How to Use the data.world MCP in LangChain

Q: Can a LangChain ReAct agent run SQL queries found in my data.world datasets?

Yes, the agent uses listdatasetqueries to pull the exact SQL or SPARQL syntax saved on the platform. It can then pass those query strings to your database chain for execution.

Run multi-step LangChain pipelines that search data.world catalogs and fetch dataset details automatically via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect data.world MCP to LangChain

Create your Vinkius account to connect data.world 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 data.world with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Pipeline Automation

The `list_dataset_queries` tool lets your LangChain agent fetch saved SQL or SPARQL queries directly from your data.world workspace via MCP. Your chains run these queries dynamically, passing the output directly to the next LLM call in your pipeline without hardcoding database connections. By feeding these query definitions into your ReAct agent, you let LangChain decide which parameters to inject based on prior user inputs. The agent inspects the query metadata, passes it through your custom prompt templates, and executes downstream tasks in a single execution run.

Dynamic LangChain Routing via MCP Server Metadata

Using this MCP Server, your LangChain chain calls `get_dataset_details` to verify field definitions and license terms before processing any raw files. This prevents your agents from feeding unauthorized or mismatched schema files into your processing pipelines. You route messages based on the dataset tags and file lists returned by the tool. If a file contains sensitive user identifiers, your LangChain router directs the payload to a sanitization chain before it hits your main model.

Project Activity Auditing

The `list_recent_activity` tool pulls a fresh stream of dataset updates and project contributions directly into your agent's context window. Your LangChain agent parses these logs to build automated daily standup drafts or flag stale datasets. Because LangSmith traces every tool execution, you see exactly when your chain queried data.world activity and how many tokens it consumed. You get full visibility into how your agent maps these activity streams to your team's project milestones.

Setup guide

Set up data.world 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 data.world 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({
    "dataworld-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 data.world 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 data.world. 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 data.world 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 data.world MCP in LangChain

You configure your API token in the Vinkius platform, which injects it into the transport layer. Your LangChain code simply calls the client to access the MCP tools without handling raw keys in your application code.

Yes, the agent uses `list_dataset_queries` to pull the exact SQL or SPARQL syntax saved on the platform. It can then pass those query strings to your database chain for execution.

The client relies on Vinkius to manage connection pooling and API limits. When your LangChain agent calls `search_catalog`, Vinkius handles the request throttling so your chain does not crash during deep searches.

Yes. You register multiple servers in your client configuration. Your LangChain agent can fetch a dataset schema using `get_dataset_details` and immediately compare it with schemas from other active database servers in the same loop.

Every request runs inside an isolated V8 sandbox on Vinkius, meaning your project insights and SQL queries are never exposed to other tenants. Your personal profile attributes fetched via `get_my_profile` remain strictly ephemeral and are destroyed as soon as the session closes.

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