How to Use the Apache Superset MCP in LlamaIndex

Q: How does LlamaIndex index Apache Superset chart metadata?

Your agent calls the MCP tool listcharts and converts the JSON payload into document nodes. LlamaIndex then embeds these nodes into your vector store, allowing semantic search over your Superset visualizations.

Q: Can I use LlamaIndex to search dashboards?

Yes, by indexing the output of listdashboards. The LlamaIndex agent can search the local index for specific dashboard names and then call getdashboarddetails to retrieve the layout.

Q: Where does my chart metadata go during indexing?

The chart details retrieved by getchartdetails flow directly to your local LlamaIndex application. Vinkius operates a zero-trust sandbox, meaning we never store your BI metadata or SQL query results on our servers.

Index Apache Superset metadata and SQL results directly into LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apache Superset MCP to LlamaIndex

Create your Vinkius account to connect Apache Superset 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 Apache Superset with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index BI metadata into LlamaIndex

The `list_datasets` tool exposes all your Superset dataset structures so LlamaIndex can index them. Your LlamaIndex agent searches this MCP tool output to find exactly which Superset tables hold the data needed for a user's query. By combining this with `list_databases`, your LlamaIndex RAG pipeline builds a semantic map of your entire Superset database warehouse. LlamaIndex queries this local index instead of hitting the Superset API repeatedly.

Query charts using LlamaIndex MCP Server

The `list_charts` tool allows your LlamaIndex agent to pull active Superset charts and index their metadata. This means the LlamaIndex agent can semantically search for existing Superset visualizations instead of writing new SQL queries from scratch. When a user asks about sales trends, LlamaIndex searches the index, finds the Superset chart, and runs `get_chart_details` to pull the precise underlying metrics. You get grounded answers directly from your active Superset charts inside your LlamaIndex application.

Ground RAG responses with live SQL queries

The `execute_sql_query` tool lets your LlamaIndex agent run queries to fetch fresh data for its vector store. This ensures your LlamaIndex RAG pipeline is grounded in real-time Superset database records rather than stale documents. The LlamaIndex agent reads the Superset query results, parses them into document nodes, and indexes them on the fly. Your LlamaIndex LLM then answers questions using actual data pulled straight from your Superset SQL Lab connection.

Setup guide

Set up Apache Superset 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 Apache Superset 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 Apache Superset tools.",
)
response = await agent.run("List recent Apache Superset 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 Apache Superset. 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 Apache Superset 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 Apache Superset MCP in LlamaIndex

Your agent calls the MCP tool `list_charts` and converts the JSON payload into document nodes. LlamaIndex then embeds these nodes into your vector store, allowing semantic search over your Superset visualizations.

Yes, you configure that by limiting the user permissions on the Superset side. The `list_datasets` tool will only return the tables that your configured Superset service account has access to view.

LlamaIndex handles caching at the index level. If you index the output of `execute_sql_query`, the agent will query your vector store first before calling the Superset tool again.

Yes, by indexing the output of `list_dashboards`. The LlamaIndex agent can search the local index for specific dashboard names and then call `get_dashboard_details` to retrieve the layout.

The chart details retrieved by `get_chart_details` flow directly to your local LlamaIndex application. Vinkius operates a zero-trust sandbox, meaning we never store your BI metadata or SQL query results on our servers.

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