Can the AI query databases connected to Superset, such as Presto or Redshift?

Yes. The `execute_sql_query` tool runs queries through Superset's SQL Lab API, which routes them to whichever database engine you have configured — Presto, Redshift, PostgreSQL, and others.

Are dashboard access permissions enforced when using the MCP server?

Yes. All requests are authenticated with your `SUPERSET_ACCESS_TOKEN`, so only the dashboards, charts, and datasets your token has access to will be visible to the AI.

Can the AI run write queries (INSERT, UPDATE, DELETE) via SQL Lab?

It depends on your Superset database connection settings. By default, SQL Lab connections are read-only. Write access must be explicitly enabled per database in the Superset admin panel.

Apache Superset MCP Server for LangChain 7 tools — connect in under 2 minutes

Name: Apache Superset
Availability: InStock
Author: Vinkius

python.langchain.com/docs/integrations/tools/mcp

Built by Vinkius GDPR 7 Tools Framework

LangChain is the leading Python framework for composable LLM applications. Connect Apache Superset through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MultiServerMCPClient({
        "apache-superset": {
            "transport": "streamable_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,
        )
        response = await agent.ainvoke({
            "messages": [{
                "role": "user",
                "content": "Using Apache Superset, show me what tools are available.",
            }]
        })
        print(response["messages"][-1].content)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Apache Superset MCP Server

Empower your conversational AI with deep Business Intelligence access by integrating the Apache Superset MCP connector. Seamlessly navigating complex data ecosystems natively from your LLM text-interface, your agent can comprehensively index your analytical infrastructure—spanning from high-level operational dashboards down to specific raw database connections. Instantly run ad-hoc data investigations utilizing internal SQL Lab queries, retrieve explicit graph metadata, and dynamically aggregate critical business insights without abandoning your development environment.

LangChain's ecosystem of 500+ components combines seamlessly with Apache Superset through native MCP adapters. Connect 7 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.

What you can do

Discover Analytics Surfaces — Audit your entire BI portal intuitively by executing list_dashboards and retrieve exact metric configurations invoking get_dashboard_details.
Graph & Dataset Inspection — Inventory active metrics logic seamlessly via list_charts (or specify via get_chart_details) and map semantic layers dynamically performing list_datasets.
Uncover Data Architectures — Examine exact backend storage clusters accurately parsing data availability via list_databases natively.
Direct SQL Processing — Interface with your central storage matrices seamlessly by generating raw extractions securely via execute_sql_query targeting specific analytic connections.

The Apache Superset MCP Server exposes 7 tools through the Vinkius. Connect it to LangChain in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Apache Superset to LangChain via MCP

Follow these steps to integrate the Apache Superset MCP Server with LangChain.

Install dependencies

Run pip install langchain langchain-mcp-adapters langgraph langchain-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save the code and run python agent.py

Explore tools

The agent discovers 7 tools from Apache Superset via MCP

Why Use LangChain with the Apache Superset MCP Server

LangChain provides unique advantages when paired with Apache Superset through the Model Context Protocol.

The largest ecosystem of integrations, chains, and agents. combine Apache Superset MCP tools with 500+ LangChain components

Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step

LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging

Memory and conversation persistence let agents maintain context across Apache Superset queries for multi-turn workflows

Apache Superset + LangChain Use Cases

Practical scenarios where LangChain combined with the Apache Superset MCP Server delivers measurable value.

RAG with live data: combine Apache Superset tool results with vector store retrievals for answers grounded in both real-time and historical data

Autonomous research agents: LangChain agents query Apache Superset, synthesize findings, and generate comprehensive research reports

Multi-tool orchestration: chain Apache Superset tools with web scrapers, databases, and calculators in a single agent run

Production monitoring: use LangSmith to trace every Apache Superset tool call, measure latency, and optimize your agent's performance

Apache Superset MCP Tools for LangChain (7)

These 7 tools become available when you connect Apache Superset to LangChain via MCP:

execute_sql_query

Provide a database ID and the SQL statement. Executes a SQL query via SQL Lab

get_chart_details

Retrieves details for a specific chart

get_dashboard_details

Retrieves details for a specific dashboard

list_charts

Lists all charts (slices) in Superset

list_dashboards

Lists all available dashboards in Apache Superset

list_databases

Lists connected data source connections

list_datasets

Lists all datasets available for analysis

Example Prompts for Apache Superset in LangChain

Ready-to-use prompts you can give your LangChain agent to start working with Apache Superset immediately.

"List all my Superset dashboards and tell me which one was updated most recently."

"Check our database connections to see if our Postgres 'SalesDB' is active."

"Run a SQL Lab query to show the top 5 product categories by revenue in SalesDB."

Troubleshooting Apache Superset MCP Server with LangChain

Common issues when connecting Apache Superset to LangChain through the Vinkius, and how to resolve them.

MultiServerMCPClient not found

Install: pip install langchain-mcp-adapters

Apache Superset + LangChain FAQ

Common questions about integrating Apache Superset MCP Server with LangChain.

How does LangChain connect to MCP servers?

Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.

Which LangChain agent types work with MCP?

All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.