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

Q: How do I pass Metabase (Business Intelligence & Analytics) metadata through a LangChain multi-step chain?

You call listdashboards to get a list of active boards, then feed those IDs into getdashboard in the next link of your chain. LangChain passes these outputs natively between steps, letting your agent inspect layout configurations dynamically.

Q: Can a LangChain agent search for specific charts using this Metabase (Business Intelligence & Analytics) integration?

Yes, the agent uses searchcontent to find cards or collections matching a user's natural language query. From there, it targets specific charts by calling getcard to extract the underlying query logic.

Q: How does LangSmith trace Metabase (Business Intelligence & Analytics) tool calls made by my LangChain agent?

LangSmith logs every single call to listcollections or listcards, showing you the exact JSON payload returned. If your agent fails to find a specific report, you can trace the inputs and outputs to see where the reasoning chain broke.

Stop copying SQL scripts into your LangChain runs. Connect this MCP Server to pull live Metabase dashboards directly.

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 LangChain

Create your Vinkius account to connect Metabase (Business Intelligence & Analytics) to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Executive Reporting Pipelines in LangChain

The `get_dashboard` tool pulls raw layout matrices and card IDs directly into your active LangChain chains. Let's be real — nobody wants to manually copy-paste layout configurations when your agent can inspect them instantly. You feed this structure into downstream steps, using `list_cards` to fetch the specific visual questions that populate those layouts. It replaces fragile, hardcoded scripts with real-time metadata pulled straight from your BI setup.

Trace Multi-Step BI Discoveries with LangSmith

The `search_content` tool lets your LangChain agent find reports across your entire BI instance when a user asks a vague data question. The agent acts on the search results, selecting the best collection to inspect. Because LangChain tracks every step, you see exactly how the agent navigated from `list_collections` to a specific card. You get complete observability into how your agent hunts down metrics, making debugging simple.

Dynamic Database Schema Mapping via LangChain MCP Server

The `list_databases` tool exposes physical database integrations connected to your reporting platform directly to your agent. Your LangChain agent uses this list to understand where your business metrics physically live. Instead of guessing table names, the agent combines this with `get_card` to extract the exact SQL logic behind existing charts. This MCP integration keeps your schema mappings up to date without writing boilerplate code.

Setup guide

Set up Metabase (Business Intelligence & Analytics) MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Metabase (Business Intelligence & Analytics) tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "metabase-business-intelligence-analytics-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Metabase (Business Intelligence & Analytics) transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You call `list_dashboards` to get a list of active boards, then feed those IDs into `get_dashboard` in the next link of your chain. LangChain passes these outputs natively between steps, letting your agent inspect layout configurations dynamically.

Yes, the agent uses `search_content` to find cards or collections matching a user's natural language query. From there, it targets specific charts by calling `get_card` to extract the underlying query logic.

LangSmith logs every single call to `list_collections` or `list_cards`, showing you the exact JSON payload returned. If your agent fails to find a specific report, you can trace the inputs and outputs to see where the reasoning chain broke.

Vinkius manages the session token for you, giving you a single secure endpoint. You just pass this endpoint to your LangChain `MultiServerMCPClient` during setup and the adapter handles the rest.

This MCP server only touches BI metadata, such as SQL query definitions, dashboard layout configurations, and collection folder structures. It never accesses your raw database credentials or the actual rows of data stored in your physical warehouses.

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