Set up Metabase (Business Intelligence & Analytics) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Metabase (Business Intelligence & Analytics) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Metabase (Business Intelligence & Analytics) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Metabase (Business Intelligence & Analytics) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Metabase (Business Intelligence & Analytics) Agent",
            instructions="You have access to Metabase (Business Intelligence & Analytics) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the `openai-agents` package and configure `MCPServerStreamableHttp` with your Vinkius endpoint. Pass this MCP Server instance inside the `mcp_servers` list when initializing your agent. The agent auto-discovers all seven tools like `list_dashboards` instantly.

Yes, you should set `cacheToolsList=True` in your server parameters to keep performance high. This prevents the agent from making repeated schema requests to Metabase when running frequent analytical loops.

The agent calls `get_card` to pull the raw SQL query mapped to a card. The OpenAI Agents SDK then processes this query text or passes it to a specialized SQL analyst agent for deep inspection.

The `get_dashboard` tool returns a clear API error which your agent catches. You can configure handoffs in your Python code to redirect the agent to `search_content` to find a similar dashboard.

All communication runs through a zero-trust, ephemeral V8 isolate sandbox on Vinkius. Your actual database credentials, SQL query strings, and dashboard layout matrices are never stored, ensuring this MCP Server keeps your core BI metadata private.

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