How to Use the data.world MCP in OpenAI Agents SDK

Q: How do I initialize the data.world MCP Server in my OpenAI Agents SDK project?

Install the package using pip install openai-agents and configure the HTTP stream. Instantiate MCPServerStreamableHttp with the Vinkius URL, then pass it to your Agent constructor using the mcpservers list.

Q: Can my OpenAI Agents SDK bot search across all my data.world catalogs?

Yes. The agent uses searchcatalog to run full-text queries across titles, descriptions, and tags. This lets the bot discover relevant datasets and projects during a live conversation.

Q: How does the OpenAI Agents SDK handle permissions for data.world resources?

The agent calls getmyprofile to check your account-level permissions and display name. If the agent tries to access a restricted dataset, the Vinkius endpoint enforces your token's read/write limits.

Q: Can I cache the list of data.world tools in the MCP SDK?

Yes, set cacheToolsList=True in your server parameters. This prevents the SDK from repeatedly querying the Vinkius endpoint for tool definitions, reducing latency during agent handovers.

Give your OpenAI Agents SDK bots direct access to data.world datasets, projects, and SQL queries via one secure MCP connection.

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 OpenAI Agents SDK

Create your Vinkius account to connect data.world to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run data.world SQL queries inside OpenAI Agents SDK

`list_dataset_queries` exposes saved SQL and SPARQL queries from your data.world catalog directly to your OpenAI agent. The agent inspects the syntax, pulls the exact query it needs, and executes it without you writing boilerplate API calls. This means your OpenAI Agents SDK production pipelines dynamically fetch data.world query logic during runtime. You get full execution tracing on the OpenAI dashboard, showing exactly when and why the agent triggered the data.world data pull.

Map data.world metadata using this MCP Server

`get_dataset_details` pulls data.world field definitions, files, tags, and license info into your OpenAI agent's context window. Instead of guessing schema shapes, the agent reads the exact structure of your data.world catalog assets before running downstream tasks. Guardrails in the OpenAI Agents SDK validate these data.world asset details before passing them to specialized agents. If a data.world field definition doesn't match your system rules, the handoff stops immediately, preventing broken pipelines.

Track project updates and insights automatically

`list_project_insights` and `get_project_details` let your OpenAI agent monitor active data.world workspaces for new charts and findings using the MCP protocol. Your agent checks the status of linked resources and pulls documented insights to keep external dashboards updated. Because the OpenAI Agents SDK supports multi-agent setups, one agent can watch for updates via `list_recent_activity` while another formats the data.world findings. They coordinate tasks using live metadata pulled directly from your data.world project workspace.

Setup guide

Set up data.world MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all data.world tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives data.world tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate data.world tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="data.world Agent",
            instructions="You have access to data.world tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package using `pip install openai-agents` and configure the HTTP stream. Instantiate `MCPServerStreamableHttp` with the Vinkius URL, then pass it to your Agent constructor using the `mcp_servers` list.

Yes. The agent uses `search_catalog` to run full-text queries across titles, descriptions, and tags. This lets the bot discover relevant datasets and projects during a live conversation.

The agent calls `get_my_profile` to check your account-level permissions and display name. If the agent tries to access a restricted dataset, the Vinkius endpoint enforces your token's read/write limits.

Yes, set `cacheToolsList=True` in your server parameters. This prevents the SDK from repeatedly querying the Vinkius endpoint for tool definitions, reducing latency during agent handovers.

Vinkius runs the server in an isolated V8 sandbox, meaning your SQL queries and API tokens never persist on disk. All traffic goes through an encrypted, ephemeral tunnel that closes the moment your agent finishes execution.

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