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

Q: How do I index my Metabase (Business Intelligence & Analytics) dashboards into LlamaIndex?

You call listdashboards to fetch the metadata, then load the text representation into your LlamaIndex document store. From there, you vector-index the layouts so your agent can quickly find dashboards matching user queries.

Q: Can LlamaIndex query raw SQL from Metabase (Business Intelligence & Analytics) cards?

Yes, the agent uses getcard to pull the exact SQL mapping logic behind any specific visual question. It parses this metadata to understand how metrics are calculated, avoiding LLM hallucinations about your schema.

Q: How do I prevent my LlamaIndex agent from hitting rate limits on Metabase (Business Intelligence & Analytics)?

You should index the outputs of listcards and listcollections into a local vector store first. This lets your agent run semantic searches against your local index instead of polling the live API for every query.

Index your Metabase dashboard layouts and SQL card queries directly into LlamaIndex vector stores using this MCP Server.

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 LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Construct a BI Knowledge Base in LlamaIndex

The `list_cards` tool retrieves the raw visual questions parsed inside your BI setup so LlamaIndex can index them. Right. So, instead of guessing metrics, your agent gets a searchable local vector store of your actual reports. When users ask questions, your agent queries this index rather than guessing metrics. It combines these results with `get_card` to pull the exact SQL definitions, keeping your answers grounded in real data.

Semantic Search Across Your BI Collection Folders

The `list_collections` tool fetches your structural folders to map how your team organizes its data assets. LlamaIndex uses this structural map to route user queries to the correct department folders. Your agent uses `search_content` to find matching reports across these collections. This keeps your RAG pipeline focused on verified corporate dashboards instead of raw, unorganized database tables.

Expose Active Dashboards to LlamaIndex MCP Server Agents

The `list_dashboards` tool extracts your live dashboard list, making it immediately queryable by your LlamaIndex agents. The agent uses this list to find out which dashboards are already built. Once found, the agent calls `get_dashboard` to pull the exact layout matrices. This prevents duplicate dashboard creation by letting your agent show users existing charts that already answer their questions.

Setup guide

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

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Metabase (Business Intelligence & Analytics) MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Metabase (Business Intelligence & Analytics) tools.",
)
response = await agent.run("List recent Metabase (Business Intelligence & Analytics) data")

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 LlamaIndex

You call `list_dashboards` to fetch the metadata, then load the text representation into your LlamaIndex document store. From there, you vector-index the layouts so your agent can quickly find dashboards matching user queries.

Yes, the agent uses `get_card` to pull the exact SQL mapping logic behind any specific visual question. It parses this metadata to understand how metrics are calculated, avoiding LLM hallucinations about your schema.

You should index the outputs of `list_cards` and `list_collections` into a local vector store first. This lets your agent run semantic searches against your local index instead of polling the live API for every query.

You initialize the MCP client with your Vinkius endpoint, convert it using `McpToolSpec`, and pass the output to your `FunctionAgent`. The adapter automatically maps the schemas so your agent can call them.

The server only reads layout coordinates, folder names, and card SQL queries. It operates in a secure sandbox, ensuring your actual report data and database credentials never leave your local 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