How to Use the data.world MCP in LlamaIndex

Q: Can I run semantic search across data.world assets with LlamaIndex?

Yes, you can. Your agent runs full-text queries using the searchcatalog MCP tool and then applies LlamaIndex's reranking algorithms to find the most relevant datasets for your user's prompt.

Q: How do I handle private data.world datasets in LlamaIndex?

The listmydatasets tool respects your account-level permissions. LlamaIndex only indexes the datasets that your authenticated profile has rights to view, keeping restricted data private.

Q: Can I use this to feed dataset schemas into a LlamaIndex query router?

Yes. You can use getdatasetdetails to fetch the file layout and tags, then feed that structural info to a router query engine to decide which database index to query.

Index data.world catalog metadata 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 data.world MCP to LlamaIndex

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build LlamaIndex RAG Engines over the data.world Catalog

The `search_catalog` tool allows your LlamaIndex pipeline to query your organization's data assets and ingest the results as Document objects. Your agent indexes these search results in a vector store, enabling semantic queries over your metadata. This integration connects your live catalog to your local index. Instead of relying on static exports, your LlamaIndex RAG system fetches real-time dataset tags and descriptions to answer user questions about available data assets.

Automated Project Context Ingestion

Your pipeline uses `list_project_insights` to retrieve documented findings and visualizations directly from your active workspaces via MCP. LlamaIndex converts these insights into text nodes, linking them to your broader organizational knowledge base. When users ask about project outcomes, the agent retrieves these nodes to ground its answers. This ensures your LLM references actual project status data instead of fabricating project milestones.

Schema-Aware Query Construction

The `get_dataset_details` tool provides the exact field definitions, file listings, and licenses your LlamaIndex query engine needs to construct accurate prompts. The tool feeds this schema data directly into the system prompt before generating SQL. This approach eliminates syntax errors during text-to-SQL tasks. By checking the official schema details first, the engine knows which tables and columns actually exist in your target dataset.

Setup guide

Set up data.world 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 data.world 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 data.world tools.",
)
response = await agent.run("List recent data.world 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 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 LlamaIndex

The framework uses the MCP tool spec to wrap the tools. When your agent calls `list_my_datasets`, LlamaIndex captures the returned JSON, converts it into document nodes, and inserts them into your vector store.

Yes, you can. Your agent runs full-text queries using the `search_catalog` MCP tool and then applies LlamaIndex's reranking algorithms to find the most relevant datasets for your user's prompt.

The `list_my_datasets` tool respects your account-level permissions. LlamaIndex only indexes the datasets that your authenticated profile has rights to view, keeping restricted data private.

Yes. You can use `get_dataset_details` to fetch the file layout and tags, then feed that structural info to a router query engine to decide which database index to query.

Vinkius executes all tool calls inside a zero-trust, ephemeral sandbox. Your project insights and file listings are fetched via HTTPS directly to your LlamaIndex instance, with no middleman caching or storing your structural data.

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