How to Use the Apache Superset MCP in LangChain

Q: Can a LangChain agent run write queries on Apache Superset?

No, because the executesqlquery tool is bound by the read-only permissions of your Superset database user. Your LangChain agent can read and analyze data, but it won't accidentally drop tables or modify your metrics.

Q: Why does my LangChain trace show slow Apache Superset tool calls?

Heavy queries run through executesqlquery depend entirely on your target database speed. You can monitor the exact latency of each Superset tool execution directly inside your LangSmith dashboard to find bottlenecks.

Q: Can LangChain combine database tools with other APIs?

Yes, that is where LangChain shines. The output from getchartdetails can be passed directly to a Slack tool or a vector database tool within the same execution chain.

Run SQL queries and pull Superset BI metadata directly into your LangChain reasoning loops.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain SQL execution with LangChain

The `execute_sql_query` tool lets your LangChain agent run raw SQL against your connected Superset databases. Your LangChain routing agent can call this MCP tool to inspect the database schema using `list_databases` first, then write and run the exact query it needs to satisfy the current chain step. Since LangChain passes outputs from one step to the next, the raw rows returned from your SQL Lab query feed straight into your subsequent chain steps. You can track this entire query flow in LangSmith to see exactly how your LangChain agent formulated the Superset SQL statement.

Trace dashboard discovery via LangChain MCP Server

The `list_dashboards` tool exposes every active Apache Superset dashboard to your LangChain routing agent. This allows the LangChain framework to dynamically decide which Superset dashboard contains the metrics it needs before digging deeper. Once the LangChain agent identifies the right dashboard, it triggers `get_dashboard_details` to inspect the layout and slice metadata. You get a clear, traceable history of how your LangChain agent navigated your Superset BI setup inside LangSmith.

Extract raw chart data for agent chains

The `list_charts` tool gives your LangChain agent a direct line of sight into all your saved Superset visualizations. Instead of guessing chart IDs, the LangChain agent pulls the full list and matches them against active chain variables. The LangChain agent then executes `get_chart_details` to extract the underlying Superset data structure. This feeds clean Superset chart data directly into your LLM chain, letting your LangChain agent write accurate summaries based on actual visualization configurations.

Setup guide

Set up Apache Superset 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 Apache Superset 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({
    "apache-superset-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 Apache Superset 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 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 LangChain

You configure the credentials once in your Vinkius dashboard. The LangChain MCP adapter connects to the single secure endpoint, so your python code never exposes raw database or Superset passwords.

No, because the `execute_sql_query` tool is bound by the read-only permissions of your Superset database user. Your LangChain agent can read and analyze data, but it won't accidentally drop tables or modify your metrics.

Heavy queries run through `execute_sql_query` depend entirely on your target database speed. You can monitor the exact latency of each Superset tool execution directly inside your LangSmith dashboard to find bottlenecks.

Yes, that is where LangChain shines. The output from `get_chart_details` can be passed directly to a Slack tool or a vector database tool within the same execution chain.

Your SQL query results are processed in memory within the Vinkius V8 sandbox. We never store the tabular data returned by `execute_sql_query`, keeping your raw database records isolated from persistent storage.

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